Information processing device and information processing method

Abstract

To provide an information processing device capable of outputting appropriate restoration measures based on captured images of damaged power distribution equipment.SOLUTION: An information processing device is provided, comprising an acquisition unit configured to acquire captured images of damaged power distribution equipment, and an output unit configured to receive the acquired captured images and output restoration measures for the power distribution equipment based on the captured images using a trained model trained to output restoration measures for the power distribution equipment.SELECTED DRAWING: Figure 3

Description

[Technical field]

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

[0002] When restoring damaged power distribution facilities such as utility poles, the on-site inspector is primarily responsible for determining the restoration method. However, the criteria for determining the restoration method vary greatly depending on the on-site inspector's level of expertise, and in some cases, more experienced workers must be dispatched to the site to re-determine the restoration method, which can delay the start of restoration work.

[0003] To address such problems, for example, Patent Document 1 discloses a technology that uses images of the damaged facility and images of the facility before the damage to assist in the selection of a restoration method for the damaged facility. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2011-059824 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the technology disclosed in Patent Document 1 requires an image of the equipment before it is damaged, and therefore cannot be applied if the image does not exist. In other words, the technology cannot be applied unless the external characteristics of the equipment before it is damaged can be grasped.

[0006] An object of the present invention is to provide an information processing device capable of outputting an appropriate restoration method based on a captured image of damaged power distribution equipment. [Means for solving the problem]

[0007] In order to achieve the above object, one of the present inventions is to provide an image capturing apparatus for capturing an image of a damaged power distribution facility.and map information around the distribution facility. and an acquisition unit for acquiring the captured image. and the map information A trained model that has been trained to output a restoration method for the power distribution equipment when and the map information and an output unit that outputs the restoration method for the power distribution facility from the

[0008] According to this configuration, the information processing device can output an appropriate restoration method based on the captured image of the damaged power distribution facility. As a result, the worker can make a certain judgment about the restoration method based on the output of the information processing device regardless of the worker's level of proficiency. Furthermore, with this configuration, map information about the surrounding area of ​​the power distribution facility is further included in the teacher data for generating the trained model. Depending on infrastructure facilities (roads, railways, bridges, etc.) and topography (rivers, mountains, seas, etc.) within a predetermined range based on the power distribution facility, the restoration method may be restricted. Therefore, by including map information including such information in the teacher data, the accuracy of the restoration method output from the trained model is improved.

[0009] Another aspect of the present invention is the information processing device, wherein the power distribution facility is a utility pole.

[0010] In such a configuration, the information processing device can output an appropriate restoration method based on the captured image of the damaged utility pole. As a result, the worker can make a certain judgment about the restoration method based on the output of the information processing device regardless of the worker's level of proficiency.

[0011] Another aspect of the present invention is the information processing device, wherein the captured image is an image including information about a periphery of the power distribution facility.

[0012] In such a configuration, the teacher data for generating the trained model further includes information about the surroundings of the power distribution facility. Depending on the structures (houses, public facilities, etc.), infrastructure facilities (roads, railways, bridges, etc.), topography (rivers, mountains, seas, etc.) surrounding the power distribution facility, the restoration method may be restricted. Therefore, by including such information in the teacher data, the accuracy of the restoration method output from the trained model is improved.

[0015] Another aspect of the present invention is the information processing device, wherein the recovery method includes equipment required for recovery.

[0016] In such a configuration, the trained model can further output the equipment required for restoration. As a result, the workers can immediately grasp and prepare the equipment required for restoration. This reduces the burden on the workers.

[0017] Another aspect of the present invention is the information processing device, wherein the recovery method includes a special vehicle required for recovery.

[0018] In such a configuration, the trained model can further output the special vehicles required for restoration. As a result, the workers can immediately grasp and arrange for the special vehicles required for restoration. This reduces the burden on the workers.

[0019] Another aspect of the present invention is the information processing device described above, wherein the recovery method includes a number of workers required for recovery.

[0020] In such a configuration, the trained model can further output the number of workers required for restoration, so that the number of workers required for restoration can be immediately known.

[0021] Another aspect of the present invention is the information processing device, wherein the recovery method includes determining whether or not a power outage is necessary.

[0022] In such a configuration, the trained model can further output whether or not a power outage is necessary, so that workers can immediately know whether or not a power outage is necessary during restoration work.

[0023] Another aspect of the present invention is the information processing device, wherein the recovery method includes a work time required for recovery.

[0024] In such a configuration, the trained model can further output the work time required for restoration. As a result, the worker can immediately grasp the work time required for restoration. Furthermore, the worker can inform the road administrators around the restoration work site of the work time.

[0025] Another aspect of the present invention is an image of a damaged power distribution facility. and map information around the distribution facility and an acquisition unit that acquires teacher data associated with the restoration method of the power distribution facility, and and the map information and a model generation unit that generates a trained model that outputs a restoration method for the power distribution equipment when the trained model is input.

[0026] With this configuration, the information processing device can generate a trained model capable of outputting an appropriate restoration method based on captured images of damaged power distribution equipment.

[0027] Another aspect of the present invention is an image of a damaged power distribution facility. and map information around the distribution facility. and acquiring the captured image. and the map information A trained model that has been trained to output a restoration method for the power distribution equipment when and the map information and outputting a restoration method for the power distribution facility from the

[0028] According to this method, an appropriate restoration method can be output based on the captured image of the damaged power distribution facility, which allows workers to make a consistent judgment on the restoration method regardless of their level of skill.

[0029] Another aspect of the present invention is an image of a damaged power distribution facility. and map information around the distribution facility and acquiring teacher data in which the image is associated with a restoration method for the power distribution facility. and the map information and generating a trained model that outputs a restoration method for the power distribution equipment when the trained model is input.

[0030] According to this method, it is possible to generate a trained model that can output an appropriate restoration method based on captured images of damaged power distribution equipment. Effect of the Invention

[0031] According to the present invention, it is possible to provide an information processing device capable of outputting an appropriate restoration method based on a captured image of damaged power distribution equipment. [Brief description of the drawings]

[0032] [Figure 1] FIG. 1 is a diagram showing a configuration of an information processing system 1. [Diagram 2] FIG. 2 is a diagram illustrating an example of hardware of an information processing device 2. [Diagram 3] FIG. 11 is a diagram illustrating an example of teacher data. [Figure 4] FIG. 2 is a diagram showing a captured image of the teacher data. [Diagram 5] FIG. 2 is a diagram showing functional blocks of an information processing device 2. [Figure 6] 1 is a flowchart illustrating the process flow for generating a trained model. [Figure 7] 13 is a flowchart illustrating a process flow up to displaying a recovery method. [Figure 8] FIG. 4 is a diagram showing an example of a captured image. [Figure 9] FIG. 2 is a diagram showing an example of an output screen 240. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0033] == Implementation form == <Information Processing System> 1 is a diagram showing a schematic configuration of an information processing system 1 according to the present embodiment. The information processing system 1 includes an information processing device 2 and a mobile terminal 4. The information processing device 2 and the mobile terminal 4 are communicatively connected via a network NW. The network NW is, for example, a public line such as the Internet, or a dedicated line such as a Wide Area Network (WAN) or a Local Area Network (LAN).

[0034] The mobile terminal 4 is a portable terminal such as a smartphone, a tablet terminal, or a laptop computer, and is equipped with a camera. A worker carries the mobile terminal 4 to a site for patrol or inspection, and takes a picture of the on-site power distribution equipment. The mobile terminal 4 provides an image of the damaged power distribution equipment (hereinafter referred to as a "captured image") to the information processing device 2. "Power distribution equipment" refers to equipment for transmitting power generated at a power plant to power consumers. Power distribution equipment includes, for example, utility poles, pole mounting equipment, and power distribution lines. Furthermore, the power distribution equipment may be overhead power distribution equipment or underground power distribution equipment.

[0035] The captured image is not limited to one captured by the mobile terminal 4, and may be, for example, one captured by a camera managed by a power company, etc. The captured image may be provided to the information processing device 2 via a recording medium, or via a wired or wireless communication means (such as a local area network (LAN) or universal serial bus (USB)).

[0036] The information processing device 2 generates a trained model that outputs a restoration method for the damaged power distribution facility. The information processing device 2 further outputs a restoration method for the damaged power distribution facility from the captured image using the generated trained model (details will be described later).

[0037] In this embodiment, the power distribution facility is described as a utility pole. In this embodiment, a concrete pole is described as an example of a support for the utility pole. The "damaged" state of the utility pole refers to a state in which the utility pole is tilted, collapsed, chipped, or broken, compared to the normal state of the utility pole.

[0038] [Hardware configuration of information processing device] 2 is a diagram showing an example of hardware of an information processing device 2. The illustrated information processing device 2 includes a processor 20, a main storage device 21, an auxiliary storage device 22, an input device 23, an output device 24, and a communication device 25. The illustrated information processing device 2 may be realized, in whole or in part, by using virtual information processing resources provided by using a virtualization technique or a process space separation technique, such as a virtual server provided by a cloud system. In addition, all or in part of the functions provided by the information processing device 2 may be realized by a service provided by the cloud system via an API (Application Programming Interface), for example. The information processing system 1 may be configured by using a plurality of information processing devices 2 connected to each other so as to be able to communicate with each other.

[0039] In the figure, the processor 20 is configured using, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), an AI (Artificial Intelligence) chip, etc.

[0040] The main memory device 21 is a device that stores programs and data, and is, for example, a Read Only Memory (ROM), a Random Access Memory (RAM), or a non-volatile memory (Non Volatile RAM (NVRAM)).

[0041] The auxiliary storage device 22 is, for example, a solid state drive (SSD), a hard disk drive, an optical storage device (such as a compact disc (CD) or a digital versatile disc (DVD)), a storage system, a reading / writing device for a recording medium such as an IC card, an SD card or an optical recording medium, a storage area of ​​a cloud server, etc. Programs and data can be read into the auxiliary storage device 22 via a recording medium reading device or a communication device 25. The programs and data stored (memorized) in the auxiliary storage device 22 are read into the main storage device 21 as needed.

[0042] The input device 23 is an interface that accepts input from the outside, and is, for example, a keyboard, a mouse, a touch panel, a card reader, a pen-input tablet, a voice input device, or the like.

[0043] The output device 24 is an interface that outputs various information such as the process progress, the process results, etc. The output device 24 is, for example, a display device (liquid crystal monitor, LCD (Liquid Crystal Display), graphic card, etc.) that visualizes the various information described above, a device that converts the various information described above into voice (voice output device (speaker, etc.)), or a device that converts the various information described above into characters (printer, etc.).

[0044] The input device 23 and the output device 24 constitute a user interface for receiving information from the user and presenting information.

[0045] The communication device 25 is a device that realizes communication with other devices. The communication device 25 is a wired or wireless communication interface that realizes communication with other devices via a communication network such as the Internet, and is, for example, a NIC (Network Interface Card), a wireless communication module, a USB module, etc. The information processing device 2 is configured to input and output information to and from the mobile terminal 4 via the communication device 25.

[0046] In the information processing device 2, for example, an operating system, a file system, a DBMS (DataBase Management System) (relational database, NoSQL, etc.), a KVS (Key-Value Store), etc. may be installed.

[0047] Each of the above-mentioned functions of the information processing system 1 is realized by the processor 20 of the information processing device 2 reading and executing a program stored in the main storage device 21, or by hardware (FPGA, ASIC, AI chip, etc.) constituting the information processing system 1. The information processing system 1 stores the above-mentioned various information (data), for example, as a table of a database or a file managed by a file system.

[0048] [Teacher data] 3 and 4 are diagrams for explaining the teacher data 5 of this embodiment stored in the auxiliary storage device 22 described above. The "teacher data" of this embodiment is data in which captured image data expressing an image of a damaged utility pole is associated with a method of restoring the utility pole. Here, the captured image data expressing an image of a damaged utility pole is input data, and the method of restoring the utility pole is correct answer data. The teacher data 5 includes a plurality of data. Each of the plurality of data corresponds to restoration work carried out in the past on a damaged utility pole. The damaged utility pole here is, for example, a utility pole that was previously damaged among utility poles existing in a predetermined area, such as an area under the jurisdiction of a power company that manages the information processing system 1. One data is arranged in one column of FIG. 3.

[0049] Here, the "input data" in this embodiment is image data of a damaged utility pole during restoration work (FIG. 3). A file name that identifies the captured image data is shown in FIG. 3. FIG. 4 is a diagram showing the captured image data of a damaged utility pole in data 5a of the teacher data 5 as a captured image.

[0050] The captured image is preferably an image including information about the vicinity of the utility pole. The "surrounding information" refers to structures (houses, public facilities, etc.), infrastructure facilities (roads, railways, bridges, etc.), topography (rivers, mountains, seas, etc.) around the utility pole. The information about the vicinity of the utility pole may affect the selection of the restoration method, such as restricting the restoration method. Therefore, when the information about the vicinity of the utility pole is included in the input data, the accuracy of the restoration method output by the trained model generated by the model generation unit 31 described later is improved.

[0051] In addition, it is preferable that the captured image includes the pole mounting equipment (voltage regulator (power transformer), pole-mounted transformer, switch, power transmission line, power distribution line, insulator, etc.) of the utility pole. The pole mounting equipment contributes to the weight of the utility pole, and thus influences the selection of the restoration method. Therefore, when information on the pole mounting equipment of the utility pole is included in the input data, the accuracy of the restoration method output by the trained model generated by the model generation unit 31 is improved.

[0052] Furthermore, if the captured image includes equipment for mounting the utility pole, when an oil leak, for example from a pole-mounted transformer, is confirmed by a worker either visually or through the information processing device 2, the worker will be able to recognize that absorbent mats, oil pans, etc. will be necessary for dealing with the oil leak during restoration work, which is preferable.

[0053] In addition, the "correct data" in this embodiment is a restoration method in a past restoration work. In this embodiment, the "restoration method" includes information such as damage details 51a, restoration method 51b, necessary equipment 51c, special vehicles 51d, number of workers 51e, power outage necessity 51f, and work time 51g.

[0054] The damage details 51a are damage details of the damaged utility pole. The damage details 51a classifies the damage of the utility pole into tilt, collapse, or breakage. For example, in the data 5a of the teacher data 5, the damage details 51a are written as "tilt."

[0055] Restoration method 51b is the type of standard restoration method applied to restoration work. Standard restoration methods include the temporary support method, ground-level reinforcement metal fitting method, reused pole construction method, substitute pole construction method, intermediate reinforcement metal fitting method, base joint pole reuse method, arm bracket extension method, arm bracket joint pole construction method, or log joint pole construction method. Restoration method 51b is a method selected from these. In data 5a, restoration method 51b is described as the "temporary support method" applied to restore the tilt of the utility pole.

[0056] The necessary equipment 51c is the equipment required for the restoration work. The necessary equipment 51c is, for example, wires, reinforcing metal fittings, etc. In the data 5a, the wire used in the "temporary support construction method" is indicated as "wire a".

[0057] Special vehicles 51d indicates whether or not special vehicles were required for the restoration work. If they were required, it indicates the type and number of special vehicles. "Special vehicles" are vehicles required for restoration, such as pole erection vehicles and crane vehicles. In data 5a, "not required" is displayed, indicating that special vehicles were not used in the "temporary support line construction method."

[0058] The number of workers 51e is the number of workers mobilized for the restoration work. In the data 5a, it is written as "10", which indicates that 10 workers were mobilized for the "temporary support construction method".

[0059] The power outage necessity 51f indicates whether or not a power outage was implemented during the restoration work. In the data 5a, "Necessary" is written, which indicates that a power outage was implemented during the restoration work using the "temporary support line method."

[0060] Work time 51g is the work time required for the restoration work. In data 5a, it is written as "3.0h", indicating that the restoration work using the "temporary support method" took 3 hours of work.

[0061] Although the teacher data 5 of this embodiment has been described above, the input data and the correct answer data in the teacher data 5 are not limited to the above description. For example, the input data may further include map information of the vicinity of the utility pole. "Map information" refers to infrastructure facilities (roads, railways, bridges, etc.) and topography (rivers, mountains, seas, etc.) within a predetermined range based on the utility pole. Depending on the map information of the vicinity of the utility pole, the selection of the restoration method may be influenced, such as restricting the restoration method. Therefore, when the input data includes map information of the vicinity of the utility pole, the accuracy of the restoration method output by the trained model is improved.

[0062] The input data may further include information on the utility pole (e.g., the location of the utility pole, the pole mounting equipment, the positional relationship with adjacent utility poles, etc.). The information on the utility pole contributes to the weight of the utility pole, the ease of transporting the utility pole, the ease of lifting the utility pole, etc., and ultimately influences the selection of the restoration method. Therefore, when the information on the utility pole is included in the input data, the accuracy of the restoration method output by the trained model is improved.

[0063] The correct answer data may also include more detailed information about the damage details 51a. Specifically, the correct answer data may further include the range of damage on the ground surface (for example, the range of distance based on the ground-level part of the utility pole, etc.). If the damage details 51a are inclinations, the correct answer data may further include the angle of inclination, the direction of inclination, etc. If the damage details 51a are breakage at the ground level, the correct answer data may further include the degree of displacement above the broken part (for example, the displacement width based on the diameter of the utility pole, etc.), the distance of the broken part from the ground, etc. If the damage details 51a are collapsed, the correct answer data may further include the direction of collapse, etc.

[0064] The details of the damage content 51a can be grasped from the imaging data 50 by the model generating unit 31 described later. However, by including the details of the damage content 51a in the correct answer data in advance, the accuracy of the restoration method output by the trained model is improved.

[0065] In addition, depending on the details of the damage content 51a, information other than the damage content 51a included in the restoration method 51 may be affected. Therefore, when the details of the damage content 51a are included in the input data, the accuracy of the restoration method output by the trained model is improved.

[0066] [Functional blocks of information processing equipment] 5 is a diagram showing functional blocks of the information processing device 2 of this embodiment. In the information processing device 2 of this embodiment, a first acquisition unit 30, a model generation unit 31, a second acquisition unit 32, an output unit 33, and a display control unit 34 are realized by the processor 20 executing a predetermined program.

[0067] The first acquisition unit 30 acquires the teacher data 5 (FIGS. 3 and 4) stored in the auxiliary storage device 22.

[0068] The model generation unit 31 generates a trained model based on the teacher data 5 acquired by the first acquisition unit 30. The trained model is a machine learning model that outputs a method for restoring a utility pole when a captured image of a restoration target is input.

[0069] Here, the restoration method output by the trained model includes the details of the damage to the damaged utility pole, the restoration method required to restore the damaged utility pole, the equipment required for restoration, the special vehicles required for restoration, the number of workers required for restoration, the standard time required for restoration work, and whether a power outage is necessary.

[0070] The model generation unit 31 performs deep learning to learn the features of damaged utility poles in the captured images, and constructs (generates) a neural network as a trained model that takes the captured images as input and outputs a method for restoring the utility poles.

[0071] The "feature amount" includes, for example, the angle at which the utility pole is tilted, the direction in which the utility pole is tilted, the direction in which the utility pole collapsed, and the distance from the ground to the broken part of the utility pole.

[0072] The neural network is, for example, a convolution neural network (CNN), and has an input layer that receives an input of a captured image, an output layer that outputs a restoration method, and an intermediate layer that extracts features. A detailed process of constructing (generating) the neural network will be described later.

[0073] The second acquisition unit 32 acquires a captured image of a damaged utility pole. The second acquisition unit 32 acquires the captured image from the mobile terminal 4 via the network NW. The mobile terminal 4 may also store the captured image in advance in the auxiliary storage device 22 via the network NW, and the second acquisition unit 32 may acquire the captured image from the auxiliary storage device 22.

[0074] The output unit 33 uses the trained model generated by the model generation unit 31 to output a method for restoring the utility pole from the captured image acquired by the second acquisition unit 32.

[0075] The display control unit 34 generates an output screen for explaining the recovery method output by the output unit 33, and causes the output device 24 to display the output screen.

[0076] [Processing to generate a trained model] 6 is a flowchart illustrating the flow of processing up to generation of a trained model by the information processing device 2. The processing up to generation of a trained model includes step S11 and step S12.

[0077] First, in step S11, the first acquisition unit 30 of the information processing device 2 acquires the teacher data 5. The teacher data 5 shown in Fig. 3 is an example of the teacher data acquired by the first acquisition unit 30 in step S11.

[0078] Next, in step S12, the model generation unit 31 of the information processing device 2 generates a trained model by using the teacher data 5 shown in FIG.

[0079] In step S12, the input layer of the neural network (not shown) passes the input pixel values ​​to the intermediate layer. The intermediate layer passes the extracted feature values ​​to the output layer. The output layer identifies a restoration method for the utility pole based on the feature values ​​output from the intermediate layer.

[0080] In this embodiment, the trained model is described as a neural network, but the trained model may be a trained model constructed using other learning algorithms, such as a Support Vector Machine (SVM), a Bayesian network, or a regression tree.

[0081] The model generation unit 31 inputs the captured image, which is input data, to the input layer, and obtains the result of the utility pole restoration method from the output layer. The model generation unit 31 compares the result of the restoration method output from the output layer with the correct data, and optimizes parameters used in the calculation process so that the result of the restoration method approaches the correct data. The parameters used in the calculation process include, for example, weights (coupling coefficients) between neurons, activation function coefficients used in each neuron, etc. There are no particular limitations on the method of optimizing the parameters, but the model generation unit 31 optimizes various parameters using, for example, an error backpropagation method.

[0082] Through the above-described processing, the processing up to generation of the trained model is completed. The generated trained model is stored in the auxiliary storage device 22.

[0083] [Processing until recovery method is displayed] 7 is a flowchart explaining the flow of processing until the information processing device 2 displays a recovery method. The processing until the information processing device 2 displays a recovery method includes steps S21 to S23. It is assumed that a trained model is stored in the auxiliary storage device 22 before this processing.

[0084] First, in step S21, the second acquisition unit 32 acquires a captured image and a trained model. At this time, the second acquisition unit 32 acquires the captured image from the mobile terminal 4 via the network NW. Furthermore, the second acquisition unit 32 acquires the trained model from the auxiliary storage device 22. FIG. 8 is a diagram illustrating an example of a captured image 4a captured by the mobile terminal 4.

[0085] In step S22, the output unit 33 uses the trained model to output a method for restoring the utility pole from the captured image 4a.

[0086] In step S23, the display control unit 34 generates an output screen 240 explaining the recovery method output by the output unit 33, and causes the output device 24 to display it.

[0087] FIG. 9 is a diagram showing an example of the output screen 240 in this example. The output screen 240 displays the captured image 4a and a display window 90 for explaining the restoration method. In this example, the display window 240a displays that the damage of the utility pole to be restored is a ground-level breakage, and the details thereof. Furthermore, the display window 240a displays that the ground-level reinforcement metal fitting method is appropriate as the restoration method. The display window 240a also displays that the restoration work requires a ground-level reinforcement metal fitting c as a necessary material, that one pole erection vehicle is required as a special vehicle, that 5 to 7 workers are required as a workforce, that a power outage is not required, and that the work time is 4.5 hours.

[0088] The user can arrange for restoration work to be carried out on the utility pole shown in the captured image 4a based on the contents of the output screen 240. Then, the mobilized workers can start the restoration work on the utility pole.

[0089] The above-mentioned embodiment is for the purpose of facilitating understanding of the present invention, and is not intended to limit the present invention. Furthermore, the present invention can be modified or improved without departing from the spirit of the present invention, and it goes without saying that the present invention includes equivalents thereof.

[0090] For example, in the present embodiment, a utility pole supported by a concrete pole has been described as the power distribution facility, but a utility pole supported by a wooden pole may be used. In addition, both a utility pole supported by a concrete pole and a utility pole supported by a wooden pole may be included. In addition, the power distribution facility is not limited to a utility pole, and may be, for example, another type of power distribution facility such as a power distribution line.

[0091] In the present embodiment, the first acquisition unit 30, the model generation unit 31, the second acquisition unit 32, the output unit 33, and the display control unit 34 are provided in the information processing device 2, but the present invention is not limited to this. For example, the first acquisition unit 30 and the model generation unit 31 may be provided in one information processing device, and the second acquisition unit 32, the output unit 33, and the display control unit 34 may be provided in another information processing device.

[0092] Even in such cases, the information processing device 2 can output an appropriate restoration method based on the captured image of the damaged power distribution facility. [Explanation of symbols]

[0093] 1: Information processing system 2: Information processing device 20: Processor 21: Main memory 22: Auxiliary storage device 23: Input device 24: Output device 25:Communication equipment 30:1st acquisition part 31: Model generation section 32:Second acquisition part 33: Output section 34: Display control unit 4. Mobile devices 5: Training data

Claims

1. an acquisition unit that acquires an image of the damaged power distribution facility and map information of a periphery of the power distribution facility; and an output unit that outputs a method for restoring the power distribution equipment from the captured image and the map information using a trained model that has been trained to output a method for restoring the power distribution equipment when the acquired captured image and the map information are input.

2. 2. The information processing device according to claim 1, The power distribution facility is a utility pole. Information processing device.

3. 3. The information processing device according to claim 1, The captured image is an image including information about the surroundings of the power distribution facility. Information processing device.

4. The information processing device according to any one of claims 1 to 3, The recovery method includes equipment required for recovery, Information processing device.

5. The information processing device according to any one of claims 1 to 4, The recovery method includes a special vehicle required for recovery, Information processing device.

6. The information processing device according to any one of claims 1 to 5, The restoration method includes the number of workers required for restoration, Information processing device.

7. The information processing device according to any one of claims 1 to 6, The recovery method includes whether or not a power outage is necessary; Information processing device.

8. The information processing device according to any one of claims 1 to 7, The recovery method includes a work time required for recovery, Information processing device.

9. an acquisition unit that acquires teacher data in which an image of a damaged power distribution facility and map information of a periphery of the power distribution facility are associated with a restoration method for the power distribution facility; a model generation unit that generates a trained model that outputs a restoration method for the power distribution facility when the captured image and the map information are input based on the acquired teacher data; An information processing device comprising:

10. acquiring an image of the damaged power distribution facility and map information of a periphery of the power distribution facility; outputting a restoration method for the power distribution equipment from the captured image and the map information using a trained model that has been trained to output a restoration method for the power distribution equipment when the acquired captured image and the map information are input; An information processing method comprising:

11. acquiring training data in which an image of a damaged power distribution facility and map information of a periphery of the power distribution facility are associated with a restoration method for the power distribution facility; generating a trained model that outputs a restoration method for the power distribution facility when the captured image and the map information are input based on the acquired teacher data; An information processing method comprising:

Images