Information processor, information processing method, and program

Abstract

To provide an information processor that predicts occurrence of a failure that cannot be detected only by information about an apparatus.SOLUTION: An information processor 1 includes; an operation data acquisition unit 131 that acquires operation data indicating an operation state of an apparatus; an extraction data generation unit 132 that extracts extraction data that is information related to a usage state of predetermined application service included in text data; a maintenance data acquisition unit 133 that acquires maintenance data; and an output unit 134 that outputs information indicating whether a failure occurs by inputting the operation data acquired by the operation data acquisition unit 131, the extraction data generated by the extraction data generation unit 132, and the maintenance data acquired by the maintenance data acquisition unit 133 into a trained model.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] 2. Description of the Related Art There is known a device that predicts future failures based on log data of the device (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-20166 A Summary of the Invention [Problem to be solved by the invention]

[0004] As the devices and networks that make up the services become more complex, it has become difficult to pinpoint the location of a failure when an application fails, resulting in problems with failures that cannot be detected based on device logs or alarms.

[0005] The present invention has been made in consideration of these points, and has as its object to make it possible to predict the occurrence of a fault that cannot be detected only from information related to the device. [Means for solving the problem]

[0006] The information processing device of the first aspect of the present invention has an operation data acquisition unit that acquires operation data indicating the operation status of devices constituting a network equipment group for providing a specified application service, an extraction data generation unit that extracts extraction data which is information regarding the usage status of the specified application service included in text data generated outside the network equipment group, a maintenance data acquisition unit that acquires maintenance data which is data input from a system for maintaining the network equipment group, a memory unit that stores a trained model that has been trained to output learning failure prediction information which is failure prediction information for learning, which is failure prediction information indicating the presence or absence of a failure in the specified application service or the network equipment group, using as input learning operation data which is operation data for learning, learning extraction data which is extracted data for learning, and learning maintenance data which is maintenance data for learning, and an output unit that outputs information indicating the presence or absence of a failure by inputting the operation data acquired by the operation data acquisition unit, the extraction data generated by the extraction data generation unit, and the maintenance data acquired by the maintenance data acquisition unit into the trained model.

[0007] The network equipment group may include a first network equipment group from which the operation data can be acquired, and a second network equipment group from which the operation data cannot be acquired, and the operation data acquisition unit may acquire the operation data indicating the operation status of devices constituting the first network equipment group, and the output unit may output information indicating whether or not a fault has occurred in the second network equipment group by inputting the operation data acquired by the operation data acquisition unit and the extracted data generated by the extracted data generation unit into the trained model.

[0008] The learning failure prediction information may further include details of a failure in the specified application service or the group of network equipment, and the output unit may further output procedures for responding to the details of the failure output by the trained model.

[0009] The maintenance data may indicate the contents of a report regarding a malfunction related to the specified application service received from a user of the specified application service, and the output unit may output a message indicating that a malfunction has occurred when the maintenance data obtained is equal to or exceeds a specified threshold value.

[0010] The extracted data may be data extracted from text including words related to the quality of the specified application service, and the output unit may output information indicating that a failure has occurred based on words included in the extracted data indicating that the quality of the specified application service is poor.

[0011] The system may further include a processing status acquisition unit that acquires processing status information that quantitatively indicates the processing status of the specified application service, and the output unit may output a message indicating that a fault has occurred when the processing status indicated by the processing status information deviates from a statistical value of past processing statuses.

[0012] The system may further include a processing status acquisition unit that acquires processing status information in a time series that quantitatively indicates the processing status of the specified application service, and the storage unit stores the processing status information, which is a processing status learning model that is a trained model that has been trained using previously acquired processing status information for learning as teaching data, and that has been trained to use processing status information as input and output a predicted value of the processing status at a future point in time predicted from the past processing status indicated by the input processing status information for learning, and the output unit may output a message that a fault has occurred when there is a discrepancy between the processing status indicated by the processing status information and the predicted value output by the processing status learning model based on the past processing status indicated by the processing status information.

[0013] An information processing method of a second aspect of the present invention includes an operation data acquisition step of acquiring operation data indicating the operation status of devices constituting a network equipment group for providing a specified application service, which is executed by a computer; an extraction step of extracting extracted data which is information regarding the usage status of the specified application service contained in text data generated outside the network equipment group; a maintenance data step of acquiring maintenance data which is data input from a system for maintaining the network equipment group; and an output step of outputting information indicating the presence or absence of a fault by inputting the acquired operation data, the generated extracted data, and the acquired maintenance data into a trained model trained using as teacher data the learning operation data which is operation data for learning, the learning extracted data which is extracted data for learning, the learning maintenance data which is maintenance data for learning, and learning fault prediction information which is fault prediction information for learning, which is fault prediction information for learning.

[0014] In a third aspect of the program of the present invention, a computer is caused to execute an operation data acquisition step of acquiring operation data indicating the operation status of devices constituting a network equipment group for providing a specified application service; an extraction step of extracting extracted data which is information regarding the usage status of the specified application service contained in text data generated outside the network equipment group; a maintenance data step of acquiring maintenance data which is data input from a system for maintaining the network equipment group; and an output step of outputting information indicating the presence or absence of a fault by inputting the acquired operation data, the generated extracted data, and the acquired maintenance data into a trained model trained using as teacher data the learning operation data which is operation data for learning, the learning extracted data which is extracted data for learning, the learning maintenance data which is maintenance data for learning, and learning fault prediction information which is fault prediction information for learning, which is fault prediction information for learning. Effect of the Invention

[0015] The present invention has an effect of making it possible to predict the occurrence of a fault that cannot be detected only by information related to the device. [Brief description of the drawings]

[0016] [Figure 1] 1 is a diagram for explaining an overview of an information processing system S according to an embodiment. [Diagram 2] 1 is a block diagram showing a configuration of an information processing device 1. FIG. [Diagram 3] 11 is a diagram showing an example of motion data acquired by a motion data acquisition unit 131. FIG. [Figure 4] 13 is a diagram showing an example of extracted data generated by an extracted data generating unit 132. FIG. [Diagram 5] 13 is a diagram showing an example of maintenance data acquired by a maintenance data acquisition unit 133. FIG. [Figure 6]13 is a diagram showing an example of processing status information acquired by a processing status acquisition unit 135. FIG. [Figure 7] 4 is a diagram showing an example of a data structure of procedure information stored in a storage unit 12. FIG. [Figure 8] 3 is a flowchart showing a process flow in the information processing device 1. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] [Outline of Information Processing System S] 1 is a diagram for explaining an overview of an information processing system S according to an embodiment. The information processing system S is a system for supporting the maintenance of equipment, etc. The information processing system S includes an information processing device 1 and an information terminal 2.

[0018] The information processing device 1 is a device for predicting a fault that occurs in a network equipment group. The information processing device 1 stores a trained model that has been trained to predict a fault. The network equipment group is a plurality of equipment configured to provide a predetermined application service or a predetermined network service. The network equipment group includes, for example, a server, a switch, a router, and the like. The predetermined application service is, for example, but is not limited to, a payment service. The information processing device 1 is, for example, a server as a predetermined network service.

[0019] The information terminal 2 is a terminal used by a user of the information processing system S. The information terminal 2 is a personal computer, a tablet, or a smartphone. The user of the information processing system S is, for example, an employee of a business that provides a predetermined application service or a predetermined network service.

[0020] An overview of the processing of the information processing device 1 will be described. The information processing device 1 acquires operation data and maintenance data. The operation data is data indicating the operation status of devices constituting a network equipment group. The operation data indicates, for example, the communication status, traffic status, and alarm occurrence status in the network.

[0021] The maintenance data is data input from a system for maintaining a group of network equipment. The maintenance data is information indicating the contents of reports of malfunctions related to a specific application service received from users of the specific application service. As an example, the maintenance data is information obtained by aggregating report information input to an external system (not shown) by an operator who receives a report of a malfunction reported by a user.

[0022] The information processing device 1 acquires text data from an external device, and generates extracted data based on the acquired text data. The text data indicates, for example, text posted on a social networking service (SNS) or blog. The text data may also include operational information, management information, fault information, status information, and other data acquired from various databases. The extracted data is information related to the usage status of a specific application service that is included in text data generated outside the network equipment group. The extracted data is data generated by extraction from text that includes words and phrases related to the quality of the specific application service. The information processing device 1 acquires the text data.

[0023] The information processing device 1 outputs failure prediction information based on the operation data, maintenance data, and extracted data. The failure prediction information is information predicting the presence or absence of a failure in a specific application service or a group of network equipment. The failure prediction information may further include information indicating the service causing the failure and the service or network that is affected. More specifically, the information processing device 1 outputs the failure prediction information by inputting the operation data, maintenance data, and extracted data into a trained model.

[0024] The information processing device 1 has the effect of being able to predict the occurrence of a failure that cannot be detected only by information related to the device.

[0025] [Configuration of information processing device 1] 2 is a block diagram showing the configuration of the information processing device 1. The information processing device 1 has a communication unit 11, a storage unit 12, and a control unit 13. The control unit 13 has an operation data acquisition unit 131, an extracted data generation unit 132, a maintenance data acquisition unit 133, an output unit 134, and a processing status acquisition unit 135.

[0026] The communication unit 11 is a communication interface for transmitting and receiving data to and from other devices via a network. The storage unit 12 is a storage medium including a ROM (Read Only Memory), a RAM (Random Access Memory), an SSD (Solid State Drive), a hard disk drive, etc. The storage unit 12 stores in advance a program to be executed by the control unit 13.

[0027] The memory unit 12 stores a trained model that has been trained to output fault prediction information. The trained model learns using the learning operation data, the learning extraction data, and the learning maintenance data as teacher data, and has learned to output fault prediction information. The trained model has learned to output fault prediction information that matches the learning fault prediction information, based on the learning operation data, the learning extraction data, and the learning maintenance data. The learning operation data, the learning extraction data, and the learning maintenance data are learning operation data, extraction data, and maintenance data, respectively.

[0028] The control unit 13 is a processor such as a CPU (Central Processing Unit). The control unit 13 executes a program stored in the storage unit 12 to function as an operation data acquisition unit 131, an extraction data generation unit 132, a maintenance data acquisition unit 133, an output unit 134, and a processing status acquisition unit 135.

[0029] The operation data acquisition unit 131 acquires operation data. The operation data acquisition unit 131 acquires operation data from a group of network equipment or from an external device (not shown). FIG. 3 is a diagram showing an example of operation data acquired by the operation data acquisition unit 131. In the operation data shown in FIG. 3, "data type" and "amount" are associated with each other. "Data type" indicates the type of operation status of the equipment indicated by the record. "Data type" includes, for example, ping test results and traffic volume. "Amount" indicates the amount of the operation status indicated by the data type.

[0030] The extracted data generating unit 132 generates extracted data from the acquired text data. As an example, the extracted data generating unit 132 extracts a sentence containing a specific character string from the acquired text data, and generates extracted data by aggregating the extracted sentences. For example, the extracted data generating unit 132 extracts a sentence containing a name or an abbreviation thereof (referred to as "name, etc.") of a predetermined application service or network service, and a character string indicating poor quality of the service, such as "slow" or "unusable." The extracted data generating unit 132 may analyze the acquired text data, extract a sentence in which the emotion of the user who posted the sentence is a negative emotion, such as "anger," and the sentence contains the name, etc., of a predetermined application service or network service, to generate extracted data.

[0031] FIG. 4 is a diagram showing an example of extracted data generated by the extracted data generation unit 132. In the extracted data, "time" and "number of negative comments" are associated. "Time" indicates the time when the extracted data indicated by the record was generated. "Number of negative comments" indicates the number of sentences containing phrases indicating poor quality extracted from the acquired text data. In the extracted data, "number of positive comments" may be further associated. "Number of positive comments" indicates the number of sentences containing phrases indicating satisfaction with the service, etc., in the acquired text data.

[0032] The text data acquired by the extracted data generating unit 132 may further include a character string indicating a place or region, a character string indicating the usage status of a service, or a character string indicating the name of a related service, etc. In this case, the extracted data generating unit 132 generates extracted data that associates the character string indicating a place or region, a character string indicating the usage status of a service, or a character string indicating the name of a related service, etc., included in the text data. Configuring the extracted data in this way enables more detailed prediction of a failure.

[0033] The maintenance data acquisition unit 133 acquires maintenance data, which is data input from a system for maintaining a network equipment group. The maintenance data acquisition unit 133 acquires maintenance data from an external device. FIG. 5 is a diagram showing an example of maintenance data acquired by the maintenance data acquisition unit 133. In the maintenance data shown in FIG. 5, a "declaration type" and a "declaration number" are associated with each other. The "declaration type" indicates the type of declaration indicated by the record. For example, the declaration type indicates an event occurring on the user side of the service. The "declaration number" indicates the number of declarations tallied for the declaration content indicated by the "declaration type". The maintenance data may further be associated with the region where the declaration was made and the service to be declared, and may include the number of declarations tallied by region and by the service to be declared.

[0034] The output unit 134 outputs the fault prediction information by inputting the operation data acquired by the operation data acquisition unit 131, the extraction data generated by the extraction data generation unit 132, and the maintenance data acquired by the maintenance data acquisition unit 133 into the trained model. The output unit 134 may cause the information terminal 2 to display a screen corresponding to the fault prediction information output by the trained model. Specifically, the output unit 134 causes the information terminal 2 to display a screen showing the presence or absence of a fault indicated by the fault prediction information, the equipment causing the fault, and all or part of the information showing the service or area affected by the fault. When the fault prediction information indicates that a fault has occurred, the output unit 134 may highlight the fault on the screen according to the size of the range of influence of the fault. In addition, the output unit 134 may output the fault prediction information in the form of voice or the like. In particular, when the fault prediction information indicates that a fault has occurred, outputting the fault prediction information by voice makes it easier for the user to recognize the occurrence of the fault.

[0035] The information processing device 1 configured in this way has the effect of being able to predict the occurrence of a failure that cannot be detected only from information about the device.

[0036] The output unit 134 may store the failure prediction information in the storage unit 12, and when a request to display the failure prediction information is received from the information terminal 2, may display the past failure prediction information stored in the storage unit 12. By configuring the output unit 134 in this way, it is possible to easily perform a verification work for a past failure after the occurrence of a failure.

[0037] The network equipment group may include equipment from which the information processing device 1 cannot acquire operation data due to, for example, a system managed by a business operator other than the business operator that maintains the network, or because logs cannot be acquired from the equipment due to a lack of a monitoring function, etc. Thus, if the information processing device 1 is configured to output failure prediction information for equipment from which operation data is not to be acquired, based on operation data from equipment from which operation data can be acquired, the predictability of failures can be improved.

[0038] In the following, among the network equipment groups, the equipment group from which the information processing device 1 can obtain operation data is referred to as a first network equipment group, and the network equipment group from which the information processing device 1 cannot obtain operation data is referred to as a second network equipment group. The operation data acquisition unit 131 acquires operation data indicating the operation status of the devices constituting the first network equipment group. In this case, the trained model has learned to output failure prediction information including at least the presence or absence of a failure in a network equipment group including the second network equipment group based on the operation data, maintenance data, and extracted data of the first network equipment group.

[0039] The output unit 134 outputs information indicating whether a fault has occurred in the second network equipment group by inputting the operation data acquired by the operation data acquisition unit 131 and the extraction data generated by the extraction data generation unit 132 into the trained model. By configuring the information processing device 1 in this way, it is possible to improve the predictability of a fault in an equipment group from which operation data cannot be acquired.

[0040] For example, a case may be assumed in which a negative comment is made about the quality of a service due to a user's operational error, etc. In this regard, the information processing device 1 may be configured to output the presence or absence of a fault when a predetermined term related to the quality of the service in the extracted data satisfies a predetermined condition.

[0041] The output unit 134 outputs the occurrence of a failure based on a phrase included in the extracted data that indicates that the quality of a predetermined application service is poor. As an example, the output unit 134 causes the information terminal 2 to display a screen indicating the occurrence of a failure when the "number of negative comments" included in the extracted data exceeds a predetermined threshold. The output unit 134 may also cause the information terminal 2 to display a screen indicating the occurrence of a failure when the frequency of the "number of negative comments" included in the extracted data exceeds a predetermined threshold. As an example, the predetermined threshold is determined based on a statistic of the "number of negative comments" extracted from text data acquired when no failure occurs.

[0042] Furthermore, when a predetermined term related to the quality of the service in the extracted data satisfies a predetermined condition, the output unit 134 may output failure prediction information based on the acquired operation data, extracted data, and maintenance data. That is, when the amount or frequency of the "number of negative comments" included in the extracted data exceeds a predetermined threshold, the output unit 134 inputs the operation data, extracted data, and maintenance data into the trained model and outputs failure prediction information.

[0043] The information processing device 1 is configured to determine the presence or absence of a fault based on a predetermined word or phrase included in the extracted data, thereby providing the effect of improving the predictability of faults. Although the occurrence of a fault is predicted by comparison with a predetermined threshold, the comparison is not limited to the threshold, and may be made with, for example, a trend in the number of comments. By configuring the information processing device 1 in this way, it is possible to reduce erroneous predictions of faults due to comments based on user operation errors, etc., providing the effect of improving the predictability of faults.

[0044] There may be cases where an erroneous report is made due to an operational error by the user, etc. Therefore, the information processing device 1 may be configured to output the presence or absence of a fault when information indicating the occurrence of a fault contained in the maintenance data satisfies a predetermined condition.

[0045] When the output unit 134 acquires maintenance data equal to or greater than a predetermined threshold, it outputs information that a failure has occurred. As an example, when the "number of reports" included in the maintenance data exceeds a predetermined threshold, the output unit 134 causes the information terminal 2 to display a screen indicating that a failure has occurred in an area or service where the number of reports exceeds the predetermined threshold. As an example, the predetermined threshold is set based on a statistical value of the amount of reports when no failure has occurred.

[0046] Furthermore, when the "number of reports" included in the maintenance data exceeds a predetermined threshold, the output unit 134 may output fault prediction information based on the acquired operation data, extraction data, and maintenance data. That is, when the "number of reports" in the maintenance data included in the extraction data exceeds a predetermined threshold, the output unit 134 inputs the operation data, extraction data, and maintenance data to the trained model, and outputs fault prediction information.

[0047] By configuring the information processing device 1 in this way, it is possible to reduce erroneous predictions of failures due to user operation errors or the like, and it is possible to achieve the effect of improving the predictability of failures.

[0048] The information processing device 1 may be configured to output failure prediction information when the processing status of the application service satisfies a predetermined condition.

[0049] The processing status acquisition unit 135 acquires processing status information that quantitatively indicates the processing status of a specified application service. FIG. 6 is a diagram showing an example of processing status information acquired by the processing status acquisition unit 135. In the processing status information, a "data type" is associated with a "quantity." The "data type" indicates the type of processing status indicated by the record. The data type includes, for example, the "number of actual payments," the "number of payment errors," etc. The "processing volume" indicates the volume of the processing status indicated by the data type. Note that the processing status information may further be associated with information such as the location or region targeted by the record, related services, and other related data types.

[0050] The output unit 134 outputs that a fault has occurred when the processing status indicated by the processing status information is compared with a statistical value of a past processing status and there is a discrepancy. The statistical value is, for example, an average value or a median value. Whether or not there is a discrepancy may be determined by, for example, using a standard deviation, or based on whether or not the difference between the processing status and the statistical value or the discrepancy rate is equal to or greater than a predetermined threshold. As an example, the output unit 134 causes the information terminal 2 to display a screen indicating that a fault has occurred when the difference between the processing volume (processing frequency) of the "number of settlement errors" and "number of charge errors" included in the processing status information and the statistical value of the past processing volume (processing frequency) exceeds a predetermined threshold. The output unit 134 may cause the information terminal 2 to display a screen indicating that a fault has occurred when the processing volume (processing frequency) of the "number of settlement transactions" and "actual charge amount" included in the processing status information is equal to or less than a predetermined threshold.

[0051] The determination of the presence or absence of the above based on the processing status of the application service may be performed based on a comparison with a predicted value based on the past processing status. In this case, the processing status acquisition unit 135 acquires processing status information that quantitatively indicates the processing status of a specific application service in chronological order. In this case, the processing status information may further be associated with the time of the record and the date and time when the processing status information was acquired or generated.

[0052] The learning unit 131, when it inputs processing status information acquired in a time series using learning processing status information, which is processing status information acquired in the past, as teacher data, trains a trained model to output a predicted value of the processing status at a future point in time, and stores the trained trained model, which is the processing status learning model, in the storage unit 12. The output unit 245 outputs the occurrence of a fault when there is a deviation between the processing status indicated by the acquired processing status information and the predicted value output by the processing status learning model based on the past processing status indicated by the processing status information.

[0053] The information processing device 1 configured in this way has the effect of improving the predictability of failures. The output unit 134 may output information indicating that a failure has occurred based on a correlation between at least two or more types of information among the operation data, the maintenance data, the extraction data, and the processing status information. The output unit 134 may also output failure prediction information based on the operation data, the extraction data, the processing status information, and the maintenance data acquired based on the correlation.

[0054] [Output of response procedures] The information processing device 1 may be configured to output a response procedure based on the failure prediction information. The learning failure prediction information further includes the details of a failure in a predetermined application service or a group of network equipment. That is, the trained model in this case is trained to output failure prediction information including the details of the failure based on the input data, based on the learning failure prediction information including the details of the failure.

[0055] In this case, the storage unit 12 stores procedure information that associates the contents of a fault with a procedure for dealing with the contents of the fault. Fig. 7 is a diagram showing an example of the data structure of procedure information stored in the storage unit 12. In the procedure information, a "fault content" and a "response procedure" are associated with each other. The "fault content" indicates the contents of the fault. The "response procedure" indicates the procedure for dealing with the contents of the fault.

[0056] The output unit 134 further outputs a procedure for dealing with the content of the fault output by the trained model. The output unit 134 refers to the storage unit 12 and identifies a response procedure corresponding to the content of the fault indicated by the fault prediction information output by the trained model. The output unit 134 causes the information terminal 2 to display a screen for displaying the identified response procedure.

[0057] By configuring the information processing device 1 in this way, the user can determine how to deal with a failure.

[0058] [Processing flow in information processing device 1] Fig. 8 is a flowchart showing the flow of processing in the information processing device 1. The processing shown in Fig. 8 starts when the information processing device 1 acquires motion data.

[0059] The motion data acquisition unit 131 acquires motion data from an external device (S01). The extracted data generation unit 132 acquires text data from the external device (S02). The extracted data generation unit 132 generates extracted data based on the acquired text data (S03).

[0060] The maintenance data acquisition unit 133 acquires maintenance data from an external device (S04). The output unit 134 causes the information terminal 2 to display a screen displaying the failure prediction information output by inputting the operation data, the extracted data, and the maintenance data into the learned model (S05). The output unit 134 causes the screen displaying the failure prediction information to be displayed, as necessary, in accordance with a confirmation screen of various statistical information regularly used for monitoring operations in the information terminal 2. Then, the information processing device 1 ends the processing. The information processing device 1 may periodically repeat the above processing to continue monitoring the operation.

[0061] [Effects of information processing device 1] The information processing device 1 configured in this way has the effect of being able to predict the occurrence of a failure that cannot be detected only from information about the device.

[0062] Furthermore, this invention will make it possible to contribute to Goal 9 of the United Nations' Sustainable Development Goals (SDGs), which is to "build resilient infrastructure, promote industry, innovation and infrastructure."

[0063] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist of the present invention. For example, all or part of the device can be configured by distributing or integrating functionally or physically in any unit. In addition, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effect of the new embodiment resulting from the combination combines the effect of the original embodiment. [Explanation of symbols]

[0064] 1. Information processing device 2. Information terminal 11 Communications Department 12 Storage section 13 Control section 131 Operation data acquisition unit 132 Extraction data generation unit 133 Maintenance Data Acquisition Unit 134 Output section 135 Processing Status Acquisition Unit

Claims

1. an operation data acquisition unit that acquires operation data indicating the operation status of devices constituting a network equipment group for providing a predetermined application service; an extracted data generating unit that extracts extracted data that is information regarding a usage status of the predetermined application service included in text data generated outside the group of network equipment; a maintenance data acquisition unit that acquires maintenance data, which is data input from a system for maintaining the network equipment group; a storage unit that stores a trained model that has been trained to output learning failure prediction information, which is failure prediction information for learning, using learning operation data, which is learning operation data, learning extraction data, which is learning extraction data, and learning maintenance data, which is learning maintenance data, as input; and an output unit that outputs information indicating whether or not a fault has occurred by inputting the operation data acquired by the operation data acquisition unit, the extraction data generated by the extraction data generation unit, and the maintenance data acquired by the maintenance data acquisition unit into the trained model; and An information processing device having the above configuration.

2. the network equipment group includes a first network equipment group from which the operational data can be acquired, and a second network equipment group which is a network equipment group from which the operational data cannot be acquired; the operation data acquisition unit acquires the operation data indicating an operation status of devices constituting the first network equipment group; the output unit outputs information indicating whether a fault has occurred in the second network equipment group by inputting the operation data acquired by the operation data acquisition unit and the extraction data generated by the extraction data generation unit into the trained model. The information processing device according to claim 1 .

3. The learning failure prediction information further includes details of a failure in the predetermined application service or the network equipment group, The output unit further outputs a procedure for responding to the content of the fault output by the trained model.

3. The information processing device according to claim 1 or 2.

4. The maintenance data indicates a report of a defect related to the specified application service received from a user of the specified application service, The output unit outputs information indicating that a failure has occurred when the maintenance data is equal to or greater than a predetermined threshold.

3. The information processing device according to claim 1 or 2.

5. the extracted data is data extracted from a text including a phrase related to the quality of the predetermined application service; the output unit outputs information indicating that a failure has occurred based on a phrase indicating that the quality of the predetermined application service is poor, the phrase being included in the extracted data.

3. The information processing device according to claim 1 or 2.

6. a processing status acquisition unit that acquires processing status information that quantitatively indicates a processing status of the predetermined application service, the output unit outputs information indicating that a failure has occurred when the processing status indicated by the processing status information is compared with a statistical value of a past processing status and there is a deviation therefrom.

3. The information processing device according to claim 1 or 2.

7. a processing status acquisition unit that acquires processing status information that quantitatively indicates a processing status of the predetermined application service in a time series; the storage unit stores a processing status learning model, which is a trained model trained using training processing status information, which is previously acquired processing status information, as training data, and which is trained to output a predicted value of a processing status at a future time point predicted from a past processing status indicated by the input training processing status information; the output unit outputs information indicating that a failure has occurred when the processing status indicated by the processing status information is compared with a predicted value output by the processing status learning model based on the past processing status indicated by the processing status information and there is a deviation therebetween.

3. The information processing device according to claim 1 or 2.

8. The computer executes an operation data acquisition step of acquiring operation data indicating operation statuses of devices constituting a network equipment group for providing a predetermined application service; an extraction step of extracting extracted data, the extracted data being information regarding a usage status of the predetermined application service, included in text data generated outside the group of network equipment; a maintenance data step of acquiring maintenance data which is data input from a system for maintaining the network equipment group; an output step of outputting information indicating the occurrence or absence of a fault by inputting the acquired operation data, the generated extraction data, and the acquired maintenance data into a trained model trained using as teacher data the learning operation data, which is the learning operation data, the learning extraction data, which is the learning maintenance data, which is the learning maintenance data, and the learning fault prediction information, which is the learning fault prediction information, stored in a storage unit; An information processing method comprising the steps of:

9. On the computer, an operation data acquisition step of acquiring operation data indicating operation statuses of devices constituting a network equipment group for providing a predetermined application service; an extraction step of extracting extracted data, the extracted data being information regarding a usage status of the predetermined application service, included in text data generated outside the group of network equipment; a maintenance data step of acquiring maintenance data which is data input from a system for maintaining the network equipment group; an output step of outputting information indicating the occurrence or absence of a fault by inputting the acquired operation data, the generated extraction data, and the acquired maintenance data into a trained model trained using as teacher data the learning operation data, which is the learning operation data, the learning extraction data, which is the learning maintenance data, which is the learning maintenance data, and the learning fault prediction information, which is the learning fault prediction information, stored in a storage unit; A program that executes the following.

Images