WO2023012898A1 - Information processing system, information processing device and information processing method - Google Patents

Information processing system, information processing device and information processing method Download PDF

Info

Publication number
WO2023012898A1
WO2023012898A1 PCT/JP2021/028787 JP2021028787W WO2023012898A1 WO 2023012898 A1 WO2023012898 A1 WO 2023012898A1 JP 2021028787 W JP2021028787 W JP 2021028787W WO 2023012898 A1 WO2023012898 A1 WO 2023012898A1
Authority
WO
WIPO (PCT)
Prior art keywords
optical fiber
information
fiber communication
communication path
information processing
Prior art date
Application number
PCT/JP2021/028787
Other languages
French (fr)
Japanese (ja)
Inventor
賢 白石
Original Assignee
日本電気株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日本電気株式会社 filed Critical 日本電気株式会社
Priority to PCT/JP2021/028787 priority Critical patent/WO2023012898A1/en
Publication of WO2023012898A1 publication Critical patent/WO2023012898A1/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/28Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]

Definitions

  • the present invention relates to an information processing system, an information processing device, and an information processing method.
  • the time difference between the last access time and the last passing traffic generation time is obtained by multiplying the maximum value of the time difference between the last access time and the last passing traffic generation time that existed in the past by a coefficient that is a safety factor.
  • a technique is disclosed for notifying a communication device that has exceeded a threshold.
  • signal interruptions that occur in optical fiber communication paths can be caused by a variety of factors, such as optical fiber deterioration, disconnection, and power on/off on the terminal device side. Therefore, even if the technique of Patent Document 1 is applied, it is difficult to preferably estimate the cause of the problem in the optical fiber communication path.
  • One aspect of the present invention has been made in view of the above problems, and an example of its purpose is to provide a technique capable of suitably estimating the cause of a problem in an optical fiber communication path.
  • An information processing system includes acquisition means for acquiring first monitor information regarding an optical fiber communication path between a terminal device and a communication device; an estimating means for estimating the cause of failure in the optical fiber communication path based on an estimation model that outputs information about the cause of failure in the fiber communication path.
  • An information processing apparatus includes acquisition means for acquiring first monitor information regarding an optical fiber communication path between a terminal device and a communication device; an estimating means for estimating the cause of failure in the optical fiber communication path based on an estimation model that outputs information about the cause of failure in the fiber communication path.
  • An information processing method includes acquiring first monitor information regarding an optical fiber communication path between a terminal device and a communication device; estimating the cause of failure in the optical fiber communication path based on an estimation model that outputs information about the cause of failure in the communication path.
  • FIG. 1 is a block diagram showing the configuration of an information processing device according to exemplary Embodiment 1 of the present invention
  • FIG. 1 is a block diagram showing the configuration of an information processing device according to exemplary Embodiment 1 of the present invention
  • FIG. 3 is a flow chart showing the flow of an information processing method by the information processing device according to exemplary Embodiment 1 of the present invention
  • FIG. 3 is a flow chart showing the flow of an information processing method by the information processing device according to exemplary Embodiment 1 of the present invention
  • 1 is a block diagram showing the configuration of an information processing system according to exemplary Embodiment 1 of the present invention
  • FIG. 1 is a block diagram showing the configuration of an information processing system according to exemplary Embodiment 1 of the present invention
  • FIG. 4 is a block diagram showing the configuration of an information processing system according to exemplary embodiment 2 of the present invention
  • FIG. 11 is a sequence diagram showing the flow of the information processing method by the information processing system according to exemplary Embodiment 2 of the present invention
  • FIG. 10 is a block diagram showing the configuration of an information processing system according to exemplary Embodiment 3 of the present invention
  • FIG. 11 is a sequence diagram showing the flow of an information processing method by an information processing system according to exemplary Embodiment 3 of the present invention
  • FIG. 12 is a block diagram showing the configuration of an information processing system according to exemplary Embodiment 4 of the present invention
  • It is a figure which shows an example of the hardware of a computer.
  • FIG. 1 is a block diagram showing the configuration of an information processing device 1.
  • the information processing device 1 is a device for estimating the cause of a problem in an optical fiber communication path between a terminal device and a communication device.
  • the terminal device and the communication terminal are communicably connected via an optical fiber communication path.
  • a terminal device is a device used by an end user, and an example thereof is an ONU (Optical Network Unit), but is not limited to this.
  • a communication device is a device that monitors the state of an optical fiber communication path between terminal devices, but the communication device is not limited to equipment dedicated to monitoring.
  • the communication device may be a device that relays data from the terminal device to another device, and the communication device may have a function of monitoring the state of the optical fiber communication path between the terminal device and the terminal device.
  • the information processing device 1 includes an acquisition unit 12 and an estimation unit 13.
  • the acquisition unit 12 is a configuration that implements acquisition means in this exemplary embodiment.
  • the estimating unit 13 is a configuration that implements an estimating means in this exemplary embodiment.
  • the acquisition unit 12 acquires monitor information regarding the optical fiber communication path between the terminal device and the communication device.
  • information included in the monitor information related to the optical fiber communication path information indicating the time period during which communication interruption occurs in the optical fiber communication path, the transmission power and the reception power in the optical fiber communication path power, and/or the number of packet errors in the optical fiber communication path and/or the packet error rate.
  • the information included in the monitor information about the optical fiber communication path includes a terminal identifier for identifying the terminal device from other terminal devices and the monitored time. Such information may also be included.
  • the term "communication disconnection” refers to the disconnection of a transmitted or received optical signal in an optical fiber communication path.
  • communication interruption ⁇ Communication interruption due to deterioration or disconnection of optical fiber communication path
  • ⁇ Communication interruption due to terminal equipment being turned off by the end user ⁇ Communication interruption due to terminal equipment being turned off due to power failure, but these The examples do not limit this exemplary embodiment.
  • transmission power and reception power indicate optical transmission power and optical reception power in an optical fiber communication path, respectively.
  • a packet error indicates an error that occurs in transmission or reception of a packet on an optical fiber communication path.
  • the estimating unit 13 estimates the cause of the problem in the optical fiber communication path. Specifically, the estimating unit 13 receives monitor information about the optical fiber communication channel and estimates the cause of the problem in the optical fiber communication channel based on an estimation model that outputs information about the cause of the problem in the optical fiber communication channel. do.
  • the estimation model is learned using teacher data including one or more sets of monitor information and information about failures in the optical fiber communication path.
  • the information related to the cause of the failure related to the optical fiber communication path which is output by the estimation model, ⁇ Type of failure in the optical fiber communication channel ⁇ Probability (accuracy) of failure in the optical fiber communication channel can be included, but are not limiting of this exemplary embodiment.
  • ⁇ Deterioration or disconnection of the optical fiber communication path ⁇ Power OFF of the terminal device by the end user ⁇ Turn off the terminal equipment due to a power outage are not intended to limit this exemplary embodiment.
  • the specific configuration of the estimation model does not limit this exemplary embodiment, as an example, a CNN (Convolution Neural Network), RNN (Recurrent Neural Network), or a combination thereof can be used.
  • Non-neural network models such as random forests and support vector machines may also be used.
  • the monitor information (monitor information referred in the estimation phase) to be referred to for estimating the cause of failure in the optical fiber communication path by the estimation model is set to the first and the monitor information referred to for learning the estimation model (monitor information referred to in the learning phase) may be referred to as second monitor information.
  • the first monitor information may be used as the second monitor information.
  • the monitor information regarding the optical fiber communication path between the terminal device and the communication device is input, and the information regarding the cause of the failure in the optical fiber communication path is obtained.
  • a configuration for estimating the cause of failure in the optical fiber communication path based on the output estimation model is adopted.
  • the acquired monitor information is input to the estimation model, and the estimation model estimates the cause of the failure in the optical fiber communication path. It is possible to suitably estimate the factor of the defect in.
  • optical fiber communication paths For example, communication interruptions in optical fiber communication paths occur even when the terminal device is turned off by the end user. On the other hand, when a communication interruption occurs due to deterioration or disconnection of an optical fiber communication path, there is a tendency for the transmission power and reception power in the optical fiber communication path to decrease or the number of packet errors to increase before the communication interruption occurs. .
  • the information processing device 1 estimates the cause of the problem in the optical fiber communication path after considering the state of the optical fiber communication path before the communication interruption of the optical fiber communication path. Therefore, the information processing apparatus 1 determines whether the cause of the problem is an intentional action on the end user's side (turning off the power of the terminal device), a failure in the optical fiber communication path, a failure on the end user's side, or an intentional It is estimated whether it is a significant event. Therefore, the information processing device 1 can preferably estimate the cause of the problem in the optical fiber communication path.
  • FIG. 2 is a block diagram showing the configuration of the information processing device 2. As shown in FIG.
  • the information processing device 2 includes an acquisition unit 22 and a learning unit 23.
  • the acquisition unit 22 is a configuration that implements acquisition means in this exemplary embodiment.
  • the learning unit 23 is a configuration that implements learning means in this exemplary embodiment.
  • the acquisition unit 22 acquires teacher data that includes a set of monitor information (second monitor information) on the optical fiber communication channel and information on failures in the optical fiber communication channel.
  • the learning unit 23 receives monitor information about the optical fiber communication channel and learns an estimation model that outputs information about the causes of defects in the optical fiber communication channel by referring to the teacher data acquired by the acquiring unit 22 .
  • the expression “learning the estimation model” may be expressed as “training the learning model” or “learning the estimation model.” .
  • the learning unit 23 may be configured to learn the monitor information and the pattern of the cause of the problem.
  • examples of training data used include monitor information near the time when communication interruption occurred in the optical fiber communication path (for example, from 24 hours before the time when the failure occurred until the time when the failure occurred), and the investigation result of the communication interruption (optical fiber channel failure factors).
  • monitor information near the time when communication interruption occurred in the optical fiber communication path for example, from 24 hours before the time when the failure occurred until the time when the failure occurred
  • the investigation result of the communication interruption optical fiber channel failure factors
  • the learning unit 23 may be configured to learn the range of monitor information when a problem due to a certain factor occurs.
  • the monitor information includes the transmission power and reception power in the optical fiber communication path or the number of packet errors in the optical fiber communication path, One or more sets of transmit power and receive power or the range of packet error counts and the failure of that certain factor.
  • this is not a limitation of this exemplary embodiment.
  • the optical fiber A configuration is adopted that learns an estimation model that outputs information about the cause of failure in the communication channel.
  • the estimation model is learned as teacher data including a set of monitor information and information about failures in the optical fiber communication path. It is possible to suitably estimate the cause of the defect.
  • optical fiber communication paths For example, communication interruptions in optical fiber communication paths occur even when the terminal device is turned off by the end user. On the other hand, when a communication interruption occurs due to deterioration or disconnection of an optical fiber communication path, there is a tendency for the transmission power and reception power in the optical fiber communication path to decrease or the number of packet errors to increase before the communication interruption occurs. .
  • the information processing device 2 refers to teacher data including a set of monitor information about the optical fiber communication channel and information about the problem in the optical fiber communication channel, and an estimation model that outputs information about the cause of the problem in the optical fiber communication channel. learn. Therefore, the information processing apparatus 2 determines whether the cause of the problem is an intentional action on the end user side (turning off the power of the terminal device), a failure in the optical fiber communication path, a failure on the end user side, or an intentional It is estimated whether it is a significant event. Therefore, the information processing device 2 can preferably estimate the cause of the problem in the optical fiber communication path.
  • FIG. 3 is a flowchart showing the flow of the information processing method S1 by the information processing device 1. As shown in FIG.
  • step S12 the acquisition unit 12 acquires monitor information regarding the optical fiber communication path between the terminal device and the communication device.
  • step S13 the estimating unit 13 inputs the monitor information about the optical fiber communication path, and based on the estimation model that outputs the information about the cause of the problem in the optical fiber communication path, determines the failure of the optical fiber communication path. Estimate the factors.
  • monitor information on the optical fiber communication path between the terminal device and the communication device is input, and information on the cause of the failure in the optical fiber communication path is input.
  • a configuration for estimating the cause of failure in the optical fiber communication path based on the output estimation model is adopted. Therefore, according to the information processing method S1 according to this exemplary embodiment, the same effects as the information processing apparatus 1 can be obtained.
  • FIG. 4 is a flowchart showing the flow of the information processing method S2 by the information processing device 2. As shown in FIG.
  • step S22 the acquisition unit 22 acquires teacher data including a set of monitor information on the optical fiber communication channel and information on the defect in the optical fiber communication channel.
  • step S23 the learning unit 23 receives monitor information about the optical fiber communication channel, and refers to the teacher data acquired by the acquisition unit 22 in step S22 for an estimation model that outputs information about the cause of failure in the optical fiber communication channel. and learn.
  • the optical fiber A configuration is adopted that learns an estimation model that outputs information about the cause of failure in the communication channel. Therefore, according to the information processing method S ⁇ b>2 according to this exemplary embodiment, the same effects as those of the information processing apparatus 2 can be obtained.
  • FIG. 5 is a block diagram showing the configuration of the information processing system 100. As shown in FIG.
  • the information processing system 100 includes an acquisition unit 12 and an estimation unit 13.
  • the obtaining unit 12 and the estimating unit 13 are configured to implement obtaining means and estimating means, respectively, in this exemplary embodiment.
  • the acquisition unit 12 acquires monitor information regarding the optical fiber communication path.
  • the estimating unit 13 receives monitor information about the optical fiber communication channel and estimates the cause of the problem in the optical fiber communication channel based on an estimation model that outputs information about the cause of the problem in the optical fiber communication channel.
  • the information processing system 100 based on an estimation model that inputs monitor information and outputs information about the cause of the defect in the optical fiber communication path, A configuration for estimating the factors of Therefore, in the information processing system 100 according to this exemplary embodiment, the acquired monitor information is input to the estimation model, and the estimation model estimates the cause of the failure in the optical fiber communication channel. can be suitably estimated.
  • FIG. 6 is a block diagram showing the configuration of the information processing system 200. As shown in FIG.
  • the information processing system 200 includes an acquisition unit 22 and a learning unit 23.
  • the acquisition unit 22 and the learning unit 23 are configured to implement acquisition means and learning means, respectively, in this exemplary embodiment.
  • the acquisition unit 22 acquires teacher data that includes a set of monitor information on the optical fiber communication channel and information on failures in the optical fiber communication channel.
  • the learning unit 23 learns an estimation model that receives monitor information about the optical fiber communication channel and outputs information about the cause of the defect in the optical fiber communication channel by referring to the teacher data acquired by the acquisition means.
  • monitor information relating to optical fiber communication paths is provided, and a combination of monitor information relating to optical fiber communication paths and information relating to defects in optical fiber communication paths is provided.
  • the information processing system 100 adopts a configuration in which monitor information about the optical fiber communication path is input, and an estimation model that outputs information about the cause of failure in the optical fiber communication path is learned by referring to the acquired teacher data. ing. Therefore, in the information processing system 100 according to the present exemplary embodiment, an estimation model is learned as teacher data including a set of monitor information and information about failures in the optical fiber communication path. Factors can be estimated favorably.
  • FIG. 7 is a block diagram showing the configuration of an information processing system 100A according to Exemplary Embodiment 2 of the present invention.
  • the information processing system 100A includes an information processing device 1A, a communication device 50, an input/output device 60, a first terminal device 70-1, and a second terminal device 70-2.
  • the communication device 50, the first terminal device 70-1 and the second terminal device 70-2 are communicably connected to each other via the optical fiber communication path F1 and the optical fiber communication path F2, respectively.
  • the information processing device 1A, the communication device 50, and the input/output device 60 are connected via the network N so as to be able to communicate with each other.
  • the specific configuration of the network N does not limit this embodiment, but as an example, a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or A combination of these networks can be used.
  • a wireless LAN Local Area Network
  • a wired LAN a wired LAN
  • a WAN Wide Area Network
  • public line network a public line network
  • mobile data communication network or A combination of these networks can be used.
  • the information processing system 100A obtains information about the causes of failures in the optical fiber communication paths F1 and F2 between the first terminal device 70-1 and the second terminal device 70-2 and the communication device 50, respectively. It is estimated in the processing device 1A. Further, the information processing system 100A presents the estimation result estimated by the information processing device 1A on the input/output device 60.
  • the terminal device 70-1 and the terminal device 70-2 are devices used by end users
  • the communication device 50 is an optical fiber communication path F1 and an optical fiber communication path F1 between the terminal device 70-1 and the terminal device 70-2. It is a device for monitoring the state of the communication path F2, and the input/output device 60 is a device used by a maintenance worker for the optical fiber communication paths F1 and F2.
  • the information processing system 100A can be configured to include any number of terminal devices.
  • these terminal devices have the same main configuration as each other.
  • the terminal device 70 is simply referred to.
  • the optical fiber communication path F1 and the optical fiber communication path F2 are simply referred to as an optical fiber communication path F when referring to any one of them.
  • the communication device 50 includes a control section 51 , a first communication section 52 and a second communication section 53 .
  • the first communication unit 52 is a communication module for performing communication via the network N.
  • the first communication unit 52 outputs the data acquired from the control unit 51 to the information processing device 1A via the network N.
  • the second communication unit 53 is a communication module for communicating with the terminal device 70.
  • the second communication unit 53 outputs data acquired from the terminal device 70 via the optical fiber communication path F to the control unit 51 .
  • control unit 51 controls each component of the communication device 50 by executing a program stored in a memory (eg, RAM, ROM, etc.) by one or more processors (eg, CPU, etc.), for example.
  • a memory eg, RAM, ROM, etc.
  • processors eg, CPU, etc.
  • the control unit 51 also functions as a monitor information acquisition unit 511 and a provision unit 21, as shown in FIG.
  • the monitor information acquisition unit 511 monitors communication with the terminal device 70 via the second communication unit 53 and acquires monitor information.
  • the provision unit 21 provides the monitor information acquired by the monitor information acquisition unit 511 to the information processing apparatus 1A via the first communication unit 52. Further, the providing unit 21 determines whether or not the acquired monitor information indicates that the communication disconnection of the optical fiber communication path F has occurred. For example, the providing unit 21 may be configured to determine whether or not the monitor information includes a LOS (Loss of Signal) signal. When it is determined that the communication interruption of the optical fiber communication path F has occurred, the provision unit 21 transmits event information indicating that the communication interruption of the optical fiber communication path F has occurred via the first communication unit 52. It is provided to the processing device 1A.
  • LOS Local Area Network
  • the event information may be information indicating an event other than the communication interruption of the optical fiber communication path F.
  • FIG. Another example of an event is - the value of the transmitted power and the received power in the optical fiber channel F is less than a predetermined value; and - the value of the number of packet errors is greater than a predetermined value, which limits this exemplary embodiment. not a thing
  • the information included in the event information includes: - A terminal identifier for identifying the terminal device 70 from other terminals - The time when the event occurred may be included. However, this is not a limitation of this exemplary embodiment.
  • the information processing apparatus 1A includes a control section 10A, a storage section 18A, and a communication section 19.
  • the storage unit 18A is a configuration that implements storage means in this exemplary embodiment.
  • the storage unit 18A is a memory that stores monitor information MI1 and model parameters MP that are referenced by the control unit 10A.
  • the storage unit 18A is realized by, for example, EPROM, EEPROM (registered trademark), HDD, flash memory, etc., which are rewritable nonvolatile memories.
  • the monitor information MI1 is accumulated monitor information provided from the communication device 50 .
  • the monitor information MI1 is also referred to as the first monitor information MI1 because it is monitor information that is referred to for estimating the cause of the failure in the optical fiber communication path F using the estimation model.
  • a model parameter MP is a parameter that defines an estimation model.
  • the estimation model receives the monitor information extracted from the monitor information MI1 and outputs information about the cause of the failure in the optical fiber communication path.
  • CNN neural network
  • RNN neural network model
  • Non-neural network models such as random forests and support vector machines may also be used.
  • the communication unit 19 is a communication module for performing communication via the network N.
  • the communication unit 19 outputs data acquired through the network N to the control unit 10A, and outputs data acquired from the control unit 10A through the network N.
  • Control section 10A In the control unit 10A, for example, one or more processors (such as a CPU (Central Processing Unit)) execute a program stored in a memory (such as a RAM (random access memory) or a ROM (read only memory)). Thereby, each component of the information processing apparatus 1A is controlled.
  • processors such as a CPU (Central Processing Unit)
  • a memory such as a RAM (random access memory) or a ROM (read only memory)
  • the control unit 10A also functions as an acquisition unit 12, an estimation unit 13, an accumulation unit 14, an extraction unit 15, and an output unit 17, as shown in FIG.
  • the obtaining unit 12, the estimating unit 13, the extracting unit 15, and the output unit 17 are configured to implement obtaining means, estimating means, extracting means, and output means, respectively, in this exemplary embodiment.
  • the acquisition unit 12 acquires monitor information about the optical fiber communication path F from the communication device 50 via the communication unit 19 .
  • the acquisition unit 12 outputs the acquired monitor information to the accumulation unit 14 .
  • the acquisition unit 12 also acquires event information output from the communication device 50 via the communication unit 19 .
  • the acquisition unit 12 outputs the acquired event information to the extraction unit 15 .
  • the estimating unit 13 inputs the monitor information extracted by the extracting unit 15 to the estimation model in response to the occurrence of communication interruption in the optical fiber communication channel F, thereby identifying the cause of the failure in the optical fiber communication channel F.
  • the estimating unit 13 estimates the cause of the problem in the optical fiber communication path F according to the occurrence of communication interruption in the optical fiber communication path F, but this is an example, and the above-described other Any configuration may be used as long as the cause of the failure in the optical fiber communication path F is estimated in accordance with the occurrence of an event.
  • the estimation unit 13 generates an estimation result and outputs it to the output unit 17 .
  • the estimating unit 13 estimates the cause of the failure in the optical fiber communication path F according to the occurrence of the communication interruption in the optical fiber communication path F. In this case, it is possible to preferably estimate the cause of the problem in the optical fiber communication path.
  • the accumulation unit 14 accumulates the monitor information acquired by the acquisition unit 12 in the storage unit 18A.
  • the extraction unit 15 refers to the event information output from the acquisition unit 12, and when the event information indicates a communication interruption of the optical fiber communication path F, the extraction unit 15 extracts monitor information regarding the communication interruption in response to the occurrence of the communication interruption. It is extracted from the monitor information MI1 in the storage unit 18A.
  • the extraction unit 15 refers to the event information output from the acquisition unit 12, and when the event information indicates a communication disconnection of the optical fiber communication path F, the communication disconnection occurs according to the occurrence of the communication disconnection.
  • the configuration may be such that the monitor information related to the communication disconnection according to the timing of is extracted from the monitor information MI1 of the storage unit 18A.
  • the monitor information related to the communication interruption according to the timing of the occurrence of the communication interruption may be monitor information for a predetermined period according to the timing of the occurrence of the communication interruption. Examples of monitor information in a predetermined period corresponding to the timing of event occurrence include monitor information in the period from the time of event occurrence to 10 minutes before, monitor information in the period from the time of event occurrence to 1 hour before, and the like. This is not a limitation of this exemplary embodiment.
  • the output unit 17 acquires the estimation result generated by the estimation unit 13 and outputs the estimation result to the input/output device 60 via the communication unit 19 .
  • the input/output device 60 includes a presentation section 61 and an operation reception section 62 .
  • the presentation unit 61 acquires the estimation result output from the information processing device 1A.
  • the presentation unit 61 acquires operation information, which will be described later, from the operation reception unit 62, and presents the acquired estimation result when the operation information indicates an operation for displaying the estimation result.
  • the presentation unit 61 has a display panel as an example, and presents the estimation result by displaying the estimation result on the display panel.
  • the operation reception unit 62 receives operations from the user.
  • the operation reception unit 62 may be configured to include a touch panel superimposed on the display panel of the presentation unit 61, but this does not limit the exemplary embodiment.
  • the operation accepting portion 62 outputs operation information indicating the operation accepted from the user to the presenting portion 61 .
  • FIG. 8 is a sequence diagram showing the flow of the information processing method S100A by the information processing system 100A.
  • step S102 the monitor information acquisition unit 511 of the communication device 50 acquires monitor information.
  • step S103 In step S ⁇ b>103 , the provision unit 21 provides the monitor information acquired by the monitor information acquisition unit 511 to the information processing apparatus 1 ⁇ /b>A via the first communication unit 52 .
  • Step S104 In step S ⁇ b>104 , the acquisition unit 12 of the information processing device 1 ⁇ /b>A acquires monitor information provided from the communication device 50 via the communication unit 19 .
  • Step S105 the accumulation unit 14 accumulates the monitor information acquired by the acquisition unit 12 in step S104 in the storage unit 18A.
  • the storage unit 18A stores monitor information.
  • Step S106 the monitor information acquisition unit 511 refers to the acquired monitor information and determines whether or not communication interruption of the optical fiber communication path F has occurred. If it is determined that the communication disconnection of the optical fiber communication path F has not occurred, the processing of the communication device 50 returns to step S102.
  • Step S107 If it is determined in step S106 that the communication interruption of the optical fiber communication path F has occurred, the providing unit 21 sends an event indicating that the communication interruption of the optical fiber communication path F has occurred via the first communication unit 52. provide information.
  • step S108 In step S ⁇ b>108 , the acquisition unit 12 of the information processing device 1 ⁇ /b>A acquires the event information supplied from the communication device 50 via the communication unit 19 .
  • Step S109 the extraction unit 15 refers to the event information acquired by the acquisition unit 12, and if the event information indicates communication interruption, the extraction unit 15 stores monitor information about the communication interruption in response to the occurrence of the communication interruption. is extracted from the monitor information MI1 accumulated in the .
  • step S110 In step S ⁇ b>110 , the estimation unit 13 inputs the extracted monitor information to the estimation model, and estimates the cause of the failure caused by the communication interruption in the optical fiber communication path F. In other words, the estimating unit 13 estimates the cause of the failure in the optical fiber communication path F by referring to the monitor information regarding the communication interruption in response to the occurrence of the communication interruption in the optical fiber communication path F.
  • step S111 In step S ⁇ b>111 , the estimation unit 13 provides the estimation result estimated in step S ⁇ b>110 to the output unit 17 .
  • the output unit 17 outputs the estimation result to the input/output device 60 via the communication unit 19 .
  • Step S112 the presentation unit 61 of the input/output device 60 acquires the estimation result provided by the information processing device 1A in step S111.
  • Step S113 the presentation unit 61 displays the estimation result.
  • the input/output device 60 presents to the maintenance worker using the input/output device 60 information indicating the priority of maintenance work included in the estimation result and the maintenance work recommended for the optical fiber communication path F. be able to.
  • monitor information provided from the communication device 50 is accumulated in the storage unit 18A as monitor information MI1. Then, in the information processing system 100A, in response to the occurrence of the communication disconnection of the optical fiber communication channel F, the cause of the failure in the optical fiber communication channel F is estimated by referring to the monitor information regarding the communication disconnection.
  • a communication disconnection of the optical fiber communication path F occurs even when the terminal device 70 is turned off by the end user.
  • a communication interruption occurs due to degradation or disconnection of the optical fiber communication path F
  • the transmission power and reception power in the optical fiber communication path F decrease or the number of packet errors to increase before the communication interruption occurs.
  • the cause of the failure in the optical fiber communication path F is estimated. It is possible to suitably estimate the cause of the defect.
  • FIG. 9 is a block diagram showing the configuration of an information processing system 100B according to Exemplary Embodiment 3 of the present invention. As shown in FIG. 9, the information processing system 100B is configured to include an information processing device 1B instead of the information processing device 1A in the information processing system 100A described above.
  • the information processing system 100B learns an estimation model by referring to teacher data including a set of monitor information on the optical fiber communication channel F and information on defects in the optical fiber communication channel F.
  • the input/output device 60 includes a presentation unit 61 and an operation reception unit 62, as shown in FIG. Note that the presentation unit 61 is as described above.
  • the operation accepting unit 62 accepts an operation of inputting the following information regarding the problem from the user (maintenance company). - A terminal identifier for distinguishing the terminal device 70 from other terminals - Time of failure occurrence in the optical fiber communication path F - Type of failure The defect information included is output via the network N to the information processing device 1B.
  • the information processing apparatus 1B includes a control section 10B, a storage section 18B, and a communication section 19, as shown in FIG. Note that the communication unit 19 is as described above.
  • the storage unit 18B is a memory that stores model parameters MP, monitor information MI2, and defect information EI that are referred to by the control unit 10B.
  • the storage unit 62 is realized by EPROM, EEPROM, HDD, flash memory, etc., which are rewritable non-volatile memories, for example.
  • the model parameter MP is as described above.
  • the monitor information MI2 is, of the monitor information provided from the communication device 50, stored in association with the defect information EI, which will be described later. Note that the monitor information MI2 is also referred to as second monitor information MI2 because it is monitor information that is referred to for learning the estimation model.
  • the defect information EI is defect information provided from the input/output device 60 and stored in association with the monitor information MI2.
  • control unit 10B controls each component of the information processing apparatus 1B by executing a program stored in a memory (eg, RAM, ROM, etc.) by one or more processors (eg, CPU, etc.), for example.
  • a memory eg, RAM, ROM, etc.
  • processors eg, CPU, etc.
  • the control unit 10B also functions as an acquisition unit 12 and a learning unit 16, as shown in FIG.
  • the acquisition unit 12 and the learning unit 16 are configured to implement acquisition means and learning means, respectively, in this exemplary embodiment.
  • the acquisition unit 12 acquires monitor information about the optical fiber communication path F from the communication device 50 via the communication unit 19 .
  • the acquisition unit 12 acquires defect information regarding a defect in the optical fiber communication path F from the input/output device 60 via the communication unit 19 .
  • the acquisition unit 12 associates the defect information EI with the monitor information MI2 and stores them in the storage unit 18B.
  • the acquisition unit 12 extracts monitor information having the same terminal identifier as the terminal identifier included in the trouble information. Further, the acquisition unit 12 sets a period from the time of occurrence of the problem indicated by the problem information to a predetermined time (for example, from 24 hours before the time of occurrence of the problem to the time of occurrence of the problem). The acquisition unit 12 extracts, from the extracted monitor information, monitor information in which the time at which the information on the transmission power, the reception power, and the number of packet errors included in the extracted monitor information is acquired is included in a set period. The acquisition unit 12 associates the defect information EI with the extracted monitor information MI2 and stores them in the storage unit 18B.
  • the acquisition unit 12 acquires information on the transmission power, the reception power, and the number of packet errors during a period from the time when the problem occurred to a predetermined time before, and the information on the number of packet errors. Associate with.
  • a set of associated monitor information MI2 and defect information EI is referred to as teacher data.
  • the learning unit 16 learns the estimation model by referring to the teacher data. As an example, the learning unit 16 repeatedly updates the model parameters of the estimation model by repeatedly executing the learning step using the teacher data. Then, the learning unit 16 stores the model parameters MP defining the estimated model after learning in the storage unit 18B.
  • CNN neural network
  • RNN neural network model
  • Non-neural network models such as random forests and support vector machines may also be used.
  • FIG. 10 is a sequence diagram showing the flow of the information processing method S100B by the information processing system 100B.
  • step S102 the monitor information acquisition unit 511 of the communication device 50 acquires monitor information.
  • step S103 In step S ⁇ b>103 , the provision unit 21 provides the monitor information acquired by the monitor information acquisition unit 511 to the information processing apparatus 1 ⁇ /b>B via the first communication unit 52 .
  • Step S104 In step S ⁇ b>104 , the acquisition unit 12 of the information processing device 1 ⁇ /b>B acquires monitor information provided from the communication device 50 via the communication unit 19 .
  • Step S122 upon receiving an operation to input information included in the defect information, the operation receiving unit 62 of the input/output device 60 provides the defect information including the input information to the information processing apparatus 1B via the network N. do.
  • Step S123 In step S ⁇ b>123 , the acquisition unit 12 of the information processing device 1 ⁇ /b>B acquires the defect information provided from the input/output device 60 via the communication unit 19 .
  • step S124 the acquisition unit 12 refers to the acquired defect information and extracts monitor information. Since the method of extracting the monitor information has been described above, the explanation is omitted here.
  • Step S125 The acquisition unit 12 associates the defect information EI acquired in step S123 with the monitor information MI2 extracted in step S123 to generate teacher data.
  • the learning unit 16 acquires the generated teacher data.
  • Step S126 The learning unit 16 learns the estimation model by referring to the acquired teacher data.
  • Step S127 The learning unit 16 stores the model parameters MP that define the estimated model after learning in the storage unit 18B.
  • an estimation model is learned using the associated defect information EI and monitor information MI2 as training data. Therefore, in the information processing system 100B, since the estimation model is learned by associating the failure with the state of the optical fiber communication path F before the failure occurs, the cause of the failure in the optical fiber communication path F can be estimated appropriately. can do.
  • FIG. 11 is a block diagram showing the configuration of an information processing system 100C according to Exemplary Embodiment 4 of the present invention. As shown in FIG. 11, an information processing system 100C is configured to include an information processing device 1C instead of the information processing device 1A in the information processing system 100A described above.
  • the information processing system 100C is a system having the functions of both the information processing system 100A in the second exemplary embodiment and the information processing system 100B in the third exemplary embodiment.
  • the information processing apparatus 1C includes a control section 10C, a storage section 18C, and a communication section 19, as shown in FIG.
  • the communication unit 19 is as described above.
  • the storage unit 18C stores the above-described monitor information MI1, model parameters MP, and associated monitor information MI2 and defect information EI.
  • control unit 10C controls each component of the information processing apparatus 1C by executing a program stored in a memory (eg, RAM, ROM, etc.) by one or more processors (eg, CPU, etc.), for example.
  • a memory eg, RAM, ROM, etc.
  • processors eg, CPU, etc.
  • the control unit 10C includes an acquisition unit 12, an estimation unit 13, an accumulation unit 14, an extraction unit 15, a learning unit 16, and an output unit 17, as shown in FIG.
  • the acquisition unit 12 has the functions of both the acquisition unit 12 in the information processing device 1A and the acquisition unit 12 in the information processing device 1B.
  • the estimation unit 13, storage unit 14, extraction unit 15, and output unit 17 have the same functions as the estimation unit 13, storage unit 14, extraction unit 15, and output unit 17 in the information processing device 1A.
  • the learning unit 16 has the same function as the learning unit 16 in the information processing device 1B.
  • the information processing system 100C is a system having the functions of both the information processing system 100A in the second exemplary embodiment and the information processing system 100B in the third exemplary embodiment. In other words, the information processing system 100C executes the processing of the information processing system 100A and the processing of the information processing system 100B.
  • the information processing system 100C executes the processing from step S102 to step S113 in the information processing method S100A shown in FIG.
  • the information processing system 100C executes the processing from step S122 to step S127 in the information processing method S100B shown in FIG.
  • the information processing device 1C acquires the monitor information acquired and provided by the communication device 50, and the storage unit 18C stores the monitor information. Then, when the communication device 50 provides the event information, the information processing device 1C estimates the cause of the communication disconnection failure of the optical fiber communication path F, and the input/output device 60 displays the estimation result.
  • the learning unit 16 of the information processing device 1C learns the estimation model based on the monitor information and the defect information, and stores the model parameters MP in the storage unit 18C. do.
  • the model parameter MP of the estimation model is sequentially updated, and the cause of the communication interruption of the optical fiber communication channel F is estimated. can do.
  • Some or all of the functions of the information processing devices 1, 1A, 1B, 1C, and 2 and the communication device 50 may be realized by hardware such as integrated circuits (IC chips) or by software. good.
  • the information processing devices 1, 1A, 1B, 1C, and 2 and the communication device 50 are implemented, for example, by a computer that executes program instructions, which are software that implements each function.
  • a computer that executes program instructions, which are software that implements each function.
  • FIG. 1 Computer C comprises at least one processor C1 and at least one memory C2.
  • a program P for operating the computer C as the information processing devices 1, 1A, 1B, 1C, 2 and the communication device 50 is recorded in the memory C2.
  • the processor C1 reads the program P from the memory C2 and executes it, thereby implementing the functions of the information processing devices 1, 1A, 1B, 1C, 2 and the communication device 50.
  • processor C1 for example, CPU (Central Processing Unit), GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating point number Processing Unit), PPU (Physics Processing Unit) , a microcontroller, or a combination thereof.
  • memory C2 for example, a flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), or a combination thereof can be used.
  • the computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and temporarily storing various data.
  • Computer C may further include a communication interface for sending and receiving data to and from other devices.
  • Computer C may further include an input/output interface for connecting input/output devices such as a keyboard, mouse, display, and printer.
  • the program P can be recorded on a non-temporary tangible recording medium M that is readable by the computer C.
  • a recording medium M for example, a tape, disk, card, semiconductor memory, programmable logic circuit, or the like can be used.
  • the computer C can acquire the program P via such a recording medium M.
  • the program P can be transmitted via a transmission medium.
  • a transmission medium for example, a communication network or broadcast waves can be used.
  • Computer C can also acquire program P via such a transmission medium.
  • (Appendix 1) Acquisition means for acquiring first monitor information relating to an optical fiber communication path between a terminal device and a communication device, and receiving the first monitor information as an input, and outputting information relating to a cause of failure in the optical fiber communication channel. and an estimating means for estimating factors of failure in the optical fiber communication path based on the estimating model.
  • Appendix 2 1. The information processing system according to appendix 1, wherein the estimating means estimates the cause of the failure in the optical fiber communication path in accordance with occurrence of a communication disconnection in the optical fiber communication path between the terminal device and the communication device.
  • Appendix 4 Any one of appendices 1 to 3, wherein the first monitor information includes at least one of transmission power and reception power in the optical fiber communication path and at least one of the number of packet errors in the optical fiber communication path.
  • the information processing system according to .
  • Appendix 5 The information processing system according to any one of Appendices 1 to 4, further comprising an output unit that outputs information indicating maintenance work corresponding to the estimated cause of the malfunction.
  • Appendix 6 The information processing according to any one of Appendices 1 to 5, further comprising learning means for learning the estimation model based on second monitor information regarding the optical fiber communication channel and information regarding defects in the optical fiber communication channel. system.
  • the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably.
  • (Appendix 7) providing means for providing monitor information on the optical fiber communication path; acquisition means for acquiring teacher data including a set of monitor information on the optical fiber communication path and information on failures in the optical fiber communication path; An information processing system comprising learning means for learning an estimation model that receives monitor information as input and outputs information about the cause of failure in an optical fiber communication path, with reference to teacher data acquired by the acquisition means.
  • the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably.
  • (Appendix 8) Acquisition means for acquiring first monitor information relating to an optical fiber communication path between a terminal device and a communication device, and receiving the first monitor information as an input, and outputting information relating to a cause of failure in the optical fiber communication channel. and an estimating means for estimating factors of failure in the optical fiber communication path based on an estimating model.
  • the information processing apparatus according to Supplementary Note 9, further comprising extracting means for extracting, wherein the estimating means estimates the cause of the failure in the optical fiber communication path according to the extracted first monitor information.
  • appendix 11 Any one of appendices 8 to 10, wherein the first monitor information includes at least one of transmission power and reception power in the optical fiber communication path and at least one of the number of packet errors in the optical fiber communication path.
  • the information processing device according to .
  • Appendix 12 12. The information processing apparatus according to any one of appendices 8 to 11, further comprising an output unit that outputs information indicating maintenance work corresponding to the estimated cause of the malfunction.
  • the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably.
  • the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably.
  • Appendix 17 Storing the first monitor information acquired in the acquiring step; and Based on the first monitor information stored in the storing step, in accordance with the occurrence of the communication disruption, a first information related to the communication disruption. 17.
  • the information processing method according to appendix 16 further comprising: extracting monitor information, wherein, in the estimating step, a factor of failure in the optical fiber communication path is estimated according to the extracted first monitor information. .
  • Appendix 18 Any one of Appendices 15 to 17, wherein the first monitor information includes at least one of transmission power and reception power in the optical fiber communication path, and at least one of the number of packet errors in the optical fiber communication path.
  • Appendix 19 19. The information processing method according to any one of Appendices 15 to 18, further comprising outputting information indicating maintenance work according to the presumed cause of the malfunction.
  • Appendix 20 20.
  • the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably.
  • the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably.
  • Appendix 22 A program for operating a computer as the information processing system according to any one of Appendices 1 to 7, wherein the program causes the computer to function as each of the means.
  • Appendix 23 A program for causing a computer to operate as the information processing apparatus according to any one of Appendices 8 to 14, the program causing the computer to function as each of the means.
  • the processor includes: a providing process for providing monitor information on an optical fiber communication path between a terminal device and a communication device; an acquisition process for obtaining monitor information on the optical fiber communication channel; By inputting the monitor information acquired in the acquisition process to an estimation model that receives monitor information related to the fiber communication channel and outputs information related to the cause of failure in the optical fiber communication channel, An information processing system that executes an estimation process for estimating the cause of a defect.
  • the information processing system may further include a memory, and the memory stores a program for causing the processor to execute the providing process, the obtaining process, and the estimating process. good too. Also, this program may be recorded in a computer-readable non-temporary tangible recording medium.
  • At least one processor stores training data including a set of a providing process for providing monitor information on the optical fiber communication channel, monitor information on the optical fiber communication channel, and information on failures in the optical fiber communication channel.
  • Acquisition processing and learning in which an estimation model that receives as input monitor information on an optical fiber communication channel and outputs information on the cause of failure in the optical fiber communication channel is learned by referring to the teacher data acquired in the acquisition processing.
  • An information processing system that executes a process.
  • the information processing system may further include a memory, and the memory stores a program for causing the processor to execute the providing process, the acquiring process, and the learning process. good too.
  • this program may be recorded in a computer-readable non-temporary tangible recording medium.
  • At least one processor is provided, and the processor receives as input an acquisition process for acquiring monitor information on the optical fiber communication path between the terminal device and the communication device, and monitor information on the optical fiber communication channel, and the optical fiber communication channel
  • An information processing apparatus that executes an estimation process of estimating the cause of a defect in the optical fiber communication path by inputting the monitor information acquired in the acquisition process to an estimation model that outputs information about the cause of the defect. .
  • the information processing apparatus may further include a memory, and the memory may store a program for causing the processor to execute the acquisition process and the estimation process.
  • this program may be recorded in a computer-readable non-temporary tangible recording medium.
  • At least one processor is provided, and the processor performs an acquisition process for acquiring teacher data including a set of monitor information about an optical fiber communication channel and information about a problem in the optical fiber communication channel, and monitor information about the optical fiber communication channel.
  • An information processing apparatus for executing a learning process of learning an estimation model, which is used as an input and outputs information about a cause of a problem in an optical fiber communication path, with reference to the teacher data acquired by the acquisition means.
  • the information processing apparatus may further include a memory, and the memory may store a program for causing the processor to execute the acquisition process and the learning process. Also, this program may be recorded in a computer-readable non-temporary tangible recording medium.

Abstract

For the purpose of suitably estimating a cause of failure in an optical fiber communication path, this information processing system comprises: an acquisition unit for acquiring monitor information; and an estimation unit for receiving the monitor information as an input and estimating a cause of failure in an optical fiber communication path on the basis of an estimation model which outputs information relating to the cause of failure in the optical fiber communication path.

Description

情報処理システム、情報処理装置、及び情報処理方法Information processing system, information processing device, and information processing method
 本発明は、情報処理システム、情報処理装置、及び情報処理方法に関する。 The present invention relates to an information processing system, an information processing device, and an information processing method.
 従来、通信網の状態を監視し、当該通信網における異常を検知する技術が知られている。例えば、特許文献1には、最終アクセス時刻と最終通過トラフィック発生時刻との時間差が、過去に存在した最終アクセス時刻と最終通過トラフィック発生時刻との時間差の最大値と安全率となる係数を乗算した閾値を超えた通信装置を通知する技術が開示されている。 Conventionally, a technique for monitoring the state of a communication network and detecting anomalies in the communication network has been known. For example, in Patent Document 1, the time difference between the last access time and the last passing traffic generation time is obtained by multiplying the maximum value of the time difference between the last access time and the last passing traffic generation time that existed in the past by a coefficient that is a safety factor. A technique is disclosed for notifying a communication device that has exceeded a threshold.
日本国特開2013-255000号公報Japanese Patent Application Laid-Open No. 2013-255000
 一般に、通信網に発生する異常には、様々な要因があり得る。このため、特許文献1に記載の技術を用いたとしても、異常発生を好適には検知できないといった事態も生じ得る。 In general, anomalies that occur in communication networks can have various causes. Therefore, even if the technique described in Patent Document 1 is used, a situation may arise in which the occurrence of an abnormality cannot be detected appropriately.
 例えば、光ファイバ通信路において生じる信号断の原因には、光ファイバの劣化、切断、及び端末装置側での電源オンオフ等の様々な要因があり得る。このため、特許文献1の技術を適用したとしても、光ファイバ通信路における不具合の要因を好適に推定することは困難である。 For example, signal interruptions that occur in optical fiber communication paths can be caused by a variety of factors, such as optical fiber deterioration, disconnection, and power on/off on the terminal device side. Therefore, even if the technique of Patent Document 1 is applied, it is difficult to preferably estimate the cause of the problem in the optical fiber communication path.
 本発明の一態様は、上記の問題に鑑みてなされたものであり、その目的の一例は、光ファイバ通信路における不具合の要因を好適に推定することのできる技術を提供することである。 One aspect of the present invention has been made in view of the above problems, and an example of its purpose is to provide a technique capable of suitably estimating the cause of a problem in an optical fiber communication path.
 本発明の一態様に係る情報処理システムは、端末装置と通信装置との間の光ファイバ通信路に関する第1のモニタ情報を取得する取得手段と、前記第1のモニタ情報を入力とし、前記光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、前記光ファイバ通信路における不具合の要因を推定する推定手段と、を備えている。 An information processing system according to an aspect of the present invention includes acquisition means for acquiring first monitor information regarding an optical fiber communication path between a terminal device and a communication device; an estimating means for estimating the cause of failure in the optical fiber communication path based on an estimation model that outputs information about the cause of failure in the fiber communication path.
 本発明の一態様に係る情報処理装置は、端末装置と通信装置との間の光ファイバ通信路に関する第1のモニタ情報を取得する取得手段と、前記第1のモニタ情報を入力とし、前記光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、前記光ファイバ通信路における不具合の要因を推定する推定手段と、を備えている。 An information processing apparatus according to an aspect of the present invention includes acquisition means for acquiring first monitor information regarding an optical fiber communication path between a terminal device and a communication device; an estimating means for estimating the cause of failure in the optical fiber communication path based on an estimation model that outputs information about the cause of failure in the fiber communication path.
 本発明の一態様に係る情報処理方法は、端末装置と通信装置との間の光ファイバ通信路に関する第1のモニタ情報を取得することと、前記第1のモニタ情報を入力とし、前記光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、前記光ファイバ通信路における不具合の要因を推定することと、を含んでいる。 An information processing method according to an aspect of the present invention includes acquiring first monitor information regarding an optical fiber communication path between a terminal device and a communication device; estimating the cause of failure in the optical fiber communication path based on an estimation model that outputs information about the cause of failure in the communication path.
 本発明の一態様によれば、光ファイバ通信路における不具合の要因を好適に推定することができる。  According to one aspect of the present invention, it is possible to suitably estimate the cause of a problem in an optical fiber communication path.
本発明の例示的実施形態1に係る情報処理装置の構成を示すブロック図である。1 is a block diagram showing the configuration of an information processing device according to exemplary Embodiment 1 of the present invention; FIG. 本発明の例示的実施形態1に係る情報処理装置の構成を示すブロック図である。1 is a block diagram showing the configuration of an information processing device according to exemplary Embodiment 1 of the present invention; FIG. 本発明の例示的実施形態1に係る情報処理装置による情報処理方法の流れを示すフロー図である。FIG. 3 is a flow chart showing the flow of an information processing method by the information processing device according to exemplary Embodiment 1 of the present invention; 本発明の例示的実施形態1に係る情報処理装置による情報処理方法の流れを示すフロー図である。FIG. 3 is a flow chart showing the flow of an information processing method by the information processing device according to exemplary Embodiment 1 of the present invention; 本発明の例示的実施形態1に係る情報処理システムの構成を示すブロック図である。1 is a block diagram showing the configuration of an information processing system according to exemplary Embodiment 1 of the present invention; FIG. 本発明の例示的実施形態1に係る情報処理システムの構成を示すブロック図である。1 is a block diagram showing the configuration of an information processing system according to exemplary Embodiment 1 of the present invention; FIG. 本発明の例示的実施形態2に係る情報処理システムの構成を示すブロック図である。FIG. 4 is a block diagram showing the configuration of an information processing system according to exemplary embodiment 2 of the present invention; 本発明の例示的実施形態2に係る情報処理システムによる情報処理方法の流れを示すシーケンス図である。FIG. 11 is a sequence diagram showing the flow of the information processing method by the information processing system according to exemplary Embodiment 2 of the present invention; 本発明の例示的実施形態3に係る情報処理システムの構成を示すブロック図である。FIG. 10 is a block diagram showing the configuration of an information processing system according to exemplary Embodiment 3 of the present invention; 本発明の例示的実施形態3に係る情報処理システムによる情報処理方法の流れを示すシーケンス図である。FIG. 11 is a sequence diagram showing the flow of an information processing method by an information processing system according to exemplary Embodiment 3 of the present invention; 本発明の例示的実施形態4に係る情報処理システムの構成を示すブロック図である。FIG. 12 is a block diagram showing the configuration of an information processing system according to exemplary Embodiment 4 of the present invention; コンピュータのハードウェアの一例を示す図である。It is a figure which shows an example of the hardware of a computer.
 〔例示的実施形態1〕
 本発明の第1の例示的実施形態について、図面を参照して詳細に説明する。本例示的実施形態は、後述する例示的実施形態の基本となる形態である。
[Exemplary embodiment 1]
A first exemplary embodiment of the invention will now be described in detail with reference to the drawings. This exemplary embodiment is the basis for the exemplary embodiments described later.
 (情報処理装置1の構成)
 本例示的実施形態に係る情報処理装置1の構成について、図1を参照して説明する。図1は、情報処理装置1の構成を示すブロック図である。情報処理装置1は、端末装置と通信装置との間の光ファイバ通信路における不具合の要因を推定する装置である。ここで、端末装置と通信端末とは光ファイバ通信路を介して通信可能に接続されている。端末装置はエンドユーザが使用する装置であり、一例としてONU(Optical Network Unit)が挙げられるが、これに限定されない。通信装置は端末装置との間の光ファイバ通信路の状態をモニタする装置であるが、通信装置はモニタ専用の機器に限定されない。例えば、通信装置は、端末装置から他の装置へのデータを中継する機器であってもよく、当該通信装置が端末装置との間の光ファイバ通信路の状態をモニタする機能を備える構成であってもよい。
(Configuration of information processing device 1)
A configuration of an information processing apparatus 1 according to this exemplary embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing the configuration of an information processing device 1. As shown in FIG. The information processing device 1 is a device for estimating the cause of a problem in an optical fiber communication path between a terminal device and a communication device. Here, the terminal device and the communication terminal are communicably connected via an optical fiber communication path. A terminal device is a device used by an end user, and an example thereof is an ONU (Optical Network Unit), but is not limited to this. A communication device is a device that monitors the state of an optical fiber communication path between terminal devices, but the communication device is not limited to equipment dedicated to monitoring. For example, the communication device may be a device that relays data from the terminal device to another device, and the communication device may have a function of monitoring the state of the optical fiber communication path between the terminal device and the terminal device. may
 図1に示すように、情報処理装置1は、取得部12及び推定部13を備えている。取得部12は、本例示的実施形態において取得手段を実現する構成である。推定部13は、本例示的実施形態において推定手段を実現する構成である。 As shown in FIG. 1, the information processing device 1 includes an acquisition unit 12 and an estimation unit 13. The acquisition unit 12 is a configuration that implements acquisition means in this exemplary embodiment. The estimating unit 13 is a configuration that implements an estimating means in this exemplary embodiment.
 取得部12は、端末装置と通信装置との間の光ファイバ通信路に関するモニタ情報を取得する。本例示的実施形態において、光ファイバ通信路に関するモニタ情報に含まれる情報の一例として、当該光ファイバ通信路において通信断が発生している時間帯を示す情報、光ファイバ通信路における送信パワー及び受信パワーの少なくとも何れか、並びに光ファイバ通信路におけるパケットエラーの回数やパケットエラー率、が挙げられる。ただし、これは本例示的実施形態を限定するものではなく、例えば、光ファイバ通信路に関するモニタ情報に含まれる情報には、端末装置を他の端末装置と識別するための端末識別子及びモニタした時刻といった情報も含まれていてもよい。 The acquisition unit 12 acquires monitor information regarding the optical fiber communication path between the terminal device and the communication device. In this exemplary embodiment, as an example of information included in the monitor information related to the optical fiber communication path, information indicating the time period during which communication interruption occurs in the optical fiber communication path, the transmission power and the reception power in the optical fiber communication path power, and/or the number of packet errors in the optical fiber communication path and/or the packet error rate. However, this is not intended to limit this exemplary embodiment. For example, the information included in the monitor information about the optical fiber communication path includes a terminal identifier for identifying the terminal device from other terminal devices and the monitored time. Such information may also be included.
 本明細書において通信断とは、光ファイバ通信路において送信又は受信の光信号が断絶されることを示す。通信断には、
・光ファイバ通信路の劣化又は切断による通信断、及び
・端末装置がエンドユーザによって電源OFFされたことによる通信断
・端末装置が停電によって電源OFFされたことによる通信断
が含まれ得るがこれらの例は本例示的実施形態を限定するものではない。
In this specification, the term "communication disconnection" refers to the disconnection of a transmitted or received optical signal in an optical fiber communication path. In case of communication interruption,
・Communication interruption due to deterioration or disconnection of optical fiber communication path, ・Communication interruption due to terminal equipment being turned off by the end user ・Communication interruption due to terminal equipment being turned off due to power failure, but these The examples do not limit this exemplary embodiment.
 また、本明細書において送信パワー及び受信パワーとは、それぞれ光ファイバ通信路における光送信パワー及び光受信パワーを示す。また、パケットエラーとは、光ファイバ通信路におけるパケットの送信又は受信において発生したエラーを示す。 Also, in this specification, transmission power and reception power indicate optical transmission power and optical reception power in an optical fiber communication path, respectively. A packet error indicates an error that occurs in transmission or reception of a packet on an optical fiber communication path.
 推定部13は、光ファイバ通信路における不具合の要因を推定する。具体的には、推定部13は、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、光ファイバ通信路における不具合の要因を推定する。 The estimating unit 13 estimates the cause of the problem in the optical fiber communication path. Specifically, the estimating unit 13 receives monitor information about the optical fiber communication channel and estimates the cause of the problem in the optical fiber communication channel based on an estimation model that outputs information about the cause of the problem in the optical fiber communication channel. do.
 ここで、上記推定モデルは、一例として、モニタ情報と光ファイバ通信路における不具合に関する情報との1又は複数の組を含む教師データを用いて学習されたものである。また、上記推定モデルが出力する、光ファイバ通信路に関する不具合の要因に関する情報には、一例として、
・当該光ファイバ通信路における不具合の種別
・当該光ファイバ通信路における不具合の確率(確度)
に関する情報が含まれ得るが、これらは本例示的実施形態を限定するものではない。
Here, as an example, the estimation model is learned using teacher data including one or more sets of monitor information and information about failures in the optical fiber communication path. In addition, as an example of the information related to the cause of the failure related to the optical fiber communication path, which is output by the estimation model,
・Type of failure in the optical fiber communication channel ・Probability (accuracy) of failure in the optical fiber communication channel
can be included, but are not limiting of this exemplary embodiment.
 また、不具合の種別の例として、
・光ファイバ通信路の劣化又は切断
・エンドユーザによる端末装置の電源OFF
・停電による端末装置の電源OFF
が挙げられるが、これらは本例示的実施形態を限定するものではない。
Also, as an example of the type of failure,
・Deterioration or disconnection of the optical fiber communication path ・Power OFF of the terminal device by the end user
・Turn off the terminal equipment due to a power outage
are not intended to limit this exemplary embodiment.
 また、不具合の確率(確度)の例として、
・光ファイバ通信路において障害が発生した確率
・上述した光ファイバ通信路における不具合の種別毎の発生確率
・エンドユーザによる操作や停電によって電源OFFされた確率
が挙げられるが、これらは本例示的実施形態を限定するものではない。
Also, as an example of the probability (accuracy) of failure,
・Probability of failure occurring in the optical fiber communication path ・Probability of occurrence of each type of failure in the optical fiber communication path described above ・Probability of power being turned off due to operation by the end user or power failure, but these are the exemplary implementation The form is not limited.
 なお、上記推定モデルの具体的構成は本例示的実施形態を限定するものではないが、一例として、CNN(Convolution Neural Network)、RNN(Recurrent Neural Network)、又はそれらの組み合わせを用いることができる。また、ランダムフォレストやサポートベクターマシンのような非ニューラルネットワーク型のモデルを用いてもよい。 Although the specific configuration of the estimation model does not limit this exemplary embodiment, as an example, a CNN (Convolution Neural Network), RNN (Recurrent Neural Network), or a combination thereof can be used. Non-neural network models such as random forests and support vector machines may also be used.
 また、本例示的実施形態及び後述する例示的実施形態において、上記推定モデルによって光ファイバ通信路における不具合の要因を推定するために参照するモニタ情報(推定フェーズにて参照するモニタ情報)を第1のモニタ情報と呼称し、上記推定モデルを学習するために参照するモニタ情報(学習フェーズにて参照するモニタ情報)を第2のモニタ情報と呼称することもある。第1のモニタ情報は、第2のモニタ情報として用いられることもある。 Further, in this exemplary embodiment and exemplary embodiments described later, the monitor information (monitor information referred in the estimation phase) to be referred to for estimating the cause of failure in the optical fiber communication path by the estimation model is set to the first and the monitor information referred to for learning the estimation model (monitor information referred to in the learning phase) may be referred to as second monitor information. The first monitor information may be used as the second monitor information.
 以上のように、本例示的実施形態に係る情報処理装置1においては、端末装置と通信装置との間の光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、光ファイバ通信路における不具合の要因を推定する構成が採用されている。このように、本例示的実施形態に係る情報処理装置1においては、推定モデルに取得したモニタ情報を入力し、当該推定モデルが光ファイバ通信路における不具合の要因を推定するので、光ファイバ通信路における不具合の要因を好適に推定することができる。 As described above, in the information processing apparatus 1 according to the present exemplary embodiment, the monitor information regarding the optical fiber communication path between the terminal device and the communication device is input, and the information regarding the cause of the failure in the optical fiber communication path is obtained. A configuration for estimating the cause of failure in the optical fiber communication path based on the output estimation model is adopted. As described above, in the information processing apparatus 1 according to the present exemplary embodiment, the acquired monitor information is input to the estimation model, and the estimation model estimates the cause of the failure in the optical fiber communication path. It is possible to suitably estimate the factor of the defect in.
 例えば、光ファイバ通信路の通信断は、端末装置がエンドユーザによって電源OFFされた場合でも発生する。一方、光ファイバ通信路の劣化又は切断によって通信断が発生した場合、通信断が発生する前に光ファイバ通信路における送信パワー及び受信パワーの低下又はパケットエラーの回数の増加が発生する傾向がある。 For example, communication interruptions in optical fiber communication paths occur even when the terminal device is turned off by the end user. On the other hand, when a communication interruption occurs due to deterioration or disconnection of an optical fiber communication path, there is a tendency for the transmission power and reception power in the optical fiber communication path to decrease or the number of packet errors to increase before the communication interruption occurs. .
 情報処理装置1は、光ファイバ通信路の通信断の発生前の光ファイバ通信路の状態を考慮した上で、光ファイバ通信路における不具合の要因を推定する。そのため、情報処理装置1は、不具合の要因がエンドユーザ側での意図的な行為(端末装置の電源OFF)なのか、光ファイバ通信路の障害なのか、エンドユーザ側の障害なのか、又は意図的事象なのか、を推定する。したがって、情報処理装置1は、光ファイバ通信路における不具合の要因を好適に推定することができる。 The information processing device 1 estimates the cause of the problem in the optical fiber communication path after considering the state of the optical fiber communication path before the communication interruption of the optical fiber communication path. Therefore, the information processing apparatus 1 determines whether the cause of the problem is an intentional action on the end user's side (turning off the power of the terminal device), a failure in the optical fiber communication path, a failure on the end user's side, or an intentional It is estimated whether it is a significant event. Therefore, the information processing device 1 can preferably estimate the cause of the problem in the optical fiber communication path.
 (情報処理装置2の構成)
 本例示的実施形態に係る情報処理装置2の構成について、図2を参照して説明する。図2は、情報処理装置2の構成を示すブロック図である。
(Configuration of information processing device 2)
The configuration of the information processing device 2 according to this exemplary embodiment will be described with reference to FIG. FIG. 2 is a block diagram showing the configuration of the information processing device 2. As shown in FIG.
 図2に示すように、情報処理装置2は、取得部22及び学習部23を備えている。取得部22は、本例示的実施形態において取得手段を実現する構成である。学習部23は、本例示的実施形態において学習手段を実現する構成である。 As shown in FIG. 2, the information processing device 2 includes an acquisition unit 22 and a learning unit 23. The acquisition unit 22 is a configuration that implements acquisition means in this exemplary embodiment. The learning unit 23 is a configuration that implements learning means in this exemplary embodiment.
 取得部22は、光ファイバ通信路に関するモニタ情報(第2のモニタ情報)と、光ファイバ通信路における不具合に関する情報との組を含む教師データを取得する。 The acquisition unit 22 acquires teacher data that includes a set of monitor information (second monitor information) on the optical fiber communication channel and information on failures in the optical fiber communication channel.
 学習部23は、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを、取得部22が取得した教師データを参照して学習する。 The learning unit 23 receives monitor information about the optical fiber communication channel and learns an estimation model that outputs information about the causes of defects in the optical fiber communication channel by referring to the teacher data acquired by the acquiring unit 22 .
 ここで、本例示的実施形態及び後述する例示的実施形態において、「推定モデルを学習する」との表現は、「学習モデルを訓練する」又は「推定モデルを学習させる」と表現してもよい。 Here, in this exemplary embodiment and exemplary embodiments described later, the expression "learning the estimation model" may be expressed as "training the learning model" or "learning the estimation model." .
 また、学習部23は、モニタ情報と不具合の要因のパターンを学習する構成であってもよい。この場合、用いられる教師データの例として、光ファイバ通信路における通信断発生時刻近辺(例えば、障害発生時刻の24時間前から障害発生時刻まで)のモニタ情報と、当該通信断の調査結果(光ファイバ通信路の不具合の要因)との1又は複数の組、が挙げられる。ただし、これは本例示的実施形態を限定するものではない。 Further, the learning unit 23 may be configured to learn the monitor information and the pattern of the cause of the problem. In this case, examples of training data used include monitor information near the time when communication interruption occurred in the optical fiber communication path (for example, from 24 hours before the time when the failure occurred until the time when the failure occurred), and the investigation result of the communication interruption (optical fiber channel failure factors). However, this is not a limitation of this exemplary embodiment.
 また、学習部23は、ある要因の不具合が発生した際のモニタ情報のレンジを学習する構成であってもよい。この場合、用いられる教師データの例として、モニタ情報に光ファイバ通信路における送信パワー及び受信パワー又は光ファイバ通信路におけるパケットエラーの回数が含まれている場合、ある要因の不具合が発生した際における送信パワー及び受信パワー又はパケットエラーの回数のレンジと、当該ある要因の不具合との1又は複数の組、が挙げられる。ただし、これは本例示的実施形態を限定するものではない。 Also, the learning unit 23 may be configured to learn the range of monitor information when a problem due to a certain factor occurs. In this case, as an example of the training data used, if the monitor information includes the transmission power and reception power in the optical fiber communication path or the number of packet errors in the optical fiber communication path, One or more sets of transmit power and receive power or the range of packet error counts and the failure of that certain factor. However, this is not a limitation of this exemplary embodiment.
 以上のように、本例示的実施例に係る情報処理装置2においては、光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを参照して、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを学習する構成が採用されている。このように、本例示的実施形態に係る情報処理装置2においては、モニタ情報と光ファイバ通信路における不具合に関する情報との組を含む教師データとして推定モデルが学習されるので、光ファイバ通信路における不具合の要因を好適に推定することができる。 As described above, in the information processing apparatus 2 according to this exemplary embodiment, referring to the teacher data including the set of the monitor information about the optical fiber communication path and the information about the trouble in the optical fiber communication path, the optical fiber A configuration is adopted that learns an estimation model that outputs information about the cause of failure in the communication channel. As described above, in the information processing apparatus 2 according to the present exemplary embodiment, the estimation model is learned as teacher data including a set of monitor information and information about failures in the optical fiber communication path. It is possible to suitably estimate the cause of the defect.
 例えば、光ファイバ通信路の通信断は、端末装置がエンドユーザによって電源OFFされた場合でも発生する。一方、光ファイバ通信路の劣化又は切断によって通信断が発生した場合、通信断が発生する前に光ファイバ通信路における送信パワー及び受信パワーの低下又はパケットエラーの回数の増加が発生する傾向がある。 For example, communication interruptions in optical fiber communication paths occur even when the terminal device is turned off by the end user. On the other hand, when a communication interruption occurs due to deterioration or disconnection of an optical fiber communication path, there is a tendency for the transmission power and reception power in the optical fiber communication path to decrease or the number of packet errors to increase before the communication interruption occurs. .
 情報処理装置2は、光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを参照して、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデル学習する。そのため、情報処理装置2は、不具合の要因がエンドユーザ側での意図的な行為(端末装置の電源OFF)なのか、光ファイバ通信路の障害なのか、エンドユーザ側の障害なのか、又は意図的事象なのか、を推定する。したがって、情報処理装置2は、光ファイバ通信路における不具合の要因を好適に推定することができる。 The information processing device 2 refers to teacher data including a set of monitor information about the optical fiber communication channel and information about the problem in the optical fiber communication channel, and an estimation model that outputs information about the cause of the problem in the optical fiber communication channel. learn. Therefore, the information processing apparatus 2 determines whether the cause of the problem is an intentional action on the end user side (turning off the power of the terminal device), a failure in the optical fiber communication path, a failure on the end user side, or an intentional It is estimated whether it is a significant event. Therefore, the information processing device 2 can preferably estimate the cause of the problem in the optical fiber communication path.
 (情報処理方法S1の流れ)
 本例示的実施形態に係る情報処理方法S1について、図3を参照して説明する。図3は、情報処理装置1による情報処理方法S1の流れを示すフロー図である。
(Flow of information processing method S1)
The information processing method S1 according to this exemplary embodiment will be described with reference to FIG. FIG. 3 is a flowchart showing the flow of the information processing method S1 by the information processing device 1. As shown in FIG.
 (ステップS12)
 ステップS12において、取得部12は、端末装置と通信装置との間の光ファイバ通信路に関するモニタ情報を取得する。
(Step S12)
In step S12, the acquisition unit 12 acquires monitor information regarding the optical fiber communication path between the terminal device and the communication device.
 (ステップS13)
 続いて、ステップS13において、推定部13は、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、前記光ファイバ通信路における不具合の要因を推定する。
(Step S13)
Subsequently, in step S13, the estimating unit 13 inputs the monitor information about the optical fiber communication path, and based on the estimation model that outputs the information about the cause of the problem in the optical fiber communication path, determines the failure of the optical fiber communication path. Estimate the factors.
 以上のように、本例示的実施形態に係る情報処理方法S1においては、端末装置と通信装置との間の光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、光ファイバ通信路における不具合の要因を推定する構成が採用されている。したがって、本例示的実施形態に係る情報処理方法S1によれば、情報処理装置1と同様の効果を奏する。 As described above, in the information processing method S1 according to the present exemplary embodiment, monitor information on the optical fiber communication path between the terminal device and the communication device is input, and information on the cause of the failure in the optical fiber communication path is input. A configuration for estimating the cause of failure in the optical fiber communication path based on the output estimation model is adopted. Therefore, according to the information processing method S1 according to this exemplary embodiment, the same effects as the information processing apparatus 1 can be obtained.
 (情報処理方法S2の流れ)
 本例示的実施形態に係る情報処理方法S2について、図4を参照して説明する。図4は、情報処理装置2による情報処理方法S2の流れを示すフロー図である。
(Flow of information processing method S2)
The information processing method S2 according to this exemplary embodiment will be described with reference to FIG. FIG. 4 is a flowchart showing the flow of the information processing method S2 by the information processing device 2. As shown in FIG.
 (ステップS22)
 ステップS22において、取得部22は、光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを取得する。
(Step S22)
In step S22, the acquisition unit 22 acquires teacher data including a set of monitor information on the optical fiber communication channel and information on the defect in the optical fiber communication channel.
 (ステップS23)
 ステップS23において、学習部23は、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを、ステップS22において取得部22が取得した教師データを参照して学習する。
(Step S23)
In step S23, the learning unit 23 receives monitor information about the optical fiber communication channel, and refers to the teacher data acquired by the acquisition unit 22 in step S22 for an estimation model that outputs information about the cause of failure in the optical fiber communication channel. and learn.
 以上のように、本例示的実施形態に係る情報処理方法S2においては、光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを参照して、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを学習する構成が採用されている。したがって、本例示的実施形態に係る情報処理方法S2によれば、情報処理装置2と同様の効果を奏する。 As described above, in the information processing method S2 according to the present exemplary embodiment, the optical fiber A configuration is adopted that learns an estimation model that outputs information about the cause of failure in the communication channel. Therefore, according to the information processing method S<b>2 according to this exemplary embodiment, the same effects as those of the information processing apparatus 2 can be obtained.
 (情報処理システム100の構成)
 本例示的実施形態に係る情報処理システム100の構成について、図5を参照して説明する。図5は、情報処理システム100の構成を示すブロック図である。
(Configuration of information processing system 100)
The configuration of the information processing system 100 according to this exemplary embodiment will be described with reference to FIG. FIG. 5 is a block diagram showing the configuration of the information processing system 100. As shown in FIG.
 図5に示すように、情報処理システム100は、取得部12、及び推定部13を備えている。取得部12、及び推定部13は、それぞれ本例示的実施形態において取得手段、及び推定手段を実現する構成である。 As shown in FIG. 5, the information processing system 100 includes an acquisition unit 12 and an estimation unit 13. The obtaining unit 12 and the estimating unit 13 are configured to implement obtaining means and estimating means, respectively, in this exemplary embodiment.
 取得部12は、光ファイバ通信路に関するモニタ情報を取得する。 The acquisition unit 12 acquires monitor information regarding the optical fiber communication path.
 推定部13は、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、光ファイバ通信路における不具合の要因を推定する。 The estimating unit 13 receives monitor information about the optical fiber communication channel and estimates the cause of the problem in the optical fiber communication channel based on an estimation model that outputs information about the cause of the problem in the optical fiber communication channel.
 以上のように、本例示的実施形態に係る情報処理システム100においては、モニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、光ファイバ通信路における不具合の要因を推定する構成が採用されている。したがって、本例示的実施形態に係る情報処理システム100においては、推定モデルに取得したモニタ情報を入力し、当該推定モデルが光ファイバ通信路における不具合の要因を推定するので、光ファイバ通信路における不具合の要因を好適に推定することができる。 As described above, in the information processing system 100 according to the present exemplary embodiment, based on an estimation model that inputs monitor information and outputs information about the cause of the defect in the optical fiber communication path, A configuration for estimating the factors of Therefore, in the information processing system 100 according to this exemplary embodiment, the acquired monitor information is input to the estimation model, and the estimation model estimates the cause of the failure in the optical fiber communication channel. can be suitably estimated.
 (情報処理システム200の構成)
 本例示的実施形態に係る情報処理システム200の構成について、図6を参照して説明する。図6は、情報処理システム200の構成を示すブロック図である。
(Configuration of information processing system 200)
The configuration of an information processing system 200 according to this exemplary embodiment will be described with reference to FIG. FIG. 6 is a block diagram showing the configuration of the information processing system 200. As shown in FIG.
 図6に示すように、情報処理システム200は、取得部22、及び学習部23を備えている。取得部22、及び学習部23はそれぞれ、本例示的実施形態において取得手段、及び学習手段を実現する構成である。 As shown in FIG. 6, the information processing system 200 includes an acquisition unit 22 and a learning unit 23. The acquisition unit 22 and the learning unit 23 are configured to implement acquisition means and learning means, respectively, in this exemplary embodiment.
 取得部22は、光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを取得する。 The acquisition unit 22 acquires teacher data that includes a set of monitor information on the optical fiber communication channel and information on failures in the optical fiber communication channel.
 学習部23は、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを、前記取得手段が取得した教師データを参照して学習する。 The learning unit 23 learns an estimation model that receives monitor information about the optical fiber communication channel and outputs information about the cause of the defect in the optical fiber communication channel by referring to the teacher data acquired by the acquisition means.
 以上のように、本例示的実施形態に係る情報処理システム100においては、光ファイバ通信路に関するモニタ情報を提供し、光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを取得する。そして、情報処理システム100は、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを、取得した教師データを参照して学習する構成が採用されている。したがって、本例示的実施形態に係る情報処理システム100においては、モニタ情報と光ファイバ通信路における不具合に関する情報との組を含む教師データとして推定モデルが学習されるので、光ファイバ通信路における不具合の要因を好適に推定することができる。 As described above, in the information processing system 100 according to this exemplary embodiment, monitor information relating to optical fiber communication paths is provided, and a combination of monitor information relating to optical fiber communication paths and information relating to defects in optical fiber communication paths is provided. Get teacher data containing Then, the information processing system 100 adopts a configuration in which monitor information about the optical fiber communication path is input, and an estimation model that outputs information about the cause of failure in the optical fiber communication path is learned by referring to the acquired teacher data. ing. Therefore, in the information processing system 100 according to the present exemplary embodiment, an estimation model is learned as teacher data including a set of monitor information and information about failures in the optical fiber communication path. Factors can be estimated favorably.
 〔例示的実施形態2〕
 本発明の第2の例示的実施形態について、図面を参照して詳細に説明する。なお、例示的実施形態1にて説明した構成要素と同じ機能を有する構成要素については、同じ符号を付し、その説明を適宜省略する。
[Exemplary embodiment 2]
A second exemplary embodiment of the invention will now be described in detail with reference to the drawings. Components having the same functions as the components described in the exemplary embodiment 1 are denoted by the same reference numerals, and descriptions thereof are omitted as appropriate.
 (情報処理システム100Aの構成)
 図7は、本発明の例示的実施形態2に係る情報処理システム100Aの構成を示すブロック図である。図7に示すように、情報処理システム100Aは、情報処理装置1A、通信装置50、入出力装置60、第1の端末装置70-1、及び第2の端末装置70-2を含んでいる。
(Configuration of information processing system 100A)
FIG. 7 is a block diagram showing the configuration of an information processing system 100A according to Exemplary Embodiment 2 of the present invention. As shown in FIG. 7, the information processing system 100A includes an information processing device 1A, a communication device 50, an input/output device 60, a first terminal device 70-1, and a second terminal device 70-2.
 通信装置50と、第1の端末装置70-1及び第2の端末装置70-2とは、それぞれ光ファイバ通信路F1及び光ファイバ通信路F2を介して互いに通信可能に接続されている。 The communication device 50, the first terminal device 70-1 and the second terminal device 70-2 are communicably connected to each other via the optical fiber communication path F1 and the optical fiber communication path F2, respectively.
 また、情報処理装置1A、通信装置50、及び入出力装置60は、ネットワークNを介して互いに通信可能に接続されている。 In addition, the information processing device 1A, the communication device 50, and the input/output device 60 are connected via the network N so as to be able to communicate with each other.
 ネットワークNの具体的構成は本実施形態を限定するものではないが、一例として、無線LAN(Local Area Network)、有線LAN、WAN(Wide Area Network)、公衆回線網、モバイルデータ通信網、又は、これらのネットワークの組み合わせを用いることができる。 The specific configuration of the network N does not limit this embodiment, but as an example, a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or A combination of these networks can be used.
 情報処理システム100Aは、第1の端末装置70-1及び第2の端末装置70-2と通信装置50との間のそれぞれの光ファイバ通信路F1及び光ファイバ通信路F2における不具合の要因を情報処理装置1Aにおいて推定する。また、情報処理システム100Aは、情報処理装置1Aにおいて推定された推定結果を入出力装置60において提示する。例えば、端末装置70-1及び端末装置70-2はエンドユーザが使用する装置であり、通信装置50は端末装置70-1及び端末装置70-2との間の光ファイバ通信路F1及び光ファイバ通信路F2の状態をモニタする装置であり、入出力装置60は光ファイバ通信路F1及び光ファイバ通信路F2の保守作業者が使用する装置である。 The information processing system 100A obtains information about the causes of failures in the optical fiber communication paths F1 and F2 between the first terminal device 70-1 and the second terminal device 70-2 and the communication device 50, respectively. It is estimated in the processing device 1A. Further, the information processing system 100A presents the estimation result estimated by the information processing device 1A on the input/output device 60. FIG. For example, the terminal device 70-1 and the terminal device 70-2 are devices used by end users, and the communication device 50 is an optical fiber communication path F1 and an optical fiber communication path F1 between the terminal device 70-1 and the terminal device 70-2. It is a device for monitoring the state of the communication path F2, and the input/output device 60 is a device used by a maintenance worker for the optical fiber communication paths F1 and F2.
 なお、図7に示す例では、端末装置として第1の端末装置70-1及び第2の端末装置70-2の2つを例示しているが、これは本実施形態を限定するものではなく、情報処理システム100Aは、任意の個数の端末装置を含む構成とすることができる。また、本例示的実施形態において、これら複数の端末装置は、互いに同様な要部構成を備えている。また、第1の端末装置70-1及び第2の端末装置70-2の何れかを指す場合、単に端末装置70と称する。光ファイバ通信路F1及び光ファイバ通信路F2も同様に、何れかを指す場合、単に光ファイバ通信路Fと称する。 In the example shown in FIG. 7, two terminal devices, the first terminal device 70-1 and the second terminal device 70-2, are illustrated, but this does not limit the present embodiment. , the information processing system 100A can be configured to include any number of terminal devices. In addition, in this exemplary embodiment, these terminal devices have the same main configuration as each other. Also, when referring to either the first terminal device 70-1 or the second terminal device 70-2, the terminal device 70 is simply referred to. Similarly, the optical fiber communication path F1 and the optical fiber communication path F2 are simply referred to as an optical fiber communication path F when referring to any one of them.
 (通信装置50の構成)
 図7に示すように、通信装置50は、制御部51、第1の通信部52、第2の通信部53を備えている。
(Configuration of communication device 50)
As shown in FIG. 7 , the communication device 50 includes a control section 51 , a first communication section 52 and a second communication section 53 .
 第1の通信部52は、ネットワークNを介した通信を行うための通信モジュールである。第1の通信部52は、制御部51から取得したデータを、ネットワークNを介して情報処理装置1Aに出力する。 The first communication unit 52 is a communication module for performing communication via the network N. The first communication unit 52 outputs the data acquired from the control unit 51 to the information processing device 1A via the network N.
 第2の通信部53は、端末装置70と通信を行うための通信モジュールである。第2の通信部53は、端末装置70から光ファイバ通信路Fを介して取得したデータを制御部51に出力する。 The second communication unit 53 is a communication module for communicating with the terminal device 70. The second communication unit 53 outputs data acquired from the terminal device 70 via the optical fiber communication path F to the control unit 51 .
 (制御部51)
 制御部51は、例えば1つ以上のプロセッサ(例えばCPUなど)が、メモリ(例えばRAMやROMなど)に記憶されているプログラムを実行することによって、通信装置50の各構成要素を制御する。
(control unit 51)
The control unit 51 controls each component of the communication device 50 by executing a program stored in a memory (eg, RAM, ROM, etc.) by one or more processors (eg, CPU, etc.), for example.
 制御部51は、図7に示すように、モニタ情報取得部511及び提供部21としても機能する。 The control unit 51 also functions as a monitor information acquisition unit 511 and a provision unit 21, as shown in FIG.
 モニタ情報取得部511は、第2の通信部53を介した端末装置70との通信をモニタし、モニタ情報を取得する。 The monitor information acquisition unit 511 monitors communication with the terminal device 70 via the second communication unit 53 and acquires monitor information.
 本例示的実施形態におけるモニタ情報に含まれる情報の一例として、
・端末装置70を他の端末と識別するための端末識別子
・光ファイバ通信路Fにおける送信パワー及び受信パワー
・光ファイバ通信路Fにおけるパケットエラーの回数
・当該送信パワー及び受信パワー、並びに当該パケットエラーの回数の情報を取得した時刻
が挙げられるが、これは本例示的実施形態を限定するものではない。
As an example of information included in the monitor information in this exemplary embodiment,
A terminal identifier for distinguishing the terminal device 70 from other terminals Transmission power and reception power in the optical fiber communication path F Number of packet errors in the optical fiber communication path F Transmission power and reception power, and the packet error number of times information is acquired, but this is not a limitation of this exemplary embodiment.
 提供部21は、モニタ情報取得部511が取得したモニタ情報を、第1の通信部52を介して情報処理装置1Aに提供する。また、提供部21は、取得したモニタ情報が、光ファイバ通信路Fの通信断が発生したことを示しているか否かを判定する。例えば、提供部21は、モニタ情報に、LOS(Loss of Signal)信号が含まれているか否かを判定する構成であってもよい。光ファイバ通信路Fの通信断が発生したと判定された場合、提供部21は、光ファイバ通信路Fの通信断が発生したことを示すイベント情報を、第1の通信部52を介して情報処理装置1Aに提供する。 The provision unit 21 provides the monitor information acquired by the monitor information acquisition unit 511 to the information processing apparatus 1A via the first communication unit 52. Further, the providing unit 21 determines whether or not the acquired monitor information indicates that the communication disconnection of the optical fiber communication path F has occurred. For example, the providing unit 21 may be configured to determine whether or not the monitor information includes a LOS (Loss of Signal) signal. When it is determined that the communication interruption of the optical fiber communication path F has occurred, the provision unit 21 transmits event information indicating that the communication interruption of the optical fiber communication path F has occurred via the first communication unit 52. It is provided to the processing device 1A.
 なお、イベント情報は、光ファイバ通信路Fの通信断以外のイベントを示す情報であってもよい。他のイベントの例として、
・光ファイバ通信路Fにおける送信パワー及び受信パワーの値が所定の値より小さくなる
・パケットエラーの回数の値が所定の値より大きくなる
が挙げられるが、これは本例示的実施形態を限定するものではない。
The event information may be information indicating an event other than the communication interruption of the optical fiber communication path F. FIG. Another example of an event is
- the value of the transmitted power and the received power in the optical fiber channel F is less than a predetermined value; and - the value of the number of packet errors is greater than a predetermined value, which limits this exemplary embodiment. not a thing
 また、イベント情報に含まれる情報は、イベントを示す情報の他に、
・端末装置70を他の端末と識別するための端末識別子
・イベントが発生した時刻
が含まれていてもよい。ただし、これは本例示的実施形態を限定するものではない。
In addition to the information indicating the event, the information included in the event information includes:
- A terminal identifier for identifying the terminal device 70 from other terminals - The time when the event occurred may be included. However, this is not a limitation of this exemplary embodiment.
 (情報処理装置1Aの構成)
 図7に示すように、情報処理装置1Aは、制御部10A、記憶部18A、及び通信部19を備えている。記憶部18Aは、本例示的実施形態において記憶手段を実現する構成である。
(Configuration of information processing device 1A)
As shown in FIG. 7, the information processing apparatus 1A includes a control section 10A, a storage section 18A, and a communication section 19. As shown in FIG. The storage unit 18A is a configuration that implements storage means in this exemplary embodiment.
 記憶部18Aは、制御部10Aによって参照されるモニタ情報MI1及びモデルパラメータMPを記憶するメモリである。記憶部18Aは、例えば、内容の書き換えが可能な不揮発性メモリである、EPROM、EEPROM(登録商標)、HDD、フラッシュメモリなどで実現される。 The storage unit 18A is a memory that stores monitor information MI1 and model parameters MP that are referenced by the control unit 10A. The storage unit 18A is realized by, for example, EPROM, EEPROM (registered trademark), HDD, flash memory, etc., which are rewritable nonvolatile memories.
 モニタ情報MI1は、通信装置50から提供されるモニタ情報を蓄積したものである。なお、モニタ情報MI1は、推定モデルによって光ファイバ通信路Fにおける不具合の要因を推定するために参照するモニタ情報であるため、第1のモニタ情報MI1とも呼称する。 The monitor information MI1 is accumulated monitor information provided from the communication device 50 . Note that the monitor information MI1 is also referred to as the first monitor information MI1 because it is monitor information that is referred to for estimating the cause of the failure in the optical fiber communication path F using the estimation model.
 モデルパラメータMPは、推定モデルを規定するパラメータである。推定モデルは、モニタ情報MI1から抽出されたモニタ情報が入力され、光ファイバ通信路における不具合の要因に関する情報を出力する。 A model parameter MP is a parameter that defines an estimation model. The estimation model receives the monitor information extracted from the monitor information MI1 and outputs information about the cause of the failure in the optical fiber communication path.
 なお、上記推定モデルの具体的構成は本例示的実施形態を限定するものではないが、一例として、CNN、RNN、又はそれらの組み合わせを用いることができる。また、ランダムフォレストやサポートベクターマシンのような非ニューラルネットワーク型のモデルを用いてもよい。 Although the specific configuration of the estimation model does not limit this exemplary embodiment, as an example, CNN, RNN, or a combination thereof can be used. Non-neural network models such as random forests and support vector machines may also be used.
 通信部19は、ネットワークNを介した通信を行うための通信モジュールである。通信部19は、ネットワークNを介して取得したデータを制御部10Aに出力したり、制御部10Aから取得したデータを、ネットワークNを介して出力したりする。 The communication unit 19 is a communication module for performing communication via the network N. The communication unit 19 outputs data acquired through the network N to the control unit 10A, and outputs data acquired from the control unit 10A through the network N.
 (制御部10A)
 制御部10Aは、例えば1つ以上のプロセッサ(例えばCPU(Central Processing Unit)など)が、メモリ(例えばRAM(random access memory)やROM(read only memory)など)に記憶されているプログラムを実行することによって、情報処理装置1Aの各構成要素を制御する。
(Control section 10A)
In the control unit 10A, for example, one or more processors (such as a CPU (Central Processing Unit)) execute a program stored in a memory (such as a RAM (random access memory) or a ROM (read only memory)). Thereby, each component of the information processing apparatus 1A is controlled.
 制御部10Aは、図7に示すように、取得部12、推定部13、蓄積部14、抽出部15、及び出力部17としても機能する。取得部12、推定部13、抽出部15、及び出力部17は、それぞれ、本例示的実施形態において取得手段、推定手段、抽出手段、及び出力手段を実現する構成である。 The control unit 10A also functions as an acquisition unit 12, an estimation unit 13, an accumulation unit 14, an extraction unit 15, and an output unit 17, as shown in FIG. The obtaining unit 12, the estimating unit 13, the extracting unit 15, and the output unit 17 are configured to implement obtaining means, estimating means, extracting means, and output means, respectively, in this exemplary embodiment.
 取得部12は、光ファイバ通信路Fに関するモニタ情報を、通信部19を介して通信装置50から取得する。取得部12は、取得したモニタ情報を蓄積部14に出力する。また、取得部12は、通信装置50から出力されたイベント情報を、通信部19を介して取得する。取得部12は、取得したイベント情報を、抽出部15に出力する。 The acquisition unit 12 acquires monitor information about the optical fiber communication path F from the communication device 50 via the communication unit 19 . The acquisition unit 12 outputs the acquired monitor information to the accumulation unit 14 . The acquisition unit 12 also acquires event information output from the communication device 50 via the communication unit 19 . The acquisition unit 12 outputs the acquired event information to the extraction unit 15 .
 推定部13は、光ファイバ通信路Fの通信断の発生に応じて、推定モデルに対して、抽出部15によって抽出されたモニタ情報を入力することにより、光ファイバ通信路Fにおける不具合の要因を推定する。なお、本例示的実施形態では、推定部13は光ファイバ通信路Fの通信断の発生に応じて光ファイバ通信路Fにおける不具合の要因を推定するが、これは一例であり、上述した他のイベントの一例が発生したことに応じて光ファイバ通信路Fにおける不具合の要因を推定する構成であればよい。推定部13は、推定結果を生成し、出力部17に出力する。 The estimating unit 13 inputs the monitor information extracted by the extracting unit 15 to the estimation model in response to the occurrence of communication interruption in the optical fiber communication channel F, thereby identifying the cause of the failure in the optical fiber communication channel F. presume. In this exemplary embodiment, the estimating unit 13 estimates the cause of the problem in the optical fiber communication path F according to the occurrence of communication interruption in the optical fiber communication path F, but this is an example, and the above-described other Any configuration may be used as long as the cause of the failure in the optical fiber communication path F is estimated in accordance with the occurrence of an event. The estimation unit 13 generates an estimation result and outputs it to the output unit 17 .
 推定部13が生成する推定結果に含まれる情報として、
・通信断が光ファイバ通信路の不具合に起因したものである可能性(確度)
・保守作業の優先度
・光ファイバ通信路Fに関して推奨される保守作業を示す情報
・推定される不具合の原因(例えば、光ファイバ通信路の劣化、切断、端末装置70の電源OFFなど)
が挙げられるが、これは本例示的実施形態を限定するものではない。
As information included in the estimation result generated by the estimation unit 13,
・Possibility (accuracy) that the communication interruption was caused by the failure of the optical fiber communication path
・Priority of maintenance work ・Information indicating recommended maintenance work for the optical fiber communication path F ・Presumed cause of failure (for example, deterioration of the optical fiber communication path, disconnection, power off of the terminal device 70, etc.)
is not intended to limit this exemplary embodiment.
 このように、推定部13は、光ファイバ通信路Fの通信断の発生に応じて、光ファイバ通信路Fにおける不具合の要因を推定するので、光ファイバ通信路Fの通信断が不具合によって起きた場合、光ファイバ通信路における不具合の要因を好適に推定することができる。 In this way, the estimating unit 13 estimates the cause of the failure in the optical fiber communication path F according to the occurrence of the communication interruption in the optical fiber communication path F. In this case, it is possible to preferably estimate the cause of the problem in the optical fiber communication path.
 蓄積部14は、取得部12が取得したモニタ情報を記憶部18Aに蓄積する。 The accumulation unit 14 accumulates the monitor information acquired by the acquisition unit 12 in the storage unit 18A.
 抽出部15は、取得部12から出力されたイベント情報を参照し、当該イベント情報が光ファイバ通信路Fの通信断を示す場合、当該通信断の発生に応じて、前記通信断に関するモニタ情報を記憶部18Aのモニタ情報MI1から抽出する。 The extraction unit 15 refers to the event information output from the acquisition unit 12, and when the event information indicates a communication interruption of the optical fiber communication path F, the extraction unit 15 extracts monitor information regarding the communication interruption in response to the occurrence of the communication interruption. It is extracted from the monitor information MI1 in the storage unit 18A.
 なお、抽出部15は、取得部12から出力されたイベント情報を参照し、当該イベント情報が光ファイバ通信路Fの通信断を示す場合、当該通信断の発生に応じて、当該通信断の発生のタイミングに応じた通信断に関するモニタ情報を記憶部18Aのモニタ情報MI1から抽出する構成であってもよい。また、通信断の発生のタイミングに応じた通信断に関するモニタ情報は、通信断発生のタイミングに応じた所定期間におけるモニタ情報であってもよい。イベント発生のタイミングに応じた所定期間におけるモニタ情報の例として、イベント発生時点から10分前までの期間におけるモニタ情報、イベント発生時点から1時間前までの期間におけるモニタ情報、などが挙げられるが、これは例示的本実施形態を限定するものではない。 Note that the extraction unit 15 refers to the event information output from the acquisition unit 12, and when the event information indicates a communication disconnection of the optical fiber communication path F, the communication disconnection occurs according to the occurrence of the communication disconnection. The configuration may be such that the monitor information related to the communication disconnection according to the timing of is extracted from the monitor information MI1 of the storage unit 18A. Further, the monitor information related to the communication interruption according to the timing of the occurrence of the communication interruption may be monitor information for a predetermined period according to the timing of the occurrence of the communication interruption. Examples of monitor information in a predetermined period corresponding to the timing of event occurrence include monitor information in the period from the time of event occurrence to 10 minutes before, monitor information in the period from the time of event occurrence to 1 hour before, and the like. This is not a limitation of this exemplary embodiment.
 出力部17は、推定部13が生成した推定結果を取得し、通信部19を介して当該推定結果を入出力装置60に出力する。 The output unit 17 acquires the estimation result generated by the estimation unit 13 and outputs the estimation result to the input/output device 60 via the communication unit 19 .
 (入出力装置60の構成)
 図7に示すように、入出力装置60は、提示部61及び操作受付部62を備えている。
(Configuration of input/output device 60)
As shown in FIG. 7 , the input/output device 60 includes a presentation section 61 and an operation reception section 62 .
 提示部61は、情報処理装置1Aから出力された推定結果を取得する。提示部61は、操作受付部62から、後述する操作情報を取得し、当該操作情報が推定結果を表示する旨の操作を示す場合、取得した推定結果を提示する。提示部61は、一例として表示パネルを備え、当該表示パネルに当該推定結果を表示させることによって、当該推定結果を提示する。 The presentation unit 61 acquires the estimation result output from the information processing device 1A. The presentation unit 61 acquires operation information, which will be described later, from the operation reception unit 62, and presents the acquired estimation result when the operation information indicates an operation for displaying the estimation result. The presentation unit 61 has a display panel as an example, and presents the estimation result by displaying the estimation result on the display panel.
 操作受付部62は、ユーザからの操作を受け付ける。操作受付部62の一例として、提示部61が備える表示パネルに重畳して配置されたタッチパネルを備える構成とすることができるが、これは本例示的実施形態を限定するものではない。操作受付部62は、ユーザから受け付けた操作を示す操作情報を、提示部61に出力する。 The operation reception unit 62 receives operations from the user. As an example of the operation reception unit 62, it may be configured to include a touch panel superimposed on the display panel of the presentation unit 61, but this does not limit the exemplary embodiment. The operation accepting portion 62 outputs operation information indicating the operation accepted from the user to the presenting portion 61 .
 (情報処理方法S100Aの流れ)
 本例示的実施形態に係る情報処理方法S100Aについて、図8を参照して説明する。図8は、情報処理システム100Aによる情報処理方法S100Aの流れを示すシーケンス図である。
(Flow of information processing method S100A)
An information processing method S100A according to this exemplary embodiment will be described with reference to FIG. FIG. 8 is a sequence diagram showing the flow of the information processing method S100A by the information processing system 100A.
 (ステップS102)
 ステップS102において、通信装置50のモニタ情報取得部511は、モニタ情報を取得する。
(Step S102)
In step S102, the monitor information acquisition unit 511 of the communication device 50 acquires monitor information.
 (ステップS103)
 ステップS103において、提供部21は、モニタ情報取得部511が取得したモニタ情報を、第1の通信部52を介して情報処理装置1Aに提供する。
(Step S103)
In step S<b>103 , the provision unit 21 provides the monitor information acquired by the monitor information acquisition unit 511 to the information processing apparatus 1</b>A via the first communication unit 52 .
 (ステップS104)
 ステップS104において、情報処理装置1Aの取得部12は、通信部19を介して、通信装置50から提供されたモニタ情報を取得する。
(Step S104)
In step S<b>104 , the acquisition unit 12 of the information processing device 1</b>A acquires monitor information provided from the communication device 50 via the communication unit 19 .
 (ステップS105)
 ステップS105において、蓄積部14は、ステップS104において取得部12が取得したモニタ情報を、記憶部18Aに蓄積する。記憶部18Aは、モニタ情報を記憶する。
(Step S105)
In step S105, the accumulation unit 14 accumulates the monitor information acquired by the acquisition unit 12 in step S104 in the storage unit 18A. The storage unit 18A stores monitor information.
 (ステップS106)
 ステップS106において、モニタ情報取得部511は、取得したモニタ情報を参照し、光ファイバ通信路Fの通信断が発生したか否かを判定する。光ファイバ通信路Fの通信断が発生していないと判定された場合、通信装置50の処理はステップS102に戻る。
(Step S106)
In step S106, the monitor information acquisition unit 511 refers to the acquired monitor information and determines whether or not communication interruption of the optical fiber communication path F has occurred. If it is determined that the communication disconnection of the optical fiber communication path F has not occurred, the processing of the communication device 50 returns to step S102.
 (ステップS107)
 ステップS106において、光ファイバ通信路Fの通信断が発生したと判定された場合、提供部21は、第1の通信部52を介して光ファイバ通信路Fの通信断が発生したことを示すイベント情報を提供する。
(Step S107)
If it is determined in step S106 that the communication interruption of the optical fiber communication path F has occurred, the providing unit 21 sends an event indicating that the communication interruption of the optical fiber communication path F has occurred via the first communication unit 52. provide information.
 (ステップS108)
 ステップS108において、情報処理装置1Aの取得部12は、通信装置50から供給されたイベント情報を、通信部19を介して取得する。
(Step S108)
In step S<b>108 , the acquisition unit 12 of the information processing device 1</b>A acquires the event information supplied from the communication device 50 via the communication unit 19 .
 (ステップS109)
 ステップS109において、抽出部15は、取得部12が取得したイベント情報を参照し、当該イベント情報が通信断を示す場合、当該通信断の発生に応じて、通信断に関するモニタ情報を、記憶部18Aに蓄積されているモニタ情報MI1から抽出する。
(Step S109)
In step S109, the extraction unit 15 refers to the event information acquired by the acquisition unit 12, and if the event information indicates communication interruption, the extraction unit 15 stores monitor information about the communication interruption in response to the occurrence of the communication interruption. is extracted from the monitor information MI1 accumulated in the .
 (ステップS110)
 ステップS110において、推定部13は、抽出されたモニタ情報を推定モデルに入力し、光ファイバ通信路Fにおける通信断における不具合の要因を推定する。換言すると、推定部13は、光ファイバ通信路Fの通信断の発生に応じて、通信断に関するモニタ情報を参照して、光ファイバ通信路Fにおける不具合の要因を推定する。
(Step S110)
In step S<b>110 , the estimation unit 13 inputs the extracted monitor information to the estimation model, and estimates the cause of the failure caused by the communication interruption in the optical fiber communication path F. In other words, the estimating unit 13 estimates the cause of the failure in the optical fiber communication path F by referring to the monitor information regarding the communication interruption in response to the occurrence of the communication interruption in the optical fiber communication path F.
 (ステップS111)
 ステップS111において、推定部13は、ステップS110において推定した推定結果を、出力部17に提供する。出力部17は、推定結果を、通信部19を介して入出力装置60に出力する。
(Step S111)
In step S<b>111 , the estimation unit 13 provides the estimation result estimated in step S<b>110 to the output unit 17 . The output unit 17 outputs the estimation result to the input/output device 60 via the communication unit 19 .
 (ステップS112)
 ステップS112において、入出力装置60の提示部61は、ステップS111において情報処理装置1Aが提供した推定結果を取得する。
(Step S112)
In step S112, the presentation unit 61 of the input/output device 60 acquires the estimation result provided by the information processing device 1A in step S111.
 (ステップS113)
 ステップS113において、提示部61は、推定結果を表示する。この構成により、入出力装置60は、推定結果に含まれる保守作業の優先度及び光ファイバ通信路Fに関して推奨される保守作業を示す情報を、入出力装置60を使用する保守作業者に提示することができる。
(Step S113)
In step S113, the presentation unit 61 displays the estimation result. With this configuration, the input/output device 60 presents to the maintenance worker using the input/output device 60 information indicating the priority of maintenance work included in the estimation result and the maintenance work recommended for the optical fiber communication path F. be able to.
 このように、情報処理システム100Aでは、通信装置50から提供されるモニタ情報が、記憶部18Aにモニタ情報MI1として蓄積される。そして、情報処理システム100Aでは、光ファイバ通信路Fの通信断の発生に応じて、通信断に関するモニタ情報を参照して、光ファイバ通信路Fにおける不具合の要因を推定する。 Thus, in the information processing system 100A, monitor information provided from the communication device 50 is accumulated in the storage unit 18A as monitor information MI1. Then, in the information processing system 100A, in response to the occurrence of the communication disconnection of the optical fiber communication channel F, the cause of the failure in the optical fiber communication channel F is estimated by referring to the monitor information regarding the communication disconnection.
 光ファイバ通信路Fの通信断は、端末装置70がエンドユーザによって電源OFFされた場合でも発生する。一方、光ファイバ通信路Fの劣化又は切断によって通信断が発生した場合、通信断が発生する前に光ファイバ通信路Fにおける送信パワー及び受信パワーの低下又はパケットエラーの回数の増加が発生する傾向がある。 A communication disconnection of the optical fiber communication path F occurs even when the terminal device 70 is turned off by the end user. On the other hand, when a communication interruption occurs due to degradation or disconnection of the optical fiber communication path F, there is a tendency for the transmission power and reception power in the optical fiber communication path F to decrease or the number of packet errors to increase before the communication interruption occurs. There is
 情報処理システム100Aでは、光ファイバ通信路Fの通信断の発生前の光ファイバ通信路Fの状態を考慮した上で、光ファイバ通信路Fにおける不具合の要因を推定するので、光ファイバ通信路における不具合の要因を好適に推定することができる。 In the information processing system 100A, after considering the state of the optical fiber communication path F before the communication interruption of the optical fiber communication path F, the cause of the failure in the optical fiber communication path F is estimated. It is possible to suitably estimate the cause of the defect.
 〔例示的実施形態3〕
 本発明の第3の例示的実施形態について、図面を参照して詳細に説明する。なお、例示的実施形態1及び例示的実施形態2にて説明した構成要素と同じ機能を有する構成要素については、同じ符号を付し、その説明を適宜省略する。
[Exemplary embodiment 3]
A third exemplary embodiment of the invention will now be described in detail with reference to the drawings. Components having the same functions as those described in exemplary embodiments 1 and 2 are denoted by the same reference numerals, and description thereof will be omitted as appropriate.
 (情報処理システム100Bの構成)
 図9は、本発明の例示的実施形態3に係る情報処理システム100Bの構成を示すブロック図である。図9に示すように、情報処理システム100Bは、上述した情報処理システム100Aにおける情報処理装置1Aに替えて、情報処理装置1Bを備える構成である。
(Configuration of information processing system 100B)
FIG. 9 is a block diagram showing the configuration of an information processing system 100B according to Exemplary Embodiment 3 of the present invention. As shown in FIG. 9, the information processing system 100B is configured to include an information processing device 1B instead of the information processing device 1A in the information processing system 100A described above.
 情報処理システム100Bは、光ファイバ通信路Fに関するモニタ情報と、光ファイバ通信路Fにおける不具合に関する情報との組を含む教師データを参照して、推定モデルを学習する。 The information processing system 100B learns an estimation model by referring to teacher data including a set of monitor information on the optical fiber communication channel F and information on defects in the optical fiber communication channel F.
 (入出力装置60の構成)
 入出力装置60は、図9に示すように、提示部61及び操作受付部62を備えている。なお、提示部61は、上述した通りである。
(Configuration of input/output device 60)
The input/output device 60 includes a presentation unit 61 and an operation reception unit 62, as shown in FIG. Note that the presentation unit 61 is as described above.
 操作受付部62は、ユーザ(保守業者)から不具合に関する以下の情報を入力する操作を受け付ける。
・端末装置70を他の端末と識別するための端末識別子
・光ファイバ通信路Fにおける不具合発生の時刻
・上記不具合の種別
 操作受付部62は、上記情報を入力する操作を受け付けると、上記情報を含む不具合情報を、ネットワークNを介して情報処理装置1Bに出力する。
The operation accepting unit 62 accepts an operation of inputting the following information regarding the problem from the user (maintenance company).
- A terminal identifier for distinguishing the terminal device 70 from other terminals - Time of failure occurrence in the optical fiber communication path F - Type of failure The defect information included is output via the network N to the information processing device 1B.
 (情報処理装置1Bの構成)
 情報処理装置1Bは図9に示すように、制御部10B、記憶部18B、及び通信部19を備えている。なお、通信部19は、上述した通りである。
(Configuration of information processing device 1B)
The information processing apparatus 1B includes a control section 10B, a storage section 18B, and a communication section 19, as shown in FIG. Note that the communication unit 19 is as described above.
 記憶部18Bは、制御部10Bによって参照されるモデルパラメータMP、モニタ情報MI2、及び不具合情報EIが格納されるメモリである。記憶部62は、例えば、内容の書き換えが可能な不揮発性メモリである、EPROM、EEPROM、HDD、フラッシュメモリなどで実現される。モデルパラメータMPについては、上述した通りである。 The storage unit 18B is a memory that stores model parameters MP, monitor information MI2, and defect information EI that are referred to by the control unit 10B. The storage unit 62 is realized by EPROM, EEPROM, HDD, flash memory, etc., which are rewritable non-volatile memories, for example. The model parameter MP is as described above.
 モニタ情報MI2は、通信装置50から提供されるモニタ情報のうち、後述する不具合情報EIと関連付けられて格納されるモニタ情報である。なお、モニタ情報MI2は、推定モデルを学習するために参照するモニタ情報であるため、第2のモニタ情報MI2とも呼称する。 The monitor information MI2 is, of the monitor information provided from the communication device 50, stored in association with the defect information EI, which will be described later. Note that the monitor information MI2 is also referred to as second monitor information MI2 because it is monitor information that is referred to for learning the estimation model.
 不具合情報EIは、入出力装置60から提供される不具合情報のうち、モニタ情報MI2と関連付けられて格納される不具合情報である。 The defect information EI is defect information provided from the input/output device 60 and stored in association with the monitor information MI2.
 モニタ情報MI2と不具合情報EIとを関連付ける処理の詳細は、後述する。 The details of the process of associating the monitor information MI2 and the defect information EI will be described later.
 (制御部10B)
 制御部10Bは、例えば1つ以上のプロセッサ(例えばCPUなど)が、メモリ(例えばRAMやROMなど)に記憶されているプログラムを実行することによって、情報処理装置1Bの各構成要素を制御する。
(control unit 10B)
The control unit 10B controls each component of the information processing apparatus 1B by executing a program stored in a memory (eg, RAM, ROM, etc.) by one or more processors (eg, CPU, etc.), for example.
 制御部10Bは、図9に示すように、取得部12及び学習部16としても機能する。取得部12及び学習部16は、それぞれ、本例示的実施形態において取得手段及び学習手段を実現する構成である。 The control unit 10B also functions as an acquisition unit 12 and a learning unit 16, as shown in FIG. The acquisition unit 12 and the learning unit 16 are configured to implement acquisition means and learning means, respectively, in this exemplary embodiment.
 取得部12は、光ファイバ通信路Fに関するモニタ情報を、通信部19を介して通信装置50から取得する。また、取得部12は、光ファイバ通信路Fにおける不具合に関する不具合情報を、通信部19を介して入出力装置60から取得する。また、取得部12は、不具合情報EIとモニタ情報MI2とを関連付けて記憶部18Bに格納する。 The acquisition unit 12 acquires monitor information about the optical fiber communication path F from the communication device 50 via the communication unit 19 . In addition, the acquisition unit 12 acquires defect information regarding a defect in the optical fiber communication path F from the input/output device 60 via the communication unit 19 . Further, the acquisition unit 12 associates the defect information EI with the monitor information MI2 and stores them in the storage unit 18B.
 取得部12がモニタ情報MI2と不具合情報EIとを関連付ける処理について、説明する。 A process of associating the monitor information MI2 and the defect information EI by the acquisition unit 12 will be described.
 取得部12は、不具合情報を取得すると、当該不具合情報に含まれる端末識別子と同じ端末識別子を有するモニタ情報を抽出する。更に、取得部12は、当該不具合情報が示す不具合発生の時刻から所定の時間前までの期間(例えば、不具合発生の時刻24時間前から不具合発生時刻まで)を設定する。取得部12は、抽出したモニタ情報の中から、抽出したモニタ情報に含まれる送信パワー及び受信パワー及びパケットエラーの回数の情報を取得した時刻が、設定した期間に含まれるモニタ情報を抽出する。取得部12は、当該不具合情報EIと抽出したモニタ情報MI2とを関連付けて記憶部18Bに格納する。換言すると、取得部12は、光ファイバ通信路Fに不具合が発生した場合、不具合が発生した時刻から所定の時間前までの期間における送信パワー及び受信パワー及びパケットエラーの回数の情報と、当該不具合とを関連付ける。関連付けられたモニタ情報MI2と不具合情報EIとの組を、教師データと呼称する。 When the trouble information is acquired, the acquisition unit 12 extracts monitor information having the same terminal identifier as the terminal identifier included in the trouble information. Further, the acquisition unit 12 sets a period from the time of occurrence of the problem indicated by the problem information to a predetermined time (for example, from 24 hours before the time of occurrence of the problem to the time of occurrence of the problem). The acquisition unit 12 extracts, from the extracted monitor information, monitor information in which the time at which the information on the transmission power, the reception power, and the number of packet errors included in the extracted monitor information is acquired is included in a set period. The acquisition unit 12 associates the defect information EI with the extracted monitor information MI2 and stores them in the storage unit 18B. In other words, when a problem occurs in the optical fiber communication path F, the acquisition unit 12 acquires information on the transmission power, the reception power, and the number of packet errors during a period from the time when the problem occurred to a predetermined time before, and the information on the number of packet errors. Associate with. A set of associated monitor information MI2 and defect information EI is referred to as teacher data.
 学習部16は、教師データを参照して推定モデルを学習する。一例として、学習部16は、前記教師データを用いた学習ステップを繰り返し実行することによって、推定モデルのモデルパラメータを繰り返し更新する。そして、学習部16は、学習後の推定モデルを規定するモデルパラメータMPを、記憶部18Bに格納する。 The learning unit 16 learns the estimation model by referring to the teacher data. As an example, the learning unit 16 repeatedly updates the model parameters of the estimation model by repeatedly executing the learning step using the teacher data. Then, the learning unit 16 stores the model parameters MP defining the estimated model after learning in the storage unit 18B.
 なお、上記推定モデルの具体的構成は本例示的実施形態を限定するものではないが、一例として、CNN、RNN、又はそれらの組み合わせを用いることができる。また、ランダムフォレストやサポートベクターマシンのような非ニューラルネットワーク型のモデルを用いてもよい。 Although the specific configuration of the estimation model does not limit this exemplary embodiment, as an example, CNN, RNN, or a combination thereof can be used. Non-neural network models such as random forests and support vector machines may also be used.
 (情報処理方法S100Bの流れ)
 本例示的実施形態に係る情報処理方法S100Bについて、図10を参照して説明する。図10は、情報処理システム100Bによる情報処理方法S100Bの流れを示すシーケンス図である。
(Flow of information processing method S100B)
An information processing method S100B according to this exemplary embodiment will be described with reference to FIG. FIG. 10 is a sequence diagram showing the flow of the information processing method S100B by the information processing system 100B.
 (ステップS102)
 ステップS102において、通信装置50のモニタ情報取得部511は、モニタ情報を取得する。
(Step S102)
In step S102, the monitor information acquisition unit 511 of the communication device 50 acquires monitor information.
 (ステップS103)
 ステップS103において、提供部21は、モニタ情報取得部511が取得したモニタ情報を、第1の通信部52を介して情報処理装置1Bに提供する。
(Step S103)
In step S<b>103 , the provision unit 21 provides the monitor information acquired by the monitor information acquisition unit 511 to the information processing apparatus 1</b>B via the first communication unit 52 .
 (ステップS104)
 ステップS104において、情報処理装置1Bの取得部12は、通信部19を介して、通信装置50から提供されたモニタ情報を取得する。
(Step S104)
In step S<b>104 , the acquisition unit 12 of the information processing device 1</b>B acquires monitor information provided from the communication device 50 via the communication unit 19 .
 (ステップS122)
 ステップS122において、入出力装置60の操作受付部62は、不具合情報に含まれる情報を入力する操作を受け付けると、入力された情報を含む不具合情報を、ネットワークNを介して情報処理装置1Bに提供する。
(Step S122)
In step S122, upon receiving an operation to input information included in the defect information, the operation receiving unit 62 of the input/output device 60 provides the defect information including the input information to the information processing apparatus 1B via the network N. do.
 (ステップS123)
 ステップS123において、情報処理装置1Bの取得部12は、通信部19を介して、入出力装置60から提供された不具合情報を取得する。
(Step S123)
In step S<b>123 , the acquisition unit 12 of the information processing device 1</b>B acquires the defect information provided from the input/output device 60 via the communication unit 19 .
 (ステップS124)
 ステップS124において、取得部12は、取得した不具合情報を参照し、モニタ情報を抽出する。モニタ情報の抽出の仕方については上述したためここでは説明を省略する。
(Step S124)
In step S124, the acquisition unit 12 refers to the acquired defect information and extracts monitor information. Since the method of extracting the monitor information has been described above, the explanation is omitted here.
 (ステップS125)
 取得部12は、ステップS123において取得した不具合情報EIと、ステップS123において抽出したモニタ情報MI2とを関連付け、教師データを生成する。学習部16は、生成された教師データを取得する。
(Step S125)
The acquisition unit 12 associates the defect information EI acquired in step S123 with the monitor information MI2 extracted in step S123 to generate teacher data. The learning unit 16 acquires the generated teacher data.
 (ステップS126)
 学習部16は、取得した教師データを参照して推定モデルを学習する。
(Step S126)
The learning unit 16 learns the estimation model by referring to the acquired teacher data.
 (ステップS127)
 学習部16は、学習後の推定モデルを規定するモデルパラメータMPを、記憶部18Bに格納する。
(Step S127)
The learning unit 16 stores the model parameters MP that define the estimated model after learning in the storage unit 18B.
 このように、情報処理システム100Bでは、関連付けられた不具合情報EIとモニタ情報MI2とを教師データとして、推定モデルが学習される。したがって、情報処理システム100Bでは、不具合と当該不具合が発生する前の光ファイバ通信路Fの状態とが関連付けられて推定モデルが学習されるので、光ファイバ通信路Fにおける不具合の要因を好適に推定することができる。 Thus, in the information processing system 100B, an estimation model is learned using the associated defect information EI and monitor information MI2 as training data. Therefore, in the information processing system 100B, since the estimation model is learned by associating the failure with the state of the optical fiber communication path F before the failure occurs, the cause of the failure in the optical fiber communication path F can be estimated appropriately. can do.
 〔例示的実施形態4〕
 本発明の第4の例示的実施形態について、図面を参照して詳細に説明する。なお、例示的実施形態1~例示的実施形態3にて説明した構成要素と同じ機能を有する構成要素については、同じ符号を付し、その説明を適宜省略する。
[Exemplary embodiment 4]
A fourth exemplary embodiment of the invention will now be described in detail with reference to the drawings. Components having the same functions as those described in Embodiments 1 to 3 are denoted by the same reference numerals, and description thereof will be omitted as appropriate.
 (情報処理システム100Cの構成)
 図11は、本発明の例示的実施形態4に係る情報処理システム100Cの構成を示すブロック図である。図11に示すように、情報処理システム100Cは、上述した情報処理システム100Aにおける情報処理装置1Aに替えて、情報処理装置1Cを備える構成である。
(Configuration of information processing system 100C)
FIG. 11 is a block diagram showing the configuration of an information processing system 100C according to Exemplary Embodiment 4 of the present invention. As shown in FIG. 11, an information processing system 100C is configured to include an information processing device 1C instead of the information processing device 1A in the information processing system 100A described above.
 情報処理システム100Cは、上述した例示的実施形態2における情報処理システム100A及び例示的実施形態3における情報処理システム100Bの両方の機能を有するシステムである。 The information processing system 100C is a system having the functions of both the information processing system 100A in the second exemplary embodiment and the information processing system 100B in the third exemplary embodiment.
 (情報処理装置1C)
 情報処理装置1Cは、図11に示すように、制御部10C、記憶部18C、及び通信部19を備えている。通信部19は、上述した通りである。
(Information processing device 1C)
The information processing apparatus 1C includes a control section 10C, a storage section 18C, and a communication section 19, as shown in FIG. The communication unit 19 is as described above.
 記憶部18Cは、上述した、モニタ情報MI1と、モデルパラメータMPと、関連付けられたモニタ情報MI2及び不具合情報EIとが格納されている。 The storage unit 18C stores the above-described monitor information MI1, model parameters MP, and associated monitor information MI2 and defect information EI.
 (制御部10C)
 制御部10Cは、例えば1つ以上のプロセッサ(例えばCPUなど)が、メモリ(例えばRAMやROMなど)に記憶されているプログラムを実行することによって、情報処理装置1Cの各構成要素を制御する。
(control unit 10C)
The control unit 10C controls each component of the information processing apparatus 1C by executing a program stored in a memory (eg, RAM, ROM, etc.) by one or more processors (eg, CPU, etc.), for example.
 制御部10Cは、図11に示すように、取得部12、推定部13、蓄積部14、抽出部15、学習部16、及び出力部17を備えている。 The control unit 10C includes an acquisition unit 12, an estimation unit 13, an accumulation unit 14, an extraction unit 15, a learning unit 16, and an output unit 17, as shown in FIG.
 取得部12は、情報処理装置1Aにおける取得部12及び情報処理装置1Bにおける取得部12の両方の機能を有している。 The acquisition unit 12 has the functions of both the acquisition unit 12 in the information processing device 1A and the acquisition unit 12 in the information processing device 1B.
 推定部13、蓄積部14、抽出部15、及び出力部17は、情報処理装置1Aにおける推定部13、蓄積部14、抽出部15、及び出力部17と同じ機能を有している。 The estimation unit 13, storage unit 14, extraction unit 15, and output unit 17 have the same functions as the estimation unit 13, storage unit 14, extraction unit 15, and output unit 17 in the information processing device 1A.
 学習部16は、情報処理装置1Bにおける学習部16と同じ機能を有している。 The learning unit 16 has the same function as the learning unit 16 in the information processing device 1B.
 (情報処理方法の流れ)
 本例示的実施形態に係る情報処理方法について説明する。
(Flow of information processing method)
An information processing method according to this exemplary embodiment will be described.
 上述したように、情報処理システム100Cは、上述した例示的実施形態2における情報処理システム100A及び例示的実施形態3における情報処理システム100Bの両方の機能を有するシステムである。換言すると、情報処理システム100Cは、情報処理システム100Aの処理及び情報処理システム100Bの処理を実行する。 As described above, the information processing system 100C is a system having the functions of both the information processing system 100A in the second exemplary embodiment and the information processing system 100B in the third exemplary embodiment. In other words, the information processing system 100C executes the processing of the information processing system 100A and the processing of the information processing system 100B.
 具体的には、情報処理システム100Cは、図8に示す情報処理方法S100AにおけるステップS102からステップS113までの処理を実行する。 Specifically, the information processing system 100C executes the processing from step S102 to step S113 in the information processing method S100A shown in FIG.
 次に、情報処理システム100Cは、図10に示す情報処理方法S100BにおけるステップS122からステップS127までの処理を実行する。 Next, the information processing system 100C executes the processing from step S122 to step S127 in the information processing method S100B shown in FIG.
 すなわち、情報処理システム100Cにおいて、通信装置50が取得し、提供したモニタ情報を情報処理装置1Cが取得し、当該モニタ情報を記憶部18Cが記憶する。そして、通信装置50がイベント情報を提供すると、情報処理装置1Cは、光ファイバ通信路Fの通信断の不具合の要因を推定し、入出力装置60は推定結果を表示する。 That is, in the information processing system 100C, the information processing device 1C acquires the monitor information acquired and provided by the communication device 50, and the storage unit 18C stores the monitor information. Then, when the communication device 50 provides the event information, the information processing device 1C estimates the cause of the communication disconnection failure of the optical fiber communication path F, and the input/output device 60 displays the estimation result.
 次に、入出力装置60が不具合情報を提供すると、情報処理装置1Cの学習部16は、モニタ情報と当該不具合情報とに基づいて、推定モデルを学習し、モデルパラメータMPを記憶部18Cに格納する。 Next, when the input/output device 60 provides the defect information, the learning unit 16 of the information processing device 1C learns the estimation model based on the monitor information and the defect information, and stores the model parameters MP in the storage unit 18C. do.
 このように、情報処理システム100Cでは、推定モデルのモデルパラメータMPを逐次更新し、光ファイバ通信路Fの通信断の不具合の要因を推定するので、光ファイバ通信路における不具合の要因を好適に推定することができる。 In this way, in the information processing system 100C, the model parameter MP of the estimation model is sequentially updated, and the cause of the communication interruption of the optical fiber communication channel F is estimated. can do.
 〔ソフトウェアによる実現例〕
 情報処理装置1、1A、1B、1C、2、及び通信装置50の一部又は全部の機能は、集積回路(ICチップ)等のハードウェアによって実現してもよいし、ソフトウェアによって実現してもよい。
[Example of realization by software]
Some or all of the functions of the information processing devices 1, 1A, 1B, 1C, and 2 and the communication device 50 may be realized by hardware such as integrated circuits (IC chips) or by software. good.
 後者の場合、情報処理装置1、1A、1B、1C、2、及び通信装置50は、例えば、各機能を実現するソフトウェアであるプログラムの命令を実行するコンピュータによって実現される。このようなコンピュータの一例(以下、コンピュータCと記載する)を図12に示す。コンピュータCは、少なくとも1つのプロセッサC1と、少なくとも1つのメモリC2と、を備えている。メモリC2には、コンピュータCを情報処理装置1、1A、1B、1C、2、及び通信装置50として動作させるためのプログラムPが記録されている。コンピュータCにおいて、プロセッサC1は、プログラムPをメモリC2から読み取って実行することにより、情報処理装置1、1A、1B、1C、2、及び通信装置50の各機能が実現される。 In the latter case, the information processing devices 1, 1A, 1B, 1C, and 2 and the communication device 50 are implemented, for example, by a computer that executes program instructions, which are software that implements each function. An example of such a computer (hereinafter referred to as computer C) is shown in FIG. Computer C comprises at least one processor C1 and at least one memory C2. A program P for operating the computer C as the information processing devices 1, 1A, 1B, 1C, 2 and the communication device 50 is recorded in the memory C2. In the computer C, the processor C1 reads the program P from the memory C2 and executes it, thereby implementing the functions of the information processing devices 1, 1A, 1B, 1C, 2 and the communication device 50. FIG.
 プロセッサC1としては、例えば、CPU(Central Processing Unit)、GPU(Graphic Processing Unit)、DSP(Digital Signal Processor)、MPU(Micro Processing Unit)、FPU(Floating point number Processing Unit)、PPU(Physics Processing Unit)、マイクロコントローラ、又は、これらの組み合わせなどを用いることができる。メモリC2としては、例えば、フラッシュメモリ、HDD(Hard Disk Drive)、SSD(Solid State Drive)、又は、これらの組み合わせなどを用いることができる。 As the processor C1, for example, CPU (Central Processing Unit), GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating point number Processing Unit), PPU (Physics Processing Unit) , a microcontroller, or a combination thereof. As the memory C2, for example, a flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), or a combination thereof can be used.
 なお、コンピュータCは、プログラムPを実行時に展開したり、各種データを一時的に記憶したりするためのRAM(Random Access Memory)を更に備えていてもよい。また、コンピュータCは、他の装置との間でデータを送受信するための通信インタフェースを更に備えていてもよい。また、コンピュータCは、キーボードやマウス、ディスプレイやプリンタなどの入出力機器を接続するための入出力インタフェースを更に備えていてもよい。 Note that the computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and temporarily storing various data. Computer C may further include a communication interface for sending and receiving data to and from other devices. Computer C may further include an input/output interface for connecting input/output devices such as a keyboard, mouse, display, and printer.
 また、プログラムPは、コンピュータCが読み取り可能な、一時的でない有形の記録媒体Mに記録することができる。このような記録媒体Mとしては、例えば、テープ、ディスク、カード、半導体メモリ、又はプログラマブルな論理回路などを用いることができる。コンピュータCは、このような記録媒体Mを介してプログラムPを取得することができる。また、プログラムPは、伝送媒体を介して伝送することができる。このような伝送媒体としては、例えば、通信ネットワーク、又は放送波などを用いることができる。コンピュータCは、このような伝送媒体を介してプログラムPを取得することもできる。 In addition, the program P can be recorded on a non-temporary tangible recording medium M that is readable by the computer C. As such a recording medium M, for example, a tape, disk, card, semiconductor memory, programmable logic circuit, or the like can be used. The computer C can acquire the program P via such a recording medium M. Also, the program P can be transmitted via a transmission medium. As such a transmission medium, for example, a communication network or broadcast waves can be used. Computer C can also acquire program P via such a transmission medium.
 〔付記事項1〕
 本発明は、上述した実施形態に限定されるものでなく、請求項に示した範囲で種々の変更が可能である。例えば、上述した実施形態に開示された技術的手段を適宜組み合わせて得られる実施形態についても、本発明の技術的範囲に含まれる。
[Appendix 1]
The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technical means disclosed in the embodiments described above are also included in the technical scope of the present invention.
 〔付記事項2〕
 上述した実施形態の一部又は全部は、以下のようにも記載され得る。ただし、本発明は、以下の記載する態様に限定されるものではない。
[Appendix 2]
Some or all of the above-described embodiments may also be described as follows. However, the present invention is not limited to the embodiments described below.
 (付記1)
 端末装置と通信装置との間の光ファイバ通信路に関する第1のモニタ情報を取得する取得手段と、前記第1のモニタ情報を入力とし、前記光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、前記光ファイバ通信路における不具合の要因を推定する推定手段と、を備えている情報処理システム。
(Appendix 1)
Acquisition means for acquiring first monitor information relating to an optical fiber communication path between a terminal device and a communication device, and receiving the first monitor information as an input, and outputting information relating to a cause of failure in the optical fiber communication channel. and an estimating means for estimating factors of failure in the optical fiber communication path based on the estimating model.
 上記の構成によれば、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, it is possible to suitably estimate the cause of the problem in the optical fiber communication path.
 (付記2)
 前記推定手段は、前記端末装置と前記通信装置との間の光ファイバ通信路の通信断の発生に応じて、前記光ファイバ通信路における不具合の要因を推定する付記1に記載の情報処理システム。
(Appendix 2)
1. The information processing system according to appendix 1, wherein the estimating means estimates the cause of the failure in the optical fiber communication path in accordance with occurrence of a communication disconnection in the optical fiber communication path between the terminal device and the communication device.
 上記の構成によれば、光ファイバ通信路の通信断が発生した場合、当該通信断における不具合の要因を好適に推定することができる。 According to the above configuration, when communication interruption occurs in the optical fiber communication path, it is possible to suitably estimate the cause of the problem caused by the communication interruption.
 (付記3)
 前記取得手段が取得した第1のモニタ情報を記憶する記憶手段と、前記記憶手段が記憶した第1のモニタ情報から、前記通信断の発生に応じて、前記通信断に関する第1のモニタ情報を抽出する抽出手段と、を更に備え、前記推定手段は、抽出した前記第1のモニタ情報に応じて、前記光ファイバ通信路における不具合の要因を推定する付記2に記載の情報処理システム。
(Appendix 3)
storage means for storing the first monitor information acquired by the acquisition means; and first monitor information relating to the communication disconnection is acquired from the first monitor information stored by the storage means in accordance with the occurrence of the communication disconnection. The information processing system according to Supplementary Note 2, further comprising extracting means for extracting, wherein the estimating means estimates the cause of the failure in the optical fiber communication path according to the extracted first monitor information.
 上記の構成によれば、光ファイバ通信路の通信断が発生した場合、当該通信断における不具合の要因を好適に推定することができる。 According to the above configuration, when communication interruption occurs in the optical fiber communication path, it is possible to suitably estimate the cause of the problem caused by the communication interruption.
 (付記4)
 前記第1のモニタ情報には、前記光ファイバ通信路における送信パワー及び受信パワーの少なくとも何れか、並びに前記光ファイバ通信路におけるパケットエラーの回数の少なくとも何れかが含まれる付記1から3の何れかに記載の情報処理システム。
(Appendix 4)
4. Any one of appendices 1 to 3, wherein the first monitor information includes at least one of transmission power and reception power in the optical fiber communication path and at least one of the number of packet errors in the optical fiber communication path. The information processing system according to .
 上記の構成によれば、光ファイバ通信路の状態を考慮するので、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, since the state of the optical fiber communication path is taken into consideration, it is possible to suitably estimate the cause of the malfunction in the optical fiber communication path.
 (付記5)
 推定した前記不具合の要因に応じた保守作業を示す情報を出力する出力部を更に備えている付記1から4の何れかに記載の情報処理システム。
(Appendix 5)
5. The information processing system according to any one of Appendices 1 to 4, further comprising an output unit that outputs information indicating maintenance work corresponding to the estimated cause of the malfunction.
 上記の構成によれば、推定した光ファイバ通信路における不具合の要因に応じた保守作業を推奨することができる。 According to the above configuration, it is possible to recommend maintenance work according to the estimated cause of the problem in the optical fiber communication path.
 (付記6)
 光ファイバ通信路に関する第2のモニタ情報と、光ファイバ通信路における不具合に関する情報とに基づいて、前記推定モデルを学習する学習手段を更に備えている付記1から5の何れかに記載の情報処理システム。
(Appendix 6)
6. The information processing according to any one of Appendices 1 to 5, further comprising learning means for learning the estimation model based on second monitor information regarding the optical fiber communication channel and information regarding defects in the optical fiber communication channel. system.
 上記の構成によれば、モニタ情報と光ファイバ通信路における不具合に関する情報との組を含む教師データとして推定モデルが学習されるので、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably. .
 (付記7)
 光ファイバ通信路に関するモニタ情報を提供する提供手段と、光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを取得する取得手段と、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを、前記取得手段が取得した教師データを参照して学習する学習手段とを備えている情報処理システム。
(Appendix 7)
providing means for providing monitor information on the optical fiber communication path; acquisition means for acquiring teacher data including a set of monitor information on the optical fiber communication path and information on failures in the optical fiber communication path; An information processing system comprising learning means for learning an estimation model that receives monitor information as input and outputs information about the cause of failure in an optical fiber communication path, with reference to teacher data acquired by the acquisition means.
 上記の構成によれば、モニタ情報と光ファイバ通信路における不具合に関する情報との組を含む教師データとして推定モデルが学習されるので、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably. .
 (付記8)
 端末装置と通信装置との間の光ファイバ通信路に関する第1のモニタ情報を取得する取得手段と、前記第1のモニタ情報を入力とし、前記光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、前記光ファイバ通信路における不具合の要因を推定する推定手段と、を備えている情報処理装置。
(Appendix 8)
Acquisition means for acquiring first monitor information relating to an optical fiber communication path between a terminal device and a communication device, and receiving the first monitor information as an input, and outputting information relating to a cause of failure in the optical fiber communication channel. and an estimating means for estimating factors of failure in the optical fiber communication path based on an estimating model.
 上記の構成によれば、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, it is possible to suitably estimate the cause of the problem in the optical fiber communication path.
 (付記9)
 前記推定手段は、前記端末装置と前記通信装置との間の光ファイバ通信路の通信断の発生に応じて、前記光ファイバ通信路における不具合の要因を推定する付記8に記載の情報処理装置。
(Appendix 9)
9. The information processing apparatus according to appendix 8, wherein the estimating means estimates a cause of failure in the optical fiber communication path in response to occurrence of a communication disconnection in the optical fiber communication path between the terminal device and the communication device.
 上記の構成によれば、光ファイバ通信路の通信断が発生した場合、当該通信断における不具合の要因を好適に推定することができる。 According to the above configuration, when communication interruption occurs in the optical fiber communication path, it is possible to suitably estimate the cause of the problem caused by the communication interruption.
 (付記10)
 前記取得手段が取得した第1のモニタ情報を記憶する記憶手段と、前記記憶手段が記憶した第1のモニタ情報から、前記通信断の発生に応じて、前記通信断に関する第1のモニタ情報を抽出する抽出手段と、を更に備え、前記推定手段は、抽出した前記第1のモニタ情報に応じて、前記光ファイバ通信路における不具合の要因を推定する付記9に記載の情報処理装置。
(Appendix 10)
storage means for storing the first monitor information acquired by the acquisition means; and first monitor information relating to the communication disconnection is acquired from the first monitor information stored by the storage means in accordance with the occurrence of the communication disconnection. The information processing apparatus according to Supplementary Note 9, further comprising extracting means for extracting, wherein the estimating means estimates the cause of the failure in the optical fiber communication path according to the extracted first monitor information.
 上記の構成によれば、光ファイバ通信路の通信断が発生した場合、当該通信断における不具合の要因を好適に推定することができる。 According to the above configuration, when communication interruption occurs in the optical fiber communication path, it is possible to suitably estimate the cause of the problem caused by the communication interruption.
 (付記11)
 前記第1のモニタ情報には、前記光ファイバ通信路における送信パワー及び受信パワーの少なくとも何れか、並びに前記光ファイバ通信路におけるパケットエラーの回数の少なくとも何れかが含まれる付記8から10の何れかに記載の情報処理装置。
(Appendix 11)
11. Any one of appendices 8 to 10, wherein the first monitor information includes at least one of transmission power and reception power in the optical fiber communication path and at least one of the number of packet errors in the optical fiber communication path. The information processing device according to .
 上記の構成によれば、光ファイバ通信路の状態を考慮するので、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, since the state of the optical fiber communication path is taken into consideration, it is possible to suitably estimate the cause of the malfunction in the optical fiber communication path.
 (付記12)
 推定した前記不具合の要因に応じた保守作業を示す情報を出力する出力部を更に備えている付記8から11の何れかに記載の情報処理装置。
(Appendix 12)
12. The information processing apparatus according to any one of appendices 8 to 11, further comprising an output unit that outputs information indicating maintenance work corresponding to the estimated cause of the malfunction.
 上記の構成によれば、推定した光ファイバ通信路における不具合の要因に応じた保守作業を推奨することができる。 According to the above configuration, it is possible to recommend maintenance work according to the estimated cause of the problem in the optical fiber communication path.
 (付記13)
 光ファイバ通信路に関する第2のモニタ情報と、光ファイバ通信路における不具合に関する情報とに基づいて、前記推定モデルを学習する学習手段を更に備えている付記8から12の何れかに記載の情報処理装置。
(Appendix 13)
13. The information processing according to any one of appendices 8 to 12, further comprising learning means for learning the estimation model based on second monitor information regarding the optical fiber communication channel and information regarding defects in the optical fiber communication channel. Device.
 上記の構成によれば、モニタ情報と光ファイバ通信路における不具合に関する情報との組を含む教師データとして推定モデルが学習されるので、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably. .
 (付記14)
 光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを取得する取得手段と、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを、前記取得手段が取得した教師データを参照して学習する学習手段とを備えている情報処理装置。
(Appendix 14)
Acquisition means for acquiring teacher data including a set of monitor information relating to an optical fiber communication channel and information relating to a defect in the optical fiber communication channel; and a learning means for learning an estimation model outputting information about the above with reference to the teacher data acquired by the acquisition means.
 上記の構成によれば、モニタ情報と光ファイバ通信路における不具合に関する情報との組を含む教師データとして推定モデルが学習されるので、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably. .
 (付記15)
 端末装置と通信装置との間の光ファイバ通信路に関する第1のモニタ情報を取得することと、前記第1のモニタ情報を入力とし、前記光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、前記光ファイバ通信路における不具合の要因を推定することと、を含んでいる情報処理方法。
(Appendix 15)
Acquisition of first monitor information regarding an optical fiber communication path between a terminal device and a communication device, and estimation of outputting information regarding a cause of failure in the optical fiber communication path using the first monitor information as an input. and estimating factors of failure in the optical fiber communication path based on a model.
 上記の構成によれば、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, it is possible to suitably estimate the cause of the problem in the optical fiber communication path.
 (付記16)
 前記推定する工程では、前記端末装置と前記通信装置との間の光ファイバ通信路の通信断の発生に応じて、前記光ファイバ通信路における不具合の要因を推定する付記15に記載の情報処理方法。
(Appendix 16)
16. The information processing method according to Supplementary Note 15, wherein in the estimating step, a cause of a problem in the optical fiber communication path is estimated in accordance with occurrence of communication interruption in the optical fiber communication path between the terminal device and the communication device. .
 上記の構成によれば、光ファイバ通信路の通信断が発生した場合、当該通信断における不具合の要因を好適に推定することができる。 According to the above configuration, when communication interruption occurs in the optical fiber communication path, it is possible to suitably estimate the cause of the problem caused by the communication interruption.
 (付記17)
 前記取得する工程にて取得した第1のモニタ情報を記憶することと、前記記憶する工程にて記憶した第1のモニタ情報から、前記通信断の発生に応じて、前記通信断に関する第1のモニタ情報を抽出することと、を更に含み、前記推定する工程では、抽出した前記第1のモニタ情報に応じて、前記光ファイバ通信路における不具合の要因を推定する付記16に記載の情報処理方法。
(Appendix 17)
Storing the first monitor information acquired in the acquiring step; and Based on the first monitor information stored in the storing step, in accordance with the occurrence of the communication disruption, a first information related to the communication disruption. 17. The information processing method according to appendix 16, further comprising: extracting monitor information, wherein, in the estimating step, a factor of failure in the optical fiber communication path is estimated according to the extracted first monitor information. .
 上記の構成によれば、光ファイバ通信路の通信断が発生した場合、当該通信断における不具合の要因を好適に推定することができる。 According to the above configuration, when communication interruption occurs in the optical fiber communication path, it is possible to suitably estimate the cause of the problem caused by the communication interruption.
 (付記18)
 前記第1のモニタ情報には、前記光ファイバ通信路における送信パワー及び受信パワーの少なくとも何れか、並びに及び前記光ファイバ通信路におけるパケットエラーの回数の少なくとも何れかが含まれる付記15から17の何れかに記載の情報処理方法。
(Appendix 18)
17. Any one of Appendices 15 to 17, wherein the first monitor information includes at least one of transmission power and reception power in the optical fiber communication path, and at least one of the number of packet errors in the optical fiber communication path. The information processing method according to claim 1.
 上記の構成によれば、光ファイバ通信路の状態を考慮するので、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, since the state of the optical fiber communication path is taken into consideration, it is possible to suitably estimate the cause of the malfunction in the optical fiber communication path.
 (付記19)
 推定した前記不具合の要因に応じた保守作業を示す情報を出力することを更に含んでいる付記15から18の何れかに記載の情報処理方法。
(Appendix 19)
19. The information processing method according to any one of Appendices 15 to 18, further comprising outputting information indicating maintenance work according to the presumed cause of the malfunction.
 上記の構成によれば、推定した光ファイバ通信路における不具合の要因に応じた保守作業を推奨することができる。 According to the above configuration, it is possible to recommend maintenance work according to the estimated cause of the problem in the optical fiber communication path.
 (付記20)
 光ファイバ通信路に関する第2のモニタ情報と、光ファイバ通信路における不具合に関する情報とに基づいて、前記推定モデルを学習することを更に含んでいる付記15から19の何れかに記載の情報処理方法。
(Appendix 20)
20. The information processing method according to any one of appendices 15 to 19, further comprising learning the estimation model based on second monitor information on the optical fiber communication channel and information on defects in the optical fiber communication channel. .
 上記の構成によれば、モニタ情報と光ファイバ通信路における不具合に関する情報との組を含む教師データとして推定モデルが学習されるので、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably. .
 (付記21)
 光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを取得することと、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを、前記取得する工程にて取得した教師データを参照して学習することとを含んでいる情報処理方法。
(Appendix 21)
Acquisition of teacher data including a set of monitor information about an optical fiber communication path and information about a problem in an optical fiber communication path An information processing method, comprising learning an estimation model for outputting information with reference to the teacher data acquired in the acquiring step.
 上記の構成によれば、モニタ情報と光ファイバ通信路における不具合に関する情報との組を含む教師データとして推定モデルが学習されるので、光ファイバ通信路における不具合の要因を好適に推定することができる。 According to the above configuration, the estimation model is learned as the teacher data including the set of the monitor information and the information about the failure in the optical fiber communication channel, so the cause of the failure in the optical fiber communication channel can be estimated favorably. .
 (付記22)
 コンピュータを付記1~7の何れか一に記載の情報処理システムとして動作させるためのプログラムであって、前記コンピュータを前記各手段として機能させる、ことを特徴とするプログラム。
(Appendix 22)
A program for operating a computer as the information processing system according to any one of Appendices 1 to 7, wherein the program causes the computer to function as each of the means.
 (付記23)
 コンピュータを付記8~14の何れか一に記載の情報処理装置として動作させるためのプログラムであって、前記コンピュータを前記各手段として機能させる、ことを特徴とするプログラム。
(Appendix 23)
15. A program for causing a computer to operate as the information processing apparatus according to any one of Appendices 8 to 14, the program causing the computer to function as each of the means.
 (付記24)
 上述した実施形態の一部又は全部は、更に、以下のように表現することもできる。
(Appendix 24)
Some or all of the embodiments described above can also be expressed as follows.
 少なくとも1つのプロセッサを備え、前記プロセッサは、端末装置と通信装置との間の光ファイバ通信路に関するモニタ情報を提供する提供処理と、前記光ファイバ通信路に関するモニタ情報を取得する取得処理と、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに対して、前記取得処理にて取得したモニタ情報を入力することによって、前記光ファイバ通信路における不具合の要因を推定する推定処理とを実行する情報処理システム。 at least one processor, the processor includes: a providing process for providing monitor information on an optical fiber communication path between a terminal device and a communication device; an acquisition process for obtaining monitor information on the optical fiber communication channel; By inputting the monitor information acquired in the acquisition process to an estimation model that receives monitor information related to the fiber communication channel and outputs information related to the cause of failure in the optical fiber communication channel, An information processing system that executes an estimation process for estimating the cause of a defect.
 なお、この情報処理システムは、更にメモリを備えていてもよく、このメモリには、前記提供処理と、前記取得処理と、前記推定処理とを前記プロセッサに実行させるためのプログラムが記憶されていてもよい。また、このプログラムは、コンピュータ読み取り可能な一時的でない有形の記録媒体に記録されていてもよい。 The information processing system may further include a memory, and the memory stores a program for causing the processor to execute the providing process, the obtaining process, and the estimating process. good too. Also, this program may be recorded in a computer-readable non-temporary tangible recording medium.
 少なくとも1つのプロセッサを備え、前記プロセッサは、光ファイバ通信路に関するモニタ情報を提供する提供処理と、光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを取得する取得処理と、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを、前記取得処理にて取得した教師データを参照して学習する学習処理とを実行する情報処理システム。 At least one processor is provided, and the processor stores training data including a set of a providing process for providing monitor information on the optical fiber communication channel, monitor information on the optical fiber communication channel, and information on failures in the optical fiber communication channel. Acquisition processing and learning in which an estimation model that receives as input monitor information on an optical fiber communication channel and outputs information on the cause of failure in the optical fiber communication channel is learned by referring to the teacher data acquired in the acquisition processing. An information processing system that executes a process.
 なお、この情報処理システムは、更にメモリを備えていてもよく、このメモリには、前記提供処理と、前記取得処理と、前記学習処理とを前記プロセッサに実行させるためのプログラムが記憶されていてもよい。また、このプログラムは、コンピュータ読み取り可能な一時的でない有形の記録媒体に記録されていてもよい。 The information processing system may further include a memory, and the memory stores a program for causing the processor to execute the providing process, the acquiring process, and the learning process. good too. In addition, this program may be recorded in a computer-readable non-temporary tangible recording medium.
 少なくとも1つのプロセッサを備え、前記プロセッサは、端末装置と通信装置との間の光ファイバ通信路に関するモニタ情報を取得する取得処理と、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに対して、前記取得処理にて取得したモニタ情報を入力することによって、前記光ファイバ通信路における不具合の要因を推定する推定処理とを実行する情報処理装置。 At least one processor is provided, and the processor receives as input an acquisition process for acquiring monitor information on the optical fiber communication path between the terminal device and the communication device, and monitor information on the optical fiber communication channel, and the optical fiber communication channel An information processing apparatus that executes an estimation process of estimating the cause of a defect in the optical fiber communication path by inputting the monitor information acquired in the acquisition process to an estimation model that outputs information about the cause of the defect. .
 なお、この情報処理装置は、更にメモリを備えていてもよく、このメモリには、前記取得処理と、前記推定処理とを前記プロセッサに実行させるためのプログラムが記憶されていてもよい。また、このプログラムは、コンピュータ読み取り可能な一時的でない有形の記録媒体に記録されていてもよい。 The information processing apparatus may further include a memory, and the memory may store a program for causing the processor to execute the acquisition process and the estimation process. In addition, this program may be recorded in a computer-readable non-temporary tangible recording medium.
 少なくとも1つのプロセッサを備え、前記プロセッサは、光ファイバ通信路に関するモニタ情報と、光ファイバ通信路における不具合に関する情報との組を含む教師データを取得する取得処理と、光ファイバ通信路に関するモニタ情報を入力とし、光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルを、前記取得手段が取得した教師データを参照して学習する学習処理とを実行する情報処理装置。 At least one processor is provided, and the processor performs an acquisition process for acquiring teacher data including a set of monitor information about an optical fiber communication channel and information about a problem in the optical fiber communication channel, and monitor information about the optical fiber communication channel. An information processing apparatus for executing a learning process of learning an estimation model, which is used as an input and outputs information about a cause of a problem in an optical fiber communication path, with reference to the teacher data acquired by the acquisition means.
 なお、この情報処理装置は、更にメモリを備えていてもよく、このメモリには、前記取得処理と、前記学習処理とを前記プロセッサに実行させるためのプログラムが記憶されていてもよい。また、このプログラムは、コンピュータ読み取り可能な一時的でない有形の記録媒体に記録されていてもよい。 The information processing apparatus may further include a memory, and the memory may store a program for causing the processor to execute the acquisition process and the learning process. Also, this program may be recorded in a computer-readable non-temporary tangible recording medium.
 1、1A、1B、1C、2、2A 情報処理装置
 10A、10B、10C、51 制御部
 12、22 取得部
 13 推定部
 14 蓄積部
 15 抽出部
 16、23 学習部
 17 出力部
 18A、18B、18C、62 記憶部
 19 通信部
 21 提供部
 50 通信装置
 52 第1の通信部
 53 第2の通信部
 511 モニタ情報取得部
 60 入出力装置
 61 提示部
 62 操作受付部
 70 端末装置
 100、100A、100B、100C、200 情報処理システム
1, 1A, 1B, 1C, 2, 2A Information processing device 10A, 10B, 10C, 51 Control unit 12, 22 Acquisition unit 13 Estimation unit 14 Storage unit 15 Extraction unit 16, 23 Learning unit 17 Output unit 18A, 18B, 18C , 62 storage unit 19 communication unit 21 provision unit 50 communication device 52 first communication unit 53 second communication unit 511 monitor information acquisition unit 60 input/output device 61 presentation unit 62 operation reception unit 70 terminal device 100, 100A, 100B, 100C, 200 Information processing system

Claims (18)

  1.  端末装置と通信装置との間の光ファイバ通信路に関する第1のモニタ情報を取得する取得手段と、
     前記第1のモニタ情報を入力とし、前記光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、前記光ファイバ通信路における不具合の要因を推定する推定手段と、
    を備えている情報処理システム。
    Acquisition means for acquiring first monitor information regarding an optical fiber communication path between a terminal device and a communication device;
    estimating means for estimating the cause of the failure in the optical fiber communication path based on an estimation model that inputs the first monitor information and outputs information about the cause of the failure in the optical fiber communication path;
    Information processing system with
  2.  前記推定手段は、前記端末装置と前記通信装置との間の光ファイバ通信路の通信断の発生に応じて、前記光ファイバ通信路における不具合の要因を推定する
    請求項1に記載の情報処理システム。
    2. The information processing system according to claim 1, wherein said estimating means estimates a cause of failure in said optical fiber communication path in accordance with occurrence of a communication disconnection in said optical fiber communication path between said terminal device and said communication device. .
  3.  前記取得手段が取得した第1のモニタ情報を記憶する記憶手段と、
     前記記憶手段が記憶した第1のモニタ情報から、前記通信断の発生に応じて、前記通信断に関する第1のモニタ情報を抽出する抽出手段と、
    を更に備え、
     前記推定手段は、抽出した前記第1のモニタ情報に応じて、前記光ファイバ通信路における不具合の要因を推定する
    請求項2に記載の情報処理システム。
    a storage means for storing the first monitor information acquired by the acquisition means;
    extracting means for extracting first monitor information about the communication interruption from the first monitor information stored in the storage means in accordance with the occurrence of the communication interruption;
    further comprising
    3. The information processing system according to claim 2, wherein said estimating means estimates a cause of failure in said optical fiber communication path according to said extracted first monitor information.
  4.  前記第1のモニタ情報には、
      前記光ファイバ通信路における送信パワー及び受信パワーの少なくとも何れか、並びに
      前記光ファイバ通信路におけるパケットエラーの回数
    の少なくとも何れかが含まれる
    請求項1から3の何れか1項に記載の情報処理システム。
    The first monitor information includes:
    4. The information processing system according to any one of claims 1 to 3, wherein at least one of transmission power and reception power in said optical fiber communication path and at least one of the number of packet errors in said optical fiber communication path is included. .
  5.  推定した前記不具合の要因に応じた保守作業を示す情報を出力する出力手段を更に備えている
    請求項1から4の何れか1項に記載の情報処理システム。
    5. The information processing system according to any one of claims 1 to 4, further comprising output means for outputting information indicating maintenance work corresponding to the presumed cause of the malfunction.
  6.  光ファイバ通信路に関する第2のモニタ情報と、光ファイバ通信路における不具合に関する情報とに基づいて、前記推定モデルを学習する学習手段を更に備えている
    請求項1から5の何れか1項に記載の情報処理システム。
    6. The method according to any one of claims 1 to 5, further comprising learning means for learning the estimation model based on second monitor information on the optical fiber communication channel and information on defects in the optical fiber communication channel. information processing system.
  7.  端末装置と通信装置との間の光ファイバ通信路に関する第1のモニタ情報を取得する取得手段と、
     前記第1のモニタ情報を入力とし、前記光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、前記光ファイバ通信路における不具合の要因を推定する推定手段と、
    を備えている情報処理装置。
    Acquisition means for acquiring first monitor information regarding an optical fiber communication path between a terminal device and a communication device;
    estimating means for estimating the cause of the failure in the optical fiber communication path based on an estimation model that inputs the first monitor information and outputs information about the cause of the failure in the optical fiber communication path;
    Information processing device equipped with.
  8.  前記推定手段は、前記端末装置と前記通信装置との間の光ファイバ通信路の通信断の発生に応じて、前記光ファイバ通信路における不具合の要因を推定する
    請求項7に記載の情報処理装置。
    8. The information processing apparatus according to claim 7, wherein the estimating means estimates the cause of the failure in the optical fiber communication path in accordance with occurrence of a communication disconnection in the optical fiber communication path between the terminal device and the communication device. .
  9.  前記取得手段が取得した第1のモニタ情報を記憶する記憶手段と、
     前記記憶手段が記憶した第1のモニタ情報から、前記通信断の発生に応じて、前記通信断に関する第1のモニタ情報を抽出する抽出手段と、
    を更に備え、
     前記推定手段は、抽出した前記第1のモニタ情報に応じて、前記光ファイバ通信路における不具合の要因を推定する
    請求項8に記載の情報処理装置。
    a storage means for storing the first monitor information acquired by the acquisition means;
    extracting means for extracting first monitor information about the communication interruption from the first monitor information stored in the storage means in accordance with the occurrence of the communication interruption;
    further comprising
    9. The information processing apparatus according to claim 8, wherein said estimating means estimates a cause of failure in said optical fiber communication path according to said extracted first monitor information.
  10.  前記第1のモニタ情報には、
      前記光ファイバ通信路における送信パワー及び受信パワーの少なくとも何れか、並びに
      前記光ファイバ通信路におけるパケットエラーの回数
    の少なくとも何れかが含まれる
    請求項7から9の何れか1項に記載の情報処理装置。
    The first monitor information includes:
    10. The information processing apparatus according to any one of claims 7 to 9, wherein at least one of transmission power and reception power in said optical fiber communication path and at least one of the number of packet errors in said optical fiber communication path is included. .
  11.  推定した前記不具合の要因に応じた保守作業を示す情報を出力する出力手段を更に備えている
    請求項7から10の何れか1項に記載の情報処理装置。
    11. The information processing apparatus according to any one of claims 7 to 10, further comprising output means for outputting information indicating maintenance work corresponding to the estimated cause of the malfunction.
  12.  光ファイバ通信路に関する第2のモニタ情報と、光ファイバ通信路における不具合に関する情報とに基づいて、前記推定モデルを学習する学習手段を更に備えている
    請求項7から11の何れか1項に記載の情報処理装置。
    12. The method according to any one of claims 7 to 11, further comprising learning means for learning the estimation model based on second monitor information on the optical fiber communication channel and information on defects in the optical fiber communication channel. information processing equipment.
  13.  端末装置と通信装置との間の光ファイバ通信路に関する第1のモニタ情報を取得することと、
     前記第1のモニタ情報を入力とし、前記光ファイバ通信路における不具合の要因に関する情報を出力する推定モデルに基づいて、前記光ファイバ通信路における不具合の要因を推定することと、
    を含んでいる情報処理方法。
    obtaining first monitor information about an optical fiber communication path between a terminal device and a communication device;
    estimating the cause of the failure in the optical fiber communication path based on an estimation model that receives the first monitor information and outputs information about the cause of the failure in the optical fiber communication path;
    Information processing methods, including.
  14.  前記推定する工程では、前記端末装置と前記通信装置との間の光ファイバ通信路の通信断の発生に応じて、前記光ファイバ通信路における不具合の要因を推定する
    請求項13に記載の情報処理方法。
    14. The information processing according to claim 13, wherein, in said estimating step, a cause of failure in said optical fiber communication path is estimated according to occurrence of a communication disconnection in said optical fiber communication path between said terminal device and said communication device. Method.
  15.  前記取得する工程にて取得した第1のモニタ情報を記憶することと、
     前記記憶する工程にて記憶した第1のモニタ情報から、前記通信断の発生に応じて、前記通信断に関する第1のモニタ情報を抽出することと、
    を更に含み、
     前記推定する工程では、抽出した前記第1のモニタ情報に応じて、前記光ファイバ通信路における不具合の要因を推定する
    請求項14に記載の情報処理方法。
    storing the first monitor information acquired in the acquiring step;
    Extracting first monitor information related to the communication disconnection from the first monitor information stored in the storing step, according to the occurrence of the communication disconnection;
    further comprising
    15. The information processing method according to claim 14, wherein, in said estimating step, a cause of a problem in said optical fiber communication path is estimated according to said extracted first monitor information.
  16.  前記第1のモニタ情報には、
      前記光ファイバ通信路における送信パワー及び受信パワーの少なくとも何れか、並びに
      前記光ファイバ通信路におけるパケットエラーの回数
    の少なくとも何れかが含まれる
    請求項13から15の何れか1項に記載の情報処理方法。
    The first monitor information includes:
    16. The information processing method according to any one of claims 13 to 15, wherein at least one of transmission power and reception power in said optical fiber communication path and at least one of the number of packet errors in said optical fiber communication path is included. .
  17.  推定した前記不具合の要因に応じた保守作業を示す情報を出力することを更に含んでいる
    請求項13から16の何れか1項に記載の情報処理方法。
    17. The information processing method according to any one of claims 13 to 16, further comprising outputting information indicating maintenance work corresponding to the presumed cause of the malfunction.
  18.  光ファイバ通信路に関する第2のモニタ情報と、光ファイバ通信路における不具合に関する情報とに基づいて、前記推定モデルを学習することを更に含んでいる
    請求項13から17の何れか1項に記載の情報処理方法。

     
    18. The method of any one of claims 13 to 17, further comprising training the estimation model based on second monitor information about the optical fiber communication path and information about failures in the optical fiber communication path. Information processing methods.

PCT/JP2021/028787 2021-08-03 2021-08-03 Information processing system, information processing device and information processing method WO2023012898A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/028787 WO2023012898A1 (en) 2021-08-03 2021-08-03 Information processing system, information processing device and information processing method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/028787 WO2023012898A1 (en) 2021-08-03 2021-08-03 Information processing system, information processing device and information processing method

Publications (1)

Publication Number Publication Date
WO2023012898A1 true WO2023012898A1 (en) 2023-02-09

Family

ID=85154353

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/028787 WO2023012898A1 (en) 2021-08-03 2021-08-03 Information processing system, information processing device and information processing method

Country Status (1)

Country Link
WO (1) WO2023012898A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010171652A (en) * 2009-01-21 2010-08-05 Nippon Telegr & Teleph Corp <Ntt> Optical line fault section estimation system and fault section estimation apparatus
JP2018157330A (en) * 2017-03-16 2018-10-04 Kddi株式会社 Fault discrimination device and control method therefor, program, and optical fiber communication system
WO2019116418A1 (en) * 2017-12-11 2019-06-20 日本電気株式会社 Failure analysis device, failure analysis method, and failure analysis program
JP2021016090A (en) * 2019-07-12 2021-02-12 日本電気株式会社 Communication device, failure notice system, failure notice method, and failure notice program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010171652A (en) * 2009-01-21 2010-08-05 Nippon Telegr & Teleph Corp <Ntt> Optical line fault section estimation system and fault section estimation apparatus
JP2018157330A (en) * 2017-03-16 2018-10-04 Kddi株式会社 Fault discrimination device and control method therefor, program, and optical fiber communication system
WO2019116418A1 (en) * 2017-12-11 2019-06-20 日本電気株式会社 Failure analysis device, failure analysis method, and failure analysis program
JP2021016090A (en) * 2019-07-12 2021-02-12 日本電気株式会社 Communication device, failure notice system, failure notice method, and failure notice program

Similar Documents

Publication Publication Date Title
EP3422639A2 (en) Performance testing method and apparatus for an industrial system deployed on cloud
CN111052087B (en) Control system, information processing apparatus, and recording medium
CN104067599A (en) Network state monitoring system
JP6880560B2 (en) Failure prediction device, failure prediction method and failure prediction program
US20130191064A1 (en) Apparatus and method for controlling water quality sensor faults using sensor data
US8533133B1 (en) Monitoring state of health information for components
JP2009064101A (en) Remote monitoring system and remote monitoring method
CN105933176B (en) A kind of method and device detecting Host Status
KR101469179B1 (en) System for diagnosing communication error of nuclear power plant simmulator
WO2023012898A1 (en) Information processing system, information processing device and information processing method
CN111130917B (en) Line testing method, device and system
US11102103B2 (en) Network stabilizing tool
US11665165B2 (en) Whitelist generator, whitelist evaluator, whitelist generator/evaluator, whitelist generation method, whitelist evaluation method, and whitelist generation/evaluation method
JP2016039610A (en) Data transmitter and remote monitoring system
CN104836679A (en) Communication abnormity processing method and network element equipment
CN110399258B (en) Stability testing method, system and device for server system
JP2012088815A (en) Microprocessor operation monitoring system
CN111127855A (en) Environmental event monitoring method and system of environmental Internet of things
WO2023276350A1 (en) Communication device, communication control method, and communication control program
JP6326383B2 (en) Network evaluation system, network evaluation method, and network evaluation program
EP3461102B1 (en) Notification control device, notification control system, notification control method, and storage medium
US20050172167A1 (en) Communication fault containment via indirect detection
JP2014023050A (en) Method and apparatus for setting monitoring path for defective link identification system
JP2013041367A (en) Operation management device, operation management method, and operation management program
WO2015194651A1 (en) Malfunction notification apparatus, malfunction notification method, and program

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21952727

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE