Network device and model learning method

Abstract

To provide a network device and a model learning method that allow quality information to be estimated with high accuracy.SOLUTION: A network device includes a group calculation unit that calculates first group information indicating the acquisition status for every packet groups, each of which includes a plurality of packets having a predetermined relationship, from the acquisition status at a capture device of packets transmitted from an application device to a terminal device via a network, and a model learning unit that generates a learning model by learning teacher data including the calculated first group information, first communication state information indicating the communication state of the packets in the network, and first quality information indicating quality about the output of the packets at the terminal device.SELECTED DRAWING: Figure 25

Description

[Technical field]

[0001] The present invention relates to a network device and a model learning method. [Background technology]

[0002] In a video distribution system (hereinafter also simply referred to as a video distribution system or an information processing system) that distributes video data to a terminal device via a network, communication state information that can be determined to have a large influence on quality information is identified based on a correlation between information indicating a communication state such as a delay time or a packet loss rate in a network (hereinafter also referred to as communication state information) and information indicating the playback quality of video data in a terminal device (hereinafter also referred to as quality information).The video distribution system then generates a learning model (hereinafter also simply referred to as a learning model) that can estimate quality information by learning the identified communication state information as an explanatory variable (see, for example, Patent Documents 1 and 2). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-193832 [Patent Document 2] JP 2018-137499 A Summary of the Invention [Problem to be solved by the invention]

[0004] Here, in the above-mentioned video distribution system, for example, the correlation between the timing when the communication state information changes in the network and the timing when the quality information changes in the terminal device may not be strong enough. Therefore, in the video distribution system, even if the above-mentioned learning model is used, for example, the quality information may not be estimated with high accuracy.

[0005] Therefore, in one aspect, the present invention has an object to provide a network device and a model learning method that enable quality information to be estimated with high accuracy. [Means for solving the problem]

[0006] In one aspect of the embodiment, the device includes a group calculation unit that calculates first group information indicating the acquisition status for each of a plurality of packet groups, each of which includes a plurality of packets having a predetermined relationship, from the acquisition status in a capture device of packets transmitted from an application device to a terminal device via a network, and a model learning unit that generates a learning model by learning teacher data including the calculated first group information, first communication status information indicating the communication status of the packets in the network, and first quality information indicating the quality of the output of the packets in the terminal device. Effect of the Invention

[0007] According to one aspect, it is possible to estimate quality information with high accuracy. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating the configuration of an information processing system 10. As shown in FIG. [Diagram 2] FIG. 2 is a diagram illustrating the configuration of the information processing system 10. As shown in FIG. [Diagram 3] FIG. 3 is a diagram illustrating the hardware configuration of the information processing device 1. As shown in FIG. [Figure 4] FIG. 4 is a diagram illustrating functions of the information processing device 1 in the first embodiment. [Diagram 5] FIG. 5 is a diagram illustrating functions of the information processing device 1 in the first embodiment. [Figure 6] FIG. 6 is a flow chart for explaining an outline of the learning process in the first embodiment. [Figure 7]FIG. 7 is a flowchart illustrating details of the learning process in the first embodiment. [Figure 8] FIG. 8 is a flowchart illustrating details of the learning process in the first embodiment. [Figure 9] FIG. 9 is a flowchart illustrating details of the learning process in the first embodiment. [Figure 10] FIG. 10 is a flowchart illustrating details of the learning process in the first embodiment. [Figure 11] FIG. 11 is a flowchart illustrating details of the learning process in the first embodiment. [Figure 12] FIG. 12 is a flowchart illustrating details of the learning process in the first embodiment. [Figure 13] FIG. 13 is a flowchart illustrating details of the learning process in the first embodiment. [Figure 14] FIG. 14 is a diagram for explaining a specific example of the quality information 132. As shown in FIG. [Figure 15] FIG. 15 is a diagram for explaining a specific example of the communication state information 133. As shown in FIG. [Figure 16] FIG. 16 is a diagram illustrating a specific example of the group communication information 134a. [Figure 17] FIG. 17 is a diagram illustrating a specific example of the group communication information 134a. [Figure 18] FIG. 18 is a diagram illustrating a specific example of the group communication information 134a. [Figure 19] FIG. 19 is a diagram illustrating a specific example of the group communication information 134a. [Figure 20] FIG. 20 is a diagram illustrating details of the learning process in the first embodiment. [Figure 21] FIG. 21 is a diagram illustrating a specific example of the group tally information 134b. [Figure 22] FIG. 22 is a diagram illustrating a specific example of the teacher data DT. [Diagram 23] FIG. 23 is a flowchart illustrating the estimation process in the first embodiment. [Figure 24] FIG. 24 is a diagram illustrating the estimation process in the first embodiment. [Diagram 25] FIG. 25 is a diagram illustrating the estimation process in the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. However, such descriptions should not be interpreted in a limiting sense and do not limit the subject matter described in the claims. In addition, various changes, substitutions, and modifications can be made without departing from the spirit and scope of the present disclosure. In addition, different embodiments can be appropriately combined.

[0010] [Configuration of the information processing system in the first embodiment] First, a description will be given of the configuration of the information processing system 10. Figures 1 and 2 are diagrams for explaining the configuration of the information processing system 10.

[0011] 1, the information processing system 10 includes, for example, an information processing device 1 (hereinafter also referred to as a network device 1), a video distribution device 2 (hereinafter also referred to as an application device 2), a capture device 3, a terminal device 4a, a terminal device 4b, and a terminal device 4c. Hereinafter, the terminal devices 4a, 4b, and 4c are collectively referred to simply as terminal devices 4. In addition, although the following description will be given of a case in which the information processing system 10 includes three terminal devices 4, the information processing system 10 may include, for example, a number of terminal devices 4 other than three.

[0012] The video distribution device 2 is, for example, a physical machine or a virtual machine, and is a device that distributes video data via a network NW.

[0013] The terminal device 4 is, for example, a terminal such as a PC (Personal Computer) or a smartphone used by a user (hereinafter also simply referred to as a user) who views video data, and outputs the video data distributed from the video distribution device 2 via the network NW to an output screen (not shown). Specifically, the terminal device 4 receives, for example, packets continuously transmitted from the video distribution device 2 via the network NW, and outputs the video data composed of each of the received packets to an output device.

[0014] The capture device 3, for example, captures a packet transmitted from the video distribution device 2 to the terminal device 4. Specifically, the capture device 3, for example, copies the packet transmitted from the video distribution device 2 to the terminal device 4 and captures the copied packet. Then, the capture device 3 transmits the captured packet to the information processing device 1, for example.

[0015] The network NW is, for example, a network including the Internet IN. Specifically, in the network NW, for example, at least a part of the connection between the video distribution device 2 and the terminal device 4 is made by wire. Also, in the network NW, for example, a part of the connection between the video distribution device 2 and the terminal device 4 may be made by wireless. Note that the wireless connection here may be, for example, a connection in accordance with the communication standard of the 5th Generation Mobile Communication System (5G).

[0016] More specifically, the network NW may include, for example, a core network (CN) 5 and a radio access network (Radio Access Network) 6, as shown in Fig. 2. The core network 5 may be connected to, for example, an Internet network IN and the radio access network 6 by wire. The radio access network 6 may be connected to, for example, each terminal device 4 by wireless. Furthermore, the capture device 3 may be installed between, for example, the core network 5 and the radio access network 6.

[0017] 1 and 2, a case will be described in which the capture device 3 is disposed between the video distribution device 2 and the terminal device 4 in the network NW, and the capture device 3 directly captures packets transmitted from the video distribution device 2 to the terminal device 4, but the present invention is not limited to this. Specifically, the packets transmitted from the video distribution device 2 to the terminal device 4 may be captured by a device such as a TAP (Terminal Access Point) disposed between the video distribution device 2 and the terminal device 4. The capture device 3 may capture the packets transmitted from the video distribution device 2 to the terminal device 4 by receiving the packets transmitted from the device such as the TAP.

[0018] The information processing device 1 is, for example, a physical machine or a virtual machine, and performs a process of generating a learning model using teacher data generated based on the acquisition status of packets in the capture device 3 (hereinafter, also referred to as a learning process).

[0019] Specifically, the information processing device 1 calculates group information (hereinafter also referred to as first group information) indicating the acquisition status of each of a plurality of groups (hereinafter also referred to as packet groups) each including a plurality of packets having a predetermined relationship from the acquisition status of a packet (hereinafter also referred to as a first packet) transmitted from the video distribution device 2 to the terminal device 4 via the network NW. The plurality of packets having the predetermined relationship are, for example, a plurality of packets used for playing video data in the same time period (for example, 10 seconds). Then, the information processing device 1 generates a learning model by learning teacher data including, for example, the calculated first group information, communication state information (hereinafter also referred to as first communication state information) indicating the communication state of the first packet in the network NW, and quality information (hereinafter also referred to as first quality information) indicating the quality related to the output of the first packet in the terminal device 4. The communication state information is, for example, KPI (Key Performance Indicator) such as delay time and packet loss rate for transmitting and receiving packets in the network NW. In addition, the quality information is, for example, QoE (Quality of Experience) in the terminal device 4.

[0020] Furthermore, the information processing device 1 performs a process of estimating quality information in the network NW (hereinafter also referred to as an estimation process) by using, for example, the learning model generated in the learning process.

[0021] Specifically, the information processing device 1 calculates group information (hereinafter also referred to as second group information) indicating the packet acquisition status for each of a plurality of packet groups from the acquisition status of packets (hereinafter also referred to as second packets) transmitted from the video distribution device 2 to the terminal device 4 via the network NW, for example, as in the case of the learning process. Then, the information processing device 1 acquires quality information (hereinafter also referred to as second quality information) output from the learning model in response to input of the calculated second group information and communication status information (hereinafter also referred to as second communication status information) indicating the communication status of the second packets in the network NW, for example. After that, the information processing device 1 outputs the acquired second quality information, for example.

[0022] That is, in the information processing device 1 of this embodiment, for example, when generating a learning model capable of estimating quality information, learning is performed using teacher data that includes not only communication state information and quality information, but also group information indicating the packet acquisition status for each of multiple packet groups.

[0023] As a result, the information processing device 1 in this embodiment is able to generate a learning model that can accurately estimate quality information such as QoE even when the correlation between the timing at which communication state information changes in the network NW and the timing at which a change in quality information occurs in the terminal device 4 is not sufficiently strong.

[0024] In the following, the learning process and the estimation process are performed in the same information processing device (information processing device 1), but the present invention is not limited to this. Specifically, the learning process and the estimation process may be performed in different information processing devices.

[0025] Further, the following description will be given of an information processing system 10 in which the source of packets sent to the terminal device 4 is the video distribution device 2 that distributes video data, but the present invention is not limited to this. Specifically, the information processing system 10 may be, for example, an information processing system in which the source of packets sent to the terminal device 4 is another information processing device (hereinafter also simply referred to as another information processing device) other than the video distribution device 2. More specifically, the information processing system 10 may be, for example, a telephone conference system that performs two-way communication of video data between the other information processing device and the terminal device 4, or a voice call system that performs two-way communication of voice data between the other information processing device and the terminal device 4.

[0026] [Hardware configuration of information processing device] Next, a description will be given of the hardware configuration of each information processing device 1. Fig. 3 is a diagram for explaining the hardware configuration of the information processing device 1.

[0027] 3, the information processing device 1 includes, for example, a CPU (Central Processing Unit) 101, which is a processor, a memory 102, a communication device (I / O interface) 103, and a storage device 104. Each unit is connected to each other via a bus 105.

[0028] The storage device 104 has, for example, a program storage area (not shown) that stores a program 110 for performing the learning process and the estimation process. The storage device 104 also has, for example, a storage unit 130 (hereinafter also referred to as information storage area 130) that stores information used when performing the learning process and the estimation process. The storage device 104 may be, for example, a hard disk drive (HDD) or a solid state drive (SSD).

[0029] The CPU 101 executes, for example, a program 110 loaded from the storage device 104 to the memory 102 to perform learning processing and estimation processing.

[0030] Furthermore, the communication device 103 communicates with, for example, the capture device 3 .

[0031] [Functions of the information processing device in the first embodiment] Next, a description will be given of functions of the information processing device 1 in the first embodiment. Figures 4 and 5 are diagrams for explaining functions of the information processing device 1 in the first embodiment.

[0032] As shown in FIG. 4, the information processing device 1 realizes various functions including a packet acquisition unit 111, an information acquisition unit 112, a communication analysis unit 113, a group calculation unit 114, a data generation unit 115, a model learning unit 116, an information estimation unit 117, and an information utilization unit 118 by organic cooperation between hardware such as a CPU 101 and a memory 102 and a program 110.

[0033] 5, for example, packets 131, quality information 132, communication state information 133, group information 134, teacher data DT, and learning model MD are stored in information storage area 130. Group information 134 includes, for example, group communication information 134a indicating the acquisition status of each packet 131 included in a plurality of packet groups, and group tally information 134b indicating the tally result of the acquisition status of packets 131 for each of a plurality of packet groups.

[0034] First, the functions in the learning process will be described.

[0035] The packet acquisition unit 111 receives, for example, packets transmitted from the capture device 3 (packets captured by the capture device 3). Then, the packet acquisition unit 111 extracts, for example, packets 131 transmitted from the video distribution device 2 from among the received packets. Thereafter, the packet acquisition unit 111 stores, for example, the extracted packets 131 in the information storage area 130. Specifically, the packet acquisition unit 111 stores, for example, the acquired packets 131 in the information storage area 130 in a state in which the terminal device 4 to which each packet 131 is sent and the session in which each packet 131 is transmitted and received can be identified.

[0036] More specifically, for example, for each packet transmitted from the capture device 3, the packet acquisition unit 111 determines whether each packet is a packet 131 transmitted from the video distribution device 2 from a combination of a source IP address included in an IP (Internet Protocol) header of each packet and a source port number included in a TCP (Transmission Control Protocol) header of each packet. Also, for each packet 131 determined to have been transmitted from the video distribution device 2, the packet acquisition unit 111 identifies the terminal device 4 to which each packet 131 is to be transmitted and the session in which each packet 131 is transmitted or received from a combination of a destination IP address included in an IP header of each packet 131 and a destination port included in a TCP header of each packet 131. Then, the packet acquisition unit 111 stores the packets 131 determined to have been transmitted from the video distribution device 2 in the information storage area 130 for each terminal device 4 and for each session.

[0037] The information acquiring unit 112 acquires, for example, for each terminal device 4 and for each session, quality information 132 for each session transmitted from each terminal device 4. Specifically, the information acquiring unit 112 acquires, for example, quality information 132 input by each user via their terminal device 4. Then, the information acquiring unit 112 stores the acquired quality information 132 in the information storage area 130, for example, for each terminal device 4 and for each session.

[0038] The communication analysis unit 113 generates communication state information 133 from the acquisition status of the packets 131 by the packet acquisition unit 111, for example, for each terminal device 4 and for each session. Then, the communication analysis unit 113 stores the generated communication state information 133 in the information storage area 130, for example, for each terminal device 4 and for each session.

[0039] Specifically, the communication analysis unit 113 may calculate, for example, for each terminal device 4 and for each session, the traffic volume per unit time of the packets 131 acquired by the packet acquisition unit 111 as the communication state information 133.

[0040] Furthermore, the communication analysis unit 113 may calculate, for example, for each terminal device 4 and for each session, the time between the timing when the packet 131 acquired by the packet acquisition unit 111 is transmitted from the video distribution device 2 and passes through the capture device 3 and the timing when the receipt acknowledgement (ACK: ACKnowledgement) of each packet 131 is transmitted from the terminal device 4 and passes through the capture device 3 (hereinafter also referred to as a response required time).The communication analysis unit 113 may calculate, for example, for each terminal device 4 and for each session, the time obtained by subtracting a predetermined threshold from the calculated response required time (hereinafter also referred to as a delay time) as the communication state information 133.

[0041] Furthermore, the communication analysis unit 113 may calculate, for example, for each terminal device 4 and for each session, a ratio of packets 131 whose receipt confirmation responses do not pass through the capture device 3 among packets 131 transmitted from the video distribution device 2 and passed through the capture device 3 (hereinafter also referred to as a packet loss rate).The communication analysis unit 113 may calculate, for example, for each terminal device 4 and for each session, the calculated ratio as communication state information 133.

[0042] The group calculation unit 114 generates group communication information 134a from the acquisition status of packets 131 by the packet acquisition unit 111, for example, for each terminal device 4 and for each session. Then, the group calculation unit 114 stores the generated group communication information 134a in the information storage area 130, for example, for each terminal device 4 and for each session.

[0043] Furthermore, the group calculation unit 114 generates group tally information 134b from the group communication information 134a corresponding to each packet group, for example, for each of the multiple packet groups. Then, the group calculation unit 114 stores the generated group tally information 134b in the information storage area 130, for example, for each of the multiple packet groups.

[0044] Specifically, for example, when RTP (Real Time Transport Protocol) is used as the communication protocol, the group calculation unit 114 refers to the timestamp included in the RTP header of each packet 131 received by the packet acquisition unit 111. Then, the group calculation unit 114 classifies each packet 131 into a plurality of packet groups so that, for example, one or more packets 131 having the same timestamp are included in the same packet group. After that, the group calculation unit 114 generates, for example, for each of the plurality of packet groups, group tally information 134b from group communication information 134a corresponding to each packet group.

[0045] Furthermore, for example, the group calculation unit 114 specifies the reception time of each packet 131 (for example, the reception time by the packet acquisition unit 111) for each packet 131 received by the packet acquisition unit 111 in the order of reception of each packet 131. Then, the group calculation unit 114 classifies each packet 131 into a plurality of packet groups such that, for example, a packet group is separated between two packets 131 whose reception time interval is equal to or greater than a predetermined threshold. That is, for example, when the difference between the reception time of each packet 131 and the reception time of the packet 131 received immediately before each packet 131 is less than a threshold, the group calculation unit 114 determines that each packet 131 and the packet 131 received immediately before each packet 131 are packets 131 included in the same packet group. On the other hand, for example, if the difference between the reception time of each packet 131 and the reception time of the packet 131 received immediately before each packet 131 is equal to or greater than a threshold, the group calculation unit 114 determines that each packet 131 and the packet 131 received immediately before each packet 131 are packets 131 included in different packet groups.

[0046] Furthermore, for example, when TCP (Transmission Control Protocol) is used as a communication protocol, the group calculation unit 114 refers to the PSH flag included in the TCP header of each packet 131 for each packet 131 received by the packet acquisition unit 111 in the order in which each packet 131 is received. Then, the group calculation unit 114 classifies each packet 131 into a plurality of packet groups such that, for example, a packet group is delimited between a packet 131 whose PSH flag is "0" and a packet 131 received immediately after the packet 131 whose PSH flag is "0". That is, for example, when the PUSH flag of each packet 131 is "1", the group calculation unit 114 determines that each packet 131 and the packet 131 received immediately after each packet 131 are packets 131 included in the same packet group. On the other hand, for example, when the PUSH flag of each packet 131 is “0”, the group calculation unit 114 determines that each packet 131 and the packet 131 received immediately after each packet 131 belong to different packet groups.

[0047] Furthermore, the group calculation unit 114, for example, identifies the packet size of each packet 131 for each packet 131 received by the packet acquisition unit 111 in the order of reception of each packet 131. Then, the group calculation unit 114 classifies each packet 131 into a plurality of packet groups so that, for example, a packet 131 whose packet size is a fraction (a number less than the maximum size of the packet 131) and a packet 131 received immediately after the packet 131 whose packet size is a fraction are delimited into packet groups. That is, for example, when the packet size of each packet 131 is not a fraction, the group calculation unit 114 determines that each packet 131 and the packet 131 received immediately after each packet 131 are packets 131 included in the same packet group. On the other hand, when the packet size of each packet 131 is a fraction, for example, the group calculation unit 114 determines that each packet 131 and the packet 131 received immediately after each packet 131 are packets 131 included in different packet groups.

[0048] The data generation unit 115 generates a plurality of pieces of teacher data DT each including, for example, the quality information 132 acquired by the information acquisition unit 112, the communication state information 133 generated by the communication analysis unit 113, and the group tally information 134b calculated by the group calculation unit 114. Then, the data generation unit 115 stores the generated plurality of pieces of teacher data DT in the information storage area 130, for example.

[0049] Specifically, the data generation unit 115 generates multiple pieces of teacher data DT so that, for example, quality information 132, communication status information 133, and group summary information 134b corresponding to the same terminal device 4 and the same session and indicating each state at the same timing (same time period) are included in the same teacher data DT.

[0050] The model learning unit 116 generates a learning model MD, for example, by learning a plurality of pieces of teacher data DT generated by the data generation unit 115. Then, the model learning unit 116 stores the generated learning model MD in the information storage area 130, for example.

[0051] Next, the functions in the estimation process will be described.

[0052] The packet acquisition unit 111 extracts and acquires new packets 131 transmitted from the video distribution device 2, for example, from among new packets transmitted from the capture device 3. Then, the packet acquisition unit 111 stores the acquired new packets 131 in the information storage area 130, for example, for each terminal device 4 and for each session.

[0053] The communication analysis unit 113 generates new communication state information 133 from the acquisition status of the new packet 131 by the packet acquisition unit 111, for example, for each terminal device 4 and for each session. Then, the communication analysis unit 113 stores the generated new communication state information 133 in the information storage area 130, for example, for each terminal device 4 and for each session.

[0054] The group calculation unit 114 generates new group communication information 134a from the acquisition status of new packets 131 by the packet acquisition unit 111, for example, for each terminal device 4 and for each session. Then, the group calculation unit 114 stores the generated new group communication information 134a in the information storage area 130, for example, for each terminal device 4 and for each session.

[0055] Furthermore, the group calculation unit 114 generates new group tally information 134b from the new group communication information 134a corresponding to each packet group, for example, for each of the multiple packet groups. Then, the group calculation unit 114 stores the generated new group tally information 134b in the information storage area 130, for example, for each of the multiple packet groups.

[0056] The information estimation unit 117 inputs, for example, new communication state information 133 generated by the communication analysis unit 113 and new group tally information 134b calculated by the group calculation unit 114 to the learning model MD. Then, the information estimation unit 117 acquires, for example, new quality information 132 output from the learning model MD.

[0057] Specifically, the information estimation unit 117 inputs, for example, new communication state information 133 and new group tally information 134b corresponding to the same terminal device 4 and the same session and indicating each state at the same timing into the learning model MD.

[0058] The information using unit 118 controls each network device (not shown) included in the information processing system 10 based on the new quality information 132 acquired by the information estimating unit 117, for example.

[0059] Specifically, for example, when the quality information 132 acquired by the information estimation unit 117 does not satisfy a predetermined quality condition (hereinafter also simply referred to as the quality condition), the information utilization unit 118 may change various settings of each network device included in the information processing system 10 (for example, the wireless access network 6 shown in FIG. 2) so that the quality information 132 satisfies the quality condition.

[0060] Furthermore, the information using unit 118 outputs, for example, the new quality information 132 acquired by the information estimating unit 117 to an operation terminal (not shown) that is viewed by the administrator of the information processing device 1 (hereinafter also simply referred to as the administrator).

[0061] [Outline of learning process in the first embodiment] Next, an outline of the first embodiment will be described with reference to Fig. 6, which is a flow chart for explaining an outline of the learning process in the first embodiment.

[0062] As shown in FIG. 6, the information processing device 1 calculates group information 134 indicating the acquisition status of packets 131 for each of a plurality of packet groups from the acquisition status of packets 131 transmitted from the video distribution device 2 to the terminal device 4 via the network NW (S1).

[0063] Then, the information processing device 1 generates a learning model MD by learning teacher data DT including, for example, group information 134 calculated in the processing of S1, communication status information 133 indicating the communication status of the packet 131 in the network NW, and quality information 132 indicating the quality related to the output of the packet 131 in the terminal device 4 (S2).

[0064] As a result, the information processing device 1 in this embodiment is able to generate a learning model MD capable of accurately estimating quality information 132 such as QoE even when, for example, there is not a sufficiently strong correlation between the timing at which communication state information 133 changes in the network NW and the timing at which a change in quality information 132 occurs in the terminal device 4.

[0065] [Details of the learning process in the first embodiment] Next, the learning process in the first embodiment will be described in detail. Fig. 7 to Fig. 13 are flow charts for explaining the learning process in the first embodiment in detail. Fig. 14 to Fig. 22 are diagrams for explaining the learning process in the first embodiment in detail.

[0066] [Packet acquisition process] First, a process of acquiring the packet 131 captured by the capture device 3 (hereinafter, also referred to as a packet acquisition process) will be described in the learning process. Fig. 7 is a flow chart for explaining the packet acquisition process.

[0067] As shown in FIG. 7, the packet acquisition unit 111 waits until it receives a packet transmitted from the capture device 3 (NO in S11).

[0068] Then, when a packet transmitted from the capture device 3 is received (YES in S11), the packet acquisition unit 111 determines, for example, whether the received packet is a packet 131 transmitted from the video distribution device 2 (S12).

[0069] Specifically, the packet acquisition unit 111 determines, for example, whether the combination of the source IP address contained in the IP header of the packet received in the processing of S11 and the source port number contained in the TCP header is a combination of an IP address and a port number corresponding to the video distribution device 2.

[0070] As a result, if it is determined that the packet received in the processing of S11 is a packet 131 sent from the video distribution device 2 (YES in S12), the packet acquisition unit 111 identifies, for example, the terminal device 4 that is the destination of the packet 131 received in the processing of S11 and the session in which the packet 131 received in the processing of S11 is sent and received (S13).

[0071] Specifically, the packet acquisition unit 111 identifies the terminal device 4 and the session corresponding to the combination of the destination IP address included in the IP header and the destination port number included in the TCP header of the packet 131 received in the process of S11, for example.

[0072] Then, the packet acquisition unit 111 stores, for example, the packet 131 received in the process of S11 in the information storage area 130 in association with the identification information of the terminal device 4 and the session identified in the process of S13 (S14).

[0073] On the other hand, if it is determined in the process of S11 that the packet received is the packet 131 transmitted from the moving image distribution device 2 (NO in S12), the packet acquisition unit 111 does not perform the process of S13 and the process of S14, for example.

[0074] [Information acquisition process] Next, the process of acquiring the quality information 132 (hereinafter, also referred to as information acquisition process) of the learning process will be described. Fig. 8 is a flow chart for explaining the information acquisition process.

[0075] As shown in FIG. 8, the information acquisition unit 112 waits until it receives the quality information 132 transmitted from the terminal device 4 (NO in S21).

[0076] Specifically, the information acquiring unit 112 waits, for example, until the user inputs the quality information 132 for each terminal device 4 and for each session via the terminal device 4. Note that the user inputs the quality information 132 for each terminal device 4 and for each session at predetermined time intervals (for example, every minute).

[0077] Then, when the quality information 132 transmitted from the terminal device 4 is received (YES in S21), the information acquisition unit 112 stores, for example, the received quality information 132 in the information storage area 130 (S22).

[0078] Specifically, the information acquiring unit 112 stores, for example, the quality information 132 received in the process of S21 in association with the identification information of the terminal device 4 and the session to which the quality information 132 received in the process of S21 was transmitted in the information storage area 130. A specific example of the quality information 132 will be described below.

[0079] [Specific examples of quality information] Fig. 14 is a diagram for explaining a specific example of the quality information 132. Specifically, Fig. 14 is a diagram for explaining a specific example of the quality information 132 stored in the information storage area .

[0080] 14 has, for example, items such as "Time" in which each time is set, "QoE" in which the QoE at each time is set, "Terminal ID" in which identification information of the terminal device 4 corresponding to each QoE is set, and "Session ID" in which identification information of the session corresponding to each QoE is set. For example, "5", "4", "3", "2", or "1" is set in order of decreasing quality to "QoE".

[0081] Specifically, in the first line of quality information 132 shown in FIG. 14, for example, “12:02:00” is set as “Time”, “5” is set as “QoE”, “T001” is set as “Terminal ID”, and “S001” is set as “Session ID”.

[0082] That is, the information in the first row of the quality information 132 shown in FIG. 14 indicates, for example, that the QoE corresponding to a session with a session ID of S001 in terminal device 4 with a terminal ID of T001 at 12:02:00 is 5.

[0083] In addition, in the information on the second line of the quality information 132 shown in FIG. 14, for example, “12:05:00” is set as the “Time”, “1” is set as the “QoE”, “T002” is set as the “Terminal ID”, and “S002” is set as the “Session ID”.

[0084] That is, the information in the second row of the quality information 132 shown in Fig. 14 indicates that, for example, among the QoEs corresponding to a session with a session ID of S002 in a terminal device 4 with a terminal ID of T002, the QoE at the time of 12:05:00 is 1. Description of other information included in Fig. 14 will be omitted.

[0085] [First information generation process] Next, the process of generating communication state information 133 (hereinafter, also referred to as first information generating process) of the learning process will be described. Fig. 9 is a flow chart for explaining the first information generating process.

[0086] 9, the communication analysis unit 113 waits until the first information generation timing comes (NO in S31), for example. The first information generation timing may be a regular timing such as every minute.

[0087] Then, when the first information generation timing arrives (YES in S31), the communication analysis unit 113 generates communication status information 133 (S32) by, for example, using each packet 131 stored in the information storage area 130 that was transmitted from the capture device 3 between the previous first information generation timing (for example, one minute ago) and the current first information generation timing.

[0088] Thereafter, the communication analysis unit 113 stores, for example, the communication state information 133 generated in the process of S32 in the information storage area 130 (S33). A specific example of the communication state information 133 will be described below.

[0089] [Examples of communication status information] Fig. 15 is a diagram for explaining a specific example of the communication state information 133. Specifically, Fig. 15 is a diagram for explaining a specific example of the communication state information 133 stored in the information storage area .

[0090] The communication status information 133 shown in FIG. 15 has, for example, items such as a "terminal ID" in which identification information of each terminal device 4 is set, a "session ID" in which identification information of each session is set, a "time" in which each time is set, a "delay time" in which the delay time for sending and receiving packets 131 at each time is set, a "loss rate" in which the packet loss rate of packets 131 at each time is set, and a "traffic volume" in which the traffic volume at each time is set.

[0091] Specifically, in the information in the first line of the communication status information 133 shown in FIG. 15, for example, "T001" is set as the "Terminal ID," "S001" is set as the "Session ID," "12:01:00" is set as the "Time," "0 (ms)" is set as the "Delay time," "0 (%)" is set as the "Loss rate," and "5.1 (Mbps)" is set as the "Traffic volume."

[0092] In addition, in the information on the fourth line of the communication status information 133 shown in Fig. 15, for example, "T001" is set as the "terminal ID", "S001" is set as the "session ID", "12:04:00" is set as the "time", "2.0 (ms)" is set as the "delay time", "0.2 (%)" is set as the "loss rate", and "2.2 (Mbps)" is set as the "traffic volume". Explanation of other information included in Fig. 15 will be omitted.

[0093] [Second information generation process] Next, the process of generating group communication information 134a (hereinafter, also referred to as second information generating process) of the learning process will be described. Fig. 10 is a flow chart illustrating the second information generating process.

[0094] 10, the group calculation unit 114 waits until the second information generation timing comes (NO in S41). The second information generation timing may be a regular timing such as every minute. Specifically, the second information generation timing may be the same timing as the first information generation timing, for example.

[0095] Then, when the second information generation timing arrives (YES in S41), the group calculation unit 114 classifies, for example, among the packets 131 stored in the information storage area 130, each packet 131 transmitted from the capture device 3 between the previous second information generation timing (for example, one minute ago) and the current second information generation timing into multiple packet groups (S42).

[0096] Specifically, for example, when RTP is adopted as the communication protocol, the group calculation unit 114 refers to the timestamp included in the RTP header of each packet 131 received by the packet acquisition unit 111 in the order in which each packet 131 is received. Then, the group calculation unit 114 specifies, for example, each of the packets 131 having the same timestamp as packets 131 included in the same packet group. Hereinafter, the process of classifying each packet 131 into a plurality of packet groups using the timestamp of each packet 131 is also referred to as a first classification process.

[0097] Furthermore, for example, the group calculation unit 114 identifies the reception time of each packet 131 (for example, the reception time by the packet acquisition unit 111) for each packet 131 received by the packet acquisition unit 111 in the order of reception of each packet 131. Then, the group calculation unit 114 identifies, for example, two packets 131 whose reception time interval is longer than a threshold value as a separator of a packet group. Hereinafter, the process of classifying each packet 131 into a plurality of packet groups using the reception time of each packet 131 is also referred to as a second classification process.

[0098] Furthermore, for example, when TCP is adopted as the communication protocol, the group calculation unit 114 refers to the PSH flag included in the TCP header of each packet 131 received by the packet acquisition unit 111 in the order in which each packet 131 is received. Then, the group calculation unit 114 specifies, for example, a packet 131 whose PSH flag is "0" and a packet 131 received immediately after the packet 131 whose PSH flag is "0" as a boundary between packet groups. Hereinafter, the process of classifying each packet 131 into a plurality of packet groups using the PSH flag of each packet 131 is also referred to as a third classification process.

[0099] Furthermore, for example, the group calculation unit 114 specifies the packet size of each packet 131 for each packet 131 received by the packet acquisition unit 111 in the order in which each packet 131 was received. Then, for example, the group calculation unit 114 specifies, as a boundary between a packet 131 whose packet size is a fraction (a number less than the maximum packet size) and a packet 131 received immediately after the packet 131 whose packet size is a fraction, as a boundary between packet groups. Hereinafter, the process of classifying each packet 131 into a plurality of packet groups using the packet size of each packet 131 is also referred to as a fourth classification process.

[0100] Next, the group calculation unit 114 generates group communication information 134a for each of the multiple packet groups into which the packets 131 are classified in the process of S42 (S43).

[0101] Thereafter, the group calculation section 114 stores, for example, the group communication information 134a generated in the process of S43 in the information storage area 130 (S44).

[0102] The second information generation timing may be, for example, the timing when the packet acquisition unit 111 receives the packet 131 in the process of S11. That is, the group calculation unit 114 may generate group communication information 134a for the received packet 131 in response to the packet acquisition unit 111 receiving the packet 131 in the process of S11. A specific example of the group communication information 134a will be described below.

[0103] [Examples of group communication information] 16 to 19 are diagrams for explaining a specific example of the group communication information 134a. Specifically, FIG. 16 is a diagram for explaining a specific example of the group communication information 134a when the first classification process is performed in the process of S42. FIG. 17 is a diagram for explaining a specific example of the group communication information 134a when the second classification process is performed in the process of S42. FIG. 18 is a diagram for explaining a specific example of the group communication information 134a when the third classification process is performed in the process of S42. FIG. 19 is a diagram for explaining a specific example of the group communication information 134a when the fourth classification process is performed in the process of S42.

[0104] The group communication information 134a shown in FIG. 16 and the like has, as items, for example, a "terminal ID" in which identification information of each terminal device 4 is set, a "session ID" in which identification information of each session is set, and a "classification type" in which identification information of the classification process performed in the process of S42 is set. In the "classification type", for example, a "timestamp" indicating the first classification process, a "packet interval" indicating the second classification process, a "PSH flag" indicating the third classification process, or a "packet length" indicating the fourth classification process is set. In addition, the group communication information 134a shown in FIG. 16 and the like has, as items, for example, a "packet length" in which the packet length (packet size) of each packet 131 is set, a "timestamp" in which the time when each packet 131 was generated in the video distribution device 2 is set, and a "PSH flag" in which the PSH flag of each packet 131 is set. 16 and the like includes, for example, items of "received time" in which the received time of each packet 131 in the information processing device 1 is set, and "group" in which identification information of the packet group including each packet 131 is set. Note that the following description will be given assuming that "-" is set in items in which no information is set.

[0105] [Specific examples of group communication information when the first classification process is performed] First, the group communication information 134a in the case where the first classification process has been performed in the process of S42 will be described.

[0106] In the group communication information 134a shown in FIG. 16, for example, the information in the first line has "T001" set as the "Terminal ID," "S001" set as the "Session ID," "Timestamp" set as the "Classification Type," "500 (bytes)" set as the "Packet Length," "12:00:00" set as the "Timestamp," "-" set as the "PSH Flag," "12:00:01" set as the "Receipt Time," and "1A" set as the "Group."

[0107] Also, in the group communication information 134a shown in FIG. 16, for example, the information on the second line has "T001" set as the "terminal ID," "S001" set as the "session ID," "timestamp" set as the "classification type," "500 (bytes)" set as the "packet length," "12:00:00" set as the "timestamp," "-" set as the "PSH flag," "12:00:02" set as the "received time," and "1A" set as the "group."

[0108] 16, for example, in the information on the fifth line, "T001" is set as the "terminal ID", "S001" is set as the "session ID", "timestamp" is set as the "classification type", "500 (bytes)" is set as the "packet length", "12:00:10" is set as the "timestamp", "-" is set as the "PSH flag", "12:00:11" is set as the "received time", and "1B" is set as the "group". Other information included in FIG. 16 will be omitted.

[0109] That is, in the group communication information 134a shown in Fig. 16, for example, the same time (12:00:00) is set in the "timestamp" of each piece of information from the first line to the fourth line. Therefore, as shown in Fig. 16, the group calculation unit 114 sets "1A", which is information indicating the same packet group, in the "group" of each piece of information from the first line to the fourth line.

[0110] 16, for example, the same time (12:00:10) is set in the "timestamp" of each piece of information from the fifth line to the seventh line. Therefore, as shown in FIG 16, the group calculation unit 114 sets "1B", which is information indicating the same packet group, in the "group" of each piece of information from the fifth line to the seventh line.

[0111] [Specific examples of group communication information when the second classification process is performed] Next, the group communication information 134a in the case where the second classification process has been performed in the process of S42 will be described.

[0112] In the group communication information 134a shown in FIG. 17, for example, in the information on the first line, "T002" is set as the "Terminal ID," "S002" is set as the "Session ID," "Packet Interval" is set as the "Classification Type," "750 (bytes)" is set as the "Packet Length," "-" is set as the "Time Stamp," "-" is set as the "PSH Flag," "12:00:01" is set as the "Receipt Time," and "2A" is set as the "Group."

[0113] Also, in the group communication information 134a shown in FIG. 17, for example, in the information on the fourth line, "T002" is set as the "Terminal ID," "S002" is set as the "Session ID," "Packet Interval" is set as the "Classification Type," "750 (bytes)" is set as the "Packet Length," "-" is set as the "Time Stamp," "-" is set as the "PSH Flag," "12:00:04" is set as the "Receipt Time," and "2A" is set as the "Group."

[0114] 17, for example, in the information on the fifth line, "T002" is set as the "terminal ID," "S002" is set as the "session ID," "packet interval" is set as the "classification type," "750 (bytes)" is set as the "packet length," "-" is set as the "timestamp," "-" is set as the "PSH flag," "12:00:11" is set as the "received time," and "2B" is set as the "group." Other information included in FIG. 17 will be omitted.

[0115] That is, in the group communication information 134a shown in Fig. 17, for example, the interval between the "received time" of the information on the fourth line and the "received time" of the information on the fifth line is 7 (seconds). Therefore, for example, when the interval between the "received time" of the information on the fourth line and the "received time" of the information on the fifth line, which is 7 (seconds), is equal to or greater than a predetermined threshold, the group calculation unit 114 sets "2A", which is information indicating the same packet group, to the "group" of each piece of information from the first line to the fourth line, as shown in Fig. 17.

[0116] 17, for example, the interval between the "received time" of the information on the seventh line and the "received time" of the information on the eighth line is 8 (seconds). Therefore, for example, when the interval between the "received time" of the information on the seventh line and the "received time" of the information on the eighth line, which is 8 (seconds), is equal to or greater than a predetermined threshold, the group calculation unit 114 sets "2B", which is information indicating the same packet group, to the "group" of each piece of information from the fifth line to the seventh line, as shown in FIG.

[0117] [Specific examples of group communication information when the third classification process is performed] Next, the group communication information 134a in the case where the third classification process has been performed in the process of S42 will be described.

[0118] In the group communication information 134a shown in FIG. 18, for example, the information in the first line has "T003" set as the "Terminal ID," "S003" set as the "Session ID," "PSH Flag" set as the "Classification Type," "1500 (bytes)" set as the "Packet Length," "-" set as the "Time Stamp," "Yes" set as the "PSH Flag," "12:00:01" set as the "Receipt Time," and "3A" set as the "Group."

[0119] Also, in the group communication information 134a shown in FIG. 18, for example, the information on the fourth line has "T003" set as the "Terminal ID," "S003" set as the "Session ID," "PSH Flag" set as the "Classification Type," "1500 (bytes)" set as the "Packet Length," "-" set as the "Time Stamp," "None" set as the "PSH Flag," "12:00:04" set as the "Receipt Time," and "3A" set as the "Group."

[0120] 18, for example, in the information on the fifth line, "T003" is set as the "terminal ID", "S003" is set as the "session ID", "PSH flag" is set as the "classification type", "1500 (bytes)" is set as the "packet length", "-" is set as the "time stamp", "Yes" is set as the "PSH flag", "12:00:11" is set as the "received time", and "3B" is set as the "group". Other information included in FIG. 18 will be omitted.

[0121] That is, in the group communication information 134a shown in Fig. 18, for example, the "PSH flag" of each piece of information from the first to third rows is set to "Yes", and the "PSH flag" of the information in the fourth row is set to "No". Therefore, as shown in Fig. 18, the group calculation unit 114 sets, for example, the "group" of each piece of information from the first to fourth rows to "3A", which is information indicating the same packet group.

[0122] 18, for example, the "PSH flag" of each piece of information in the fifth and sixth rows is set to "Yes," and the "PSH flag" of the information in the seventh row is set to "No." Therefore, the group calculation unit 114 sets, for example, the "group" of each piece of information in the fifth to seventh rows to "3B," which is information indicating the same packet group, as shown in FIG.

[0123] [Specific examples of group communication information when classification 4 processing is performed] Next, the group communication information 134a in the case where the fourth classification process has been performed in the process of S42 will be described.

[0124] In the group communication information 134a shown in FIG. 19, for example, in the information in the first line, "T004" is set as the "Terminal ID", "S004" is set as the "Session ID", "Packet length" is set as the "Classification type", "Packet length" is set as "1000 (bytes)", "Time stamp" is set as "-", "PSH flag" is set as "-", "Receipt time" is set as "12:00:01", and "Group" is set as "4A".

[0125] Also, in the group communication information 134a shown in FIG. 19, for example, in the information on the fourth line, "T004" is set as the "Terminal ID", "S004" is set as the "Session ID", "Packet length" is set as the "Classification type", "Packet length" is set as "200 (bytes)", "Time stamp" is set as "-", "PSH flag" is set as "-", "Receipt time" is set as "12:00:04", and "Group" is set as "4A".

[0126] 19, for example, in the information on the fifth line, "T004" is set as the "terminal ID", "S004" is set as the "session ID", "packet length" is set as the "classification type", "1000 (bytes)" is set as the "packet length", "-" is set as the "timestamp", "-" is set as the "PSH flag", "12:00:11" is set as the "received time", and "4B" is set as the "group". Other information included in FIG. 19 will be omitted.

[0127] That is, in the group communication information 134a shown in Fig. 19, for example, "1000 (bytes)" is set in the "packet length" of each piece of information from the first to third lines, and "200 (bytes)" is set in the "packet length" of the information in the fourth line. Therefore, as shown in Fig. 19, for example, the group calculation unit 114 sets "4A", which is information indicating the same packet group, in the "group" of each piece of information from the first to fourth lines.

[0128] 19, for example, "1000 (bytes)" is set in the "packet length" of each piece of information in the fifth and sixth rows, and "200 (bytes)" is set in the "packet length" of the information in the seventh row. Therefore, as shown in FIG 19, the group calculation unit 114 sets "4B", which is information indicating the same packet group, in the "group" of each piece of information in the fifth to seventh rows.

[0129] [Third information generation process] Next, the process of generating group tally information 134b (hereinafter also referred to as third information generation process) of the learning process will be described. Figures 11 and 12 are flow charts explaining the third information generation process. Note that the following description will be given assuming that the group communication information 134a generated in the second information generation process is the group communication information 134a explained in Figure 16.

[0130] 11, the group calculation unit 114 waits until the third information generation timing comes (NO in S51). The third information generation timing may be a regular timing such as every minute. Specifically, the third information generation timing may be, for example, the timing immediately after the second information generation timing.

[0131] Then, when the third information generation timing arrives (YES in S51), the group calculation unit 114 initializes, for example, the total amount of data stored in the information storage area 130 (S52). Specifically, the group calculation unit 114 sets, for example, the total amount of data stored in the information storage area 130 to 0 (bytes).

[0132] Then, the group calculation section 114 identifies, for example, one piece of information included in the group communication information 134a stored in the information storage area 130 (S53).

[0133] Specifically, for example, when the process of S53 is performed for the first time, the group calculation unit 114 identifies the information in the first row of the group communication information 134a described with reference to FIG.

[0134] Next, the group calculation unit 114 adds, for example, the packet length included in the information identified in the process of S53 to the total data amount (S54).

[0135] Specifically, "500 (bytes)" is set in the "packet length" of the information in the first line of group communication information 134a described in Fig. 16. Therefore, for example, when the information identified in the process of S53 is the information in the first line of group communication information 134a described in Fig. 16, group calculation unit 114 adds "500 (bytes)" to the value indicated by the total amount of data stored in information storage area 130.

[0136] Next, the group computation unit 114 determines whether or not the packet 131 indicated by the information identified in the process of S53 is the first packet 131 in the packet group (hereinafter also referred to as the initial packet 131) (S55).

[0137] Specifically, the group calculation unit 114, for example, refers to the group communication information 134a stored in the information storage area 130, and compares the times set in the "received time" of each piece of information in which the information set in the "group" is the same as the information identified in the processing of S53. Then, the group calculation unit 114 determines whether or not the time set in the "received time" of the information identified in the processing of S53 is the earliest time.

[0138] As a result, when it is determined that the packet 131 indicated by the information specified in the process of S53 is the initial packet 131 (YES in S55), the group calculation unit 114, for example, calculates a group no communication time corresponding to the packet 131 indicated by the information specified in the process of S53, and stores the calculated group no communication time in the information storage area 130 as a part of the group tally information 134b (S56). The group no communication time is, for example, the time between the reception time of the packet 131 received immediately before the packet 131 indicated by the information specified in the process of S53 and the reception time of the packet 131 indicated by the information specified in the process of S53. In other words, the group no communication time is, for example, the time between the reception time of the last packet 131 (hereinafter also referred to as the final packet 131) in the packet group received immediately before the packet group including the packet 131 indicated by the information specified in the process of S53, and the reception time of the initial packet 131 included in the packet group including the packet 131 indicated by the information specified in the process of S53.

[0139] In this case, the group calculation unit 114 calculates a group interval time corresponding to the packet 131 indicated by the information specified in the process of S53, and stores the calculated group interval time in the information storage area 130 as a part of the group tally information 134b (S57). The group interval time is, for example, the time between the reception time of the first packet 131 in the packet group received immediately before the packet group including the packet 131 indicated by the information specified in the process of S53 and the reception time of the packet 131 indicated by the information specified in the process of S53. In other words, the group interval time is, for example, the time between the reception time of the first packet 131 in the packet group received immediately before the packet group including the packet 131 indicated by the information specified in the process of S53 and the reception time of the first packet 131 in the packet group including the packet 131 indicated by the information specified in the process of S53.

[0140] On the other hand, if it is determined in the processing of S55 that the packet 131 indicated by the information identified in the processing of S53 is not the initial packet 131 (NO in S55), the group calculation unit 114 determines, for example, as shown in FIG. 12, whether or not the packet 131 indicated by the information identified in the processing of S53 is the final packet 131 included in the packet group (S61).

[0141] Specifically, the group calculation unit 114, for example, refers to the group communication information 134a stored in the information storage area 130, and compares the times set in the "received time" of each piece of information in which the information set in the "group" is the same as the information identified in the processing of S53. Then, the group calculation unit 114 determines whether the time set in the "received time" of the information identified in the processing of S53 is the last time.

[0142] As a result, when it is determined that the packet 131 indicated by the information specified in the process of S53 is the last packet 131 (YES in S61), the group calculation unit 114 calculates, for example, a group transmission time corresponding to the packet 131 indicated by the information specified in the process of S53, and stores the calculated group transmission time in the information storage area 130 as a part of the group tally information 134b (S62). The group transmission time is, for example, the time between the reception time of the first packet 131 in the packet group including the packet 131 indicated by the information specified in the process of S53 and the reception time of the packet 131 indicated by the information specified in the process of S53. In other words, the group transmission time is, for example, the time between the reception time of the first packet 131 in the packet group including the packet 131 indicated by the information specified in the process of S53 and the reception time of the last packet 131 in the packet group including the packet 131 indicated by the information specified in the process of S53.

[0143] In this case, the group calculation section 114 stores, for example, the total amount of data stored in the information storage area 130 as a part of the group tally information 134b in the information storage area 130 (S63).

[0144] Thereafter, the group calculation unit 114 initializes, for example, the total amount of data stored in the information storage area 130 (S64). Specifically, the group calculation unit 114 sets, for example, the total amount of data stored in the information storage area 130 to 0 (bytes).

[0145] On the other hand, if it is determined that the packet 131 indicated by the information identified in the process of S53 is not the last packet 131 (NO in S61), the group calculation unit 114 does not perform the processes from S62 to S64, for example.

[0146] Then, the group calculation unit 114 judges whether or not all information has been identified in the process of S53 (S58). Note that the group calculation unit 114 also performs the process of S58 after the process of S57.

[0147] As a result, when it is determined that not all of the information has been specified in the process of S53 (NO in S58), the group calculation section 114 performs, for example, the process of S53 and subsequent processes again.

[0148] On the other hand, when it is determined in the process of S53 that all information has been identified (YES in S58), the group calculation section 114 ends, for example, the third information generation process. A specific example of the third information generation process will be described below.

[0149] [Specific example of the third information generation process] Fig. 20 is a diagram for explaining a specific example of the third information generation process. In addition, the horizontal axis in the graph shown in Fig. 20 corresponds to time. In addition, the vertical axis in the graph shown in Fig. 20 corresponds to the communication data amount (packet length of the packet 131) in the network NW.

[0150] Specifically, the example shown in FIG. 20 shows, for example, a packet group Ga and a packet group Gb received immediately after the packet group Ga.

[0151] Then, for example, if the packet 131 corresponding to the information identified in the processing of S53 is the initial packet 131 (hereinafter also referred to as packet 131c) included in the packet group Gb, the group calculation unit 114 calculates the time t1 between the reception time of the final packet 131 (hereinafter also referred to as packet 131b) included in the packet group Ga and the reception time of packet 131c as the group no-communication time (S56).

[0152] Also, for example, if the packet 131 corresponding to the information identified in the processing of S53 is packet 131c, the group calculation unit 114 calculates the time t2 between the reception time of the initial packet 131 (hereinafter also referred to as packet 131a) included in the packet group Ga and the reception time of packet 131c as the group interval time (S57).

[0153] Also, for example, if the packet 131 corresponding to the information identified in the processing of S53 is the final packet 131 (hereinafter also referred to as packet 131d) included in the packet group Gb, the group calculation unit 114 calculates the time t3 between the reception time of packet 131c and the reception time of packet 131d as the group transmission time (S62).

[0154] [Examples of group aggregate information] Next, a specific example of the group tally information 134b will be described. Fig. 21 is a diagram for explaining a specific example of the group tally information 134b.

[0155] Group tally information 134b shown in FIG. 21 has, for example, items such as "group" in which identification information for each packet group is set, "total data amount" in which the total data amount corresponding to each packet group is set, "group no communication time" in which the group no communication time corresponding to each packet group is set, "group interval time" in which the group interval time corresponding to each packet group is set, and "group transmission time" in which the group transmission time corresponding to each packet group is set.

[0156] Specifically, in the group summary information 134b shown in FIG. 21, for example, in the first line, the "group" is set to "1A," the "total data volume" is set to "5000 (bytes)," the "group no communication time" is set to "400 (ms)," the "group interval time" is set to "500 (ms)," and the "group transmission time" is set to "100 (ms)."

[0157] 21, for example, in the second line, "1B" is set as "group", "total data amount" is set as "3000 (bytes)", "group no communication time" is set as "100 (ms)", "group interval time" is set as "500 (ms)", and "group transmission time" is set as "400 (ms)". Other information included in FIG. 21 is omitted.

[0158] [Main process of learning process] Next, the main process of the learning process (hereinafter, simply referred to as the main process) will be described with reference to FIG 13.

[0159] 13, the data generation unit 115 waits until the learning timing (NO in S71), for example. The learning timing may be the timing when the administrator inputs information to the information processing device 1 to generate the learning model MD, for example.

[0160] Then, when it is time to learn (YES in S71), the data generation unit 115 generates a plurality of pieces of teacher data DT each including, for example, the quality information 132, the communication state information 133, and the group tally information 134b stored in the information storage area 130 (S72). After that, the data generation unit 115 stores, for example, the generated plurality of pieces of teacher data DT in the information storage area 130.

[0161] Specifically, the data generation unit 115 generates a plurality of pieces of teacher data DT so that, for example, quality information 132, communication state information 133, and group information 134 corresponding to the same terminal device 4 and the same session and generated at the same timing are included in the same teacher data DT. Specific examples of the plurality of pieces of teacher data DT will be described below.

[0162] [Specific examples of training data] 22 is a diagram for explaining a specific example of a plurality of pieces of teacher data DT. Specifically, FIG. 22 is a diagram for explaining a specific example of a plurality of pieces of teacher data DT stored in the information storage area 130.

[0163] 22 has, for example, items such as a "delay time" in which a delay time for transmitting and receiving each packet 131 is set, a "loss rate" in which a loss rate for each packet 131 is set, a "traffic volume" in which a traffic volume for each packet 131 is set, and a "QoE" in which a QoE in each terminal device 4 is set. Also, each teacher data DT shown in Fig. 22 has, for example, items such as a "total data volume" in which a total data volume corresponding to each packet group is set, a "group no-communication time" in which a group no-communication time corresponding to each packet group is set, a "group interval time" in which a group interval time corresponding to each packet group is set, and a "group transmission time" in which a group transmission time corresponding to each packet group is set.

[0164] Specifically, in the information in the first line of the teacher data DT shown in Fig. 22, for example, "0 (ms)" is set as the "delay time", "0 (%)" is set as the "loss rate", "5.1 (Mbps)" is set as the "traffic volume", and "5" is set as the "QoE". In addition, in the information in the first line of the teacher data DT shown in Fig. 22, for example, "5000 (bytes)" is set as the "total data volume", "400 (ms)" is set as the "group no communication time", "500 (ms)" is set as the "group interval time", and "100 (ms)" is set as the "group transmission time".

[0165] In addition, in the information in the third row of the teacher data DT shown in Fig. 22, for example, "3.5 (ms)" is set as the "delay time", "0.5 (%)" is set as the "loss rate", "3.0 (Mbps)" is set as the "traffic volume", and "2" is set as the "QoE". In addition, in the information in the third row of the teacher data DT shown in Fig. 22, for example, "5000 (bytes)" is set as the "total data volume", "200 (ms)" is set as the "group no communication time", "500 (ms)" is set as the "group interval time", and "300 (ms)" is set as the "group transmission time". Description of other data included in Fig. 22 will be omitted.

[0166] 13, the model learning unit 116 generates a learning model MD by learning the multiple pieces of teacher data DT generated in the process of S72 (S73). After that, the model learning unit 116 stores the generated learning model MD in the information storage area 130, for example.

[0167] [Estimation process in the first embodiment] Next, the estimation process in the first embodiment will be described. Fig. 23 is a flow chart illustrating the estimation process in the first embodiment. Fig. 24 and Fig. 25 are diagrams illustrating the estimation process in the first embodiment.

[0168] 23, the information estimation unit 117 waits until the estimation timing (NO in S81), for example. The estimation timing may be the timing when the administrator inputs information to the information processing device 1 to estimate the quality information 132, for example.

[0169] Then, when the estimation timing arrives (YES in S81), the information estimation unit 117 inputs, for example, the communication status information 133 stored in the information storage area 130 and the group summary information 134b stored in the information storage area 130 into the learning model MD (S82).

[0170] Specifically, the information estimation unit 117 acquires, for example, the communication state information 133 stored in the information storage area 130, that corresponds to the timing at which the quality information 132 is estimated. Also, the information estimation unit 117 acquires, for example, the group tally information 134b stored in the information storage area 130, that corresponds to the timing at which the quality information 132 is estimated. Then, the information estimation unit 117 inputs, for example, the acquired communication state information 133 and group tally information 134b to the learning model MD.

[0171] More specifically, the information estimation unit 117 acquires, for example, the most recent communication state information 133 from among the communication state information 133 stored in the information storage area 130. Also, the information estimation unit 117 acquires, for example, the most recent group tally information 134b from among the group tally information 134b stored in the information storage area 130. Then, the information estimation unit 117 inputs, for example, the acquired communication state information 133 and group tally information 134b to the learning model MD.

[0172] After that, the information estimation unit 117 acquires, for example, the quality information 132 output from the learning model MD (S83).

[0173] Then, the information using unit 118 outputs the quality information 132 acquired in the process of S83 to an operation terminal (not shown) (S84).

[0174] In this case, the information using unit 118 controls each network device (not shown) included in the information processing system 10, for example, based on the quality information 132 acquired in the process of S83.

[0175] In this way, in the learning process, the information processing device 1 in this embodiment calculates first group information 134 indicating the acquisition status of the first packets 131 for each of a plurality of packet groups from the acquisition status of the first packets 131 transmitted from the video distribution device 2 to the terminal device 4 via the network NW. Then, the information processing device 1 generates a learning model MD by learning teacher data DT including, for example, the calculated first group information 134, first communication state information 133 indicating the communication state of the first packets 131 in the network NW, and first quality information 132 indicating the quality related to the output of the first packets 131 in the terminal device 4.

[0176] Furthermore, in the estimation process, for example, similarly to the case of the learning process, the information processing device 1 calculates second group information 134 indicating the acquisition status of the second packets 131 (hereinafter also referred to as other packets 131) for each of a plurality of packet groups from the acquisition status of the second packets 131 transmitted from the video distribution device 2 to the terminal device 4 via the network NW. Then, the information processing device 1 acquires, for example, second quality information 132 output from the learning model MD in association with input of the calculated second group information 134 and second communication state information 133 indicating the communication state of the second packets 131 in the network NW. Then, the information processing device 1 outputs, for example, the acquired second quality information 132.

[0177] That is, in the information processing device 1 of this embodiment, for example, when generating a learning model MD capable of estimating quality information 132, learning is performed using teacher data DT that includes not only communication state information 133 and quality information 132, but also group information 134 indicating the acquisition status of packets 131 for each of multiple packet groups.

[0178] As a result, the information processing device 1 in this embodiment is able to generate a learning model MD that can accurately estimate quality information 132 such as QoE even when the correlation between the timing at which communication status information 133 changes in the network NW and the timing at which a change in quality information 132 occurs in the terminal device 4 is not sufficiently strong (the correlation is weak).

[0179] Therefore, for example, by referring to the estimated result of the quality information 132 in the terminal device 4, the administrator can take appropriate measures such as controlling network devices to improve the quality information 132 in the terminal device 4.

[0180] 24, for example, during transmission of packet group G2, which is transmitted in the time between packet group G1 and packet group G3, if a decrease in the amount of communication data occurs in the network NW and the transmission time T1 of packet group G2 becomes long, playback of video data may be interrupted in the terminal device 4. In this case, for example, a decrease in QoE or the like occurs in the terminal device 4.

[0181] 25, even if a decrease in the amount of communication data in the network NW occurs during transmission of packet group G2, if the transmission time T2 of packet group G2 is shorter than the transmission time T1 and the transmission of all packets 131 included in packet group G2 is completed before an interruption in playback of video data occurs in terminal device 4, there is a possibility that playback of video data will not be interrupted in terminal device 4. In this case, for example, a decrease in QoE or the like will not occur in terminal device 4.

[0182] That is, the correlation between the communication state information 133 and the quality information 132 at the transmission timing of the packet group G2 varies depending on, for example, the transmission time of the packet group G2 (for example, the group transmission time described in FIG. 21) etc. Therefore, it can be determined that the correlation between the communication state information 133 and the quality information 132 at the transmission timing of the packet group G2 is not necessarily strong.

[0183] Therefore, the information processing device 1 in this embodiment generates a learning model MD by learning the teacher data DT including, for example, the communication state information 133, the quality information 132, and also the group information 134, and by using information regarding whether or not a deterioration in the communication state that occurred in the network NW actually affected the playback of video data in the terminal device 4. This makes it possible for the information processing device 1 in this embodiment to generate a learning model MD that can accurately estimate the quality information 132 such as QoE.

[0184] In addition, the information processing device 1 in this embodiment generates group information 134 corresponding to each packet 131, for example, by referring to data contained in the header (e.g., an RTP header or a TCP header) of the packet 131 transmitted from the video distribution device 2.

[0185] This enables the information processing device 1 in this embodiment to generate group information 134 corresponding to each packet 131, for example, without performing analysis of data included in portions other than the header of the data included in the packet 131. Furthermore, the information processing device 1 can generate group information 134 corresponding to each packet 131 even if part of the data included in the packet 131 (data included in portions other than the header) is encrypted from the standpoint of, for example, strengthening security.

[0186] In the above example, the learning model MD is generated by using the teacher data DT including the quality information 132, the communication state information 133, and the group information 134 at the same timing, but the present invention is not limited to this. Specifically, the information processing device 1 may generate the learning model MD by using the teacher data DT including the communication state information 133 and the group information 134 at the same timing (hereinafter also referred to as the first timing) and the quality information 132 at the second timing later than the first timing.

[0187] This enables the information processing device 1 to, in the estimation process, estimate quality information 132 (i.e., future quality information 132) at a timing later than the timing corresponding to the communication state information 133 and group information 134 input to the learning model MD.

[0188] In addition, in the above example, a case has been described in which the information processing device 1 (packet acquisition unit 111) acquires the packet 131 transmitted from the capture device 3, and the information processing device 1 (communication analysis unit 113) generates communication status information 133 from the packet 131, but this is not limited to this.

[0189] Specifically, the communication state information 133 may be generated by, for example, the capture device 3 that captures the packet 131. Then, the information processing device 1 (information acquisition unit 112) may receive the communication state information 133 transmitted from the capture device 3, and store the received communication state information 133 in the information storage area 130, for example.

[0190] This eliminates the need for the information processing device 1 to have a storage area (information storage area 130) capable of storing, for example, the packet 131 transmitted from the capture device 3, making it possible to reduce operational costs.

[0191] The above embodiment can be summarized as follows:

[0192] (Appendix 1) a group calculation unit that calculates first group information indicating an acquisition status for each of a plurality of packet groups, each of which includes a plurality of packets having a predetermined relationship, from an acquisition status in a capture device of packets transmitted from an application device to a terminal device via a network; a model learning unit that generates a learning model by learning teacher data including the calculated first group information, first communication state information indicating a communication state of the packet in the network, and first quality information indicating a quality related to an output of the packet in the terminal device, A network device comprising:

[0193] (Appendix 2) In Appendix 1: the packets are packets constituting video data that is distributed from the application device to the terminal device and played back on the terminal device, The first quality information is information indicating a Quality of Experience (QoE) for the video data in the terminal device. A network device comprising:

[0194] (Appendix 3) In Appendix 2: each of the plurality of packets having the predetermined relationship is a plurality of packets used for playing the video data in the same time period; A network device comprising:

[0195] (Appendix 4) Appendix 1 further states: a packet acquisition unit that acquires the packet transmitted from the capture device; the group calculation unit calculates the first group information from an acquisition status of the packets in the packet acquisition unit. A network device comprising:

[0196] (Appendix 5) Appendix 4 further states: a communication analysis unit that calculates the first communication state information from an acquisition status of the packet in the packet acquisition unit; A network device comprising:

[0197] (Appendix 6) In Appendix 1: The capture device generates the first communication state information from an acquisition status of the packet at the capture device, and further an information acquisition unit that acquires the first communication state information transmitted from the capture device; A network device comprising:

[0198] (Appendix 7) In Appendix 1: the group calculation unit generates, for each of the plurality of packet groups, information indicating a time difference between a reception timing of a first received packet among the plurality of packets included in each packet group and a reception timing of a last received packet among the plurality of packets included in each packet group, as at least one of the first group information; A network device comprising:

[0199] (Appendix 8) In Appendix 1: the group calculation unit generates, for each of the plurality of packet groups, information indicating a time difference between a reception timing of a last received packet among the plurality of packets included in a packet group transmitted immediately before each of the plurality of packet groups and a reception timing of a first received packet among the plurality of packets included in each of the packet groups, as at least one of the first group information; A network device comprising:

[0200] (Appendix 9) In Appendix 1: the group calculation unit generates, for each of the plurality of packet groups, information indicating a time difference between a reception timing of a first received packet among the plurality of packets included in a packet group transmitted immediately before each of the plurality of packet groups and a reception timing of a first received packet among the plurality of packets included in each of the packet groups, as at least one of the first group information; A network device comprising:

[0201] (Appendix 10) In Appendix 1: the group calculation unit generates, for each of the plurality of packet groups, a total amount of data of the plurality of packets included in each of the packet groups as at least one piece of the first group information; A network device comprising:

[0202] (Appendix 11) In Appendix 1: The group calculation unit calculates second group information indicating the acquisition status for each of the plurality of packet groups from the acquisition status of other packets transmitted from the application device to the terminal device via the network, and further an information estimation unit that acquires second quality information output from the learning model in response to input of the calculated second group information and second communication state information indicating a communication state of the other packets in the network; and an information output unit that outputs the acquired second quality information. A network device comprising:

[0203] (Appendix 12) calculating first group information indicating an acquisition status for each of a plurality of packet groups each including a plurality of packets having a predetermined relationship from an acquisition status in a capture device of packets transmitted from the application device to the terminal device via the network; generating a learning model by learning training data including the calculated first group information, first communication state information indicating a communication state of the packets in the network, and first quality information indicating a quality related to an output of the packets in the terminal device; A model learning method comprising:

[0204] (Appendix 13) Appendix 12 further states: calculating second group information indicating the acquisition status for each of the plurality of packet groups from the acquisition status of other packets transmitted from the application device to the terminal device via the network; Acquire second quality information output from the learning model in response to input of the calculated second group information and second communication state information indicating a communication state of the other packets in the network; outputting the acquired second quality information; A model learning method comprising: [Explanation of symbols]

[0205] 1: Information processing device 2: Video distribution device 3: Capture device 4: Terminal device 10: Information Processing System 101: CPU 102: Memory 103: I / O interface 104: Storage device 105: Bus 130: Information storage area IN: Internet NW:Network

Claims

1. a group calculation unit that calculates first group information indicating an acquisition status for each of a plurality of packet groups, each of which includes a plurality of packets having a predetermined relationship, from an acquisition status in a capture device of packets transmitted from an application device to a terminal device via a network; a model learning unit that generates a learning model by learning teacher data including the calculated first group information, first communication state information indicating a communication state of the packet in the network, and first quality information indicating a quality related to an output of the packet in the terminal device, A network device comprising:

2. In claim 1, the packets are packets constituting video data that is distributed from the application device to the terminal device and played back on the terminal device, The first quality information is information indicating a Quality of Experience (QoE) for the video data in the terminal device. A network device comprising:

3. In claim 2, each of the plurality of packets having the predetermined relationship is a plurality of packets used for playing the video data in the same time period; A network device comprising:

4. In claim 1, the group calculation unit generates, for each of the plurality of packet groups, information indicating a time difference between a reception timing of a first received packet among the plurality of packets included in each packet group and a reception timing of a last received packet among the plurality of packets included in each packet group, as at least one of the first group information. A network device comprising:

5. In claim 1, the group calculation unit generates, for each of the plurality of packet groups, information indicating a time difference between a reception timing of a last received packet among the plurality of packets included in a packet group transmitted immediately before each of the plurality of packet groups and a reception timing of a first received packet among the plurality of packets included in each of the packet groups, as at least one of the first group information; A network device comprising:

6. In claim 1, the group calculation unit generates, for each of the plurality of packet groups, information indicating a time difference between a reception timing of a first received packet among the plurality of packets included in a packet group transmitted immediately before each of the plurality of packet groups and a reception timing of a first received packet among the plurality of packets included in each of the packet groups, as at least one of the first group information; A network device comprising:

7. In claim 1, the group calculation unit generates, for each of the plurality of packet groups, a sum of data amounts of the plurality of packets included in each of the plurality of packet groups as at least one piece of the first group information. A network device comprising:

8. In claim 1, The group calculation unit calculates second group information indicating the acquisition status for each of the plurality of packet groups from the acquisition status of other packets transmitted from the application device to the terminal device via the network, and further an information estimation unit that acquires second quality information output from the learning model in response to input of the calculated second group information and second communication state information indicating a communication state of the other packets in the network; and an information output unit that outputs the acquired second quality information. A network device comprising:

9. calculating first group information indicating an acquisition status for each of a plurality of packet groups each including a plurality of packets having a predetermined relationship from an acquisition status in a capture device of packets transmitted from the application device to the terminal device via a network; generating a learning model by learning teacher data including the calculated first group information, first communication state information indicating a communication state of the packets in the network, and first quality information indicating a quality related to an output of the packets in the terminal device; A model learning method comprising:

10. In claim 9, further comprising: calculating second group information indicating the acquisition status for each of the plurality of packet groups from the acquisition status of other packets transmitted from the application device to the terminal device via the network; acquiring second quality information output from the learning model in response to input of the calculated second group information and second communication state information indicating a communication state of the other packets in the network; outputting the acquired second quality information; A model learning method comprising:

Images