Information processing device

Abstract

An information processing device (D) includes a control unit. The control unit executes operations including: selecting prediction target equipment; extracting a prediction target area from the prediction target equipment; constructing an equipment capacity predictor that predicts an equipment capacity required in the prediction target area on the basis of equipment information associated with the prediction target equipment and service demand related data associated with the prediction target area; constructing a corrosion predictor that predicts the corrosion level of the prediction target equipment on the basis of the equipment information associated with the prediction target equipment and corrosion related data associated with the prediction target area; and executing, for the prediction target equipment on the basis of the predicted equipment capacity or the predicted corrosion level, at least one of determination of an inspection frequency, determination of priorities for repair and replacement, and determination of quantities of replacement and construction.

Description

Information processing device

[0001] The present disclosure relates to an information processing device.

[0002] Social infrastructure facilities were intensively developed during the period of rapid economic growth. The number of aging facilities is increasing, and there are concerns that the proportion of facilities built more than 50 years ago will increase exponentially in the future. However, the number of engineers involved in the construction and maintenance of social infrastructure is on the decline. Due to population decline and an aging population, this number is expected to continue to decline. Furthermore, demographic changes and technological advances are having a direct impact on social infrastructure facilities. Facilities in some areas, particularly depopulated areas, are experiencing a decline in business profitability due to reduced utilization. In particular, with regard to information and communications infrastructure facilities, wired communication networks are shrinking due to changes in information and communications networks (e.g., the decline of copper networks and advances in optical and wireless access technologies). This is expected to lead to a decline in the capacity of communication cables in communication infrastructure facilities (such as buried pipelines). These factors make it difficult to properly maintain social infrastructure facilities, potentially hindering the provision of safe and secure social infrastructure services.

[0003] Meanwhile, digitalization of social infrastructure facilities is progressing. Data collection of social infrastructure facilities and inspections using AI based on the collected data are being carried out (e.g., Non-Patent Document 1). Furthermore, a method for predicting corrosion progression using machine learning based on inspection data collected from social infrastructure facilities has been established (e.g., Non-Patent Document 2).

[0004] Nippon Telegraph and Telephone Corporation, "High-Precision Detection of Rust on Social Infrastructure Equipment Using Image Recognition AI," [Online], May 16, 2022, [November 30, 2023], Internet <URL: https: / / group.ntt / jp / newsrelease / 2022 / 05 / 16 / 220516a.html> Yo Ito and Aiko Furukawa, "A Method for Predicting Corrosion on the Inner Surface of Telecommunication Pipes Using Machine Learning Based on Inspection Results," Proceedings of AI and Data Science, August 2022, Vol. 3, Issue J2, pp. 517-526

[0005] As mentioned above, methods have been proposed to improve the efficiency of equipment inspections and evaluate corrosion of equipment by utilizing digitized equipment information. However, no method has been clarified for efficiently inspecting, repairing, and updating the vast amount of social infrastructure equipment that exists, taking into account the area where the equipment is installed.

[0006] The purpose of the present disclosure, made in consideration of such circumstances, is to perform economical maintenance and management of facilities for each region, taking into account the area where the facilities are installed.

[0007] An information processing device according to one embodiment is an information processing device including a control unit, wherein the control unit performs operations including: selecting a facility to be predicted; extracting a prediction target area from the facility to be predicted; constructing an equipment quantity predictor that predicts the predicted equipment quantity required in the prediction target area based on equipment information associated with the facility to be predicted and service demand-related data associated with the prediction target area; constructing a corrosion predictor that predicts the corrosion level of the facility to be predicted based on the equipment information associated with the facility to be predicted and corrosion-related data associated with the prediction target area; and performing at least one of determining an inspection frequency, a priority for repairs and updates, and an amount of updates and construction for the facility to be predicted based on the predicted equipment quantity or the predicted corrosion level.

[0008] According to the present disclosure, the objective is to perform economical maintenance and management of facilities for each region, taking into consideration the area where the facilities are installed.

[0009] 1 is a block diagram showing the configuration of an information processing device according to an embodiment; FIG. 2 is a diagram showing equipment and areas; FIG. 3 is a diagram showing other equipment and areas; FIG. 4 is a diagram showing an example of determining inspection frequency; FIG. 5 is a diagram showing an example of determining priority; FIG. 6 is a diagram showing a flowchart of selection and extraction processing by an information processing device; FIG. 7 is a diagram showing a flowchart of generation processing of an equipment quantity predictor by an information processing device; FIG. 8 is a diagram showing a flowchart of generation processing of a corrosion predictor by an information processing device; FIG. 9 is a diagram showing a flowchart of prediction processing of predicted equipment quantity by an information processing device; FIG. 10 is a diagram showing a flowchart of prediction processing of corrosion degree by an information processing device; FIG. 11 is a diagram showing a flowchart of judgment processing by an information processing device;

[0010] An embodiment will be described below with reference to the drawings. In each drawing, identical or corresponding parts are designated by the same reference numerals. In the description of this embodiment, the description of identical or corresponding parts will be omitted or simplified as appropriate.

[0011] The information processing device D shown in FIG. 1 can communicate with one or more terminals via a network. The network includes, for example, the Internet, at least one WAN, at least one MAN, or any combination thereof. "WAN" is an abbreviation for wide area network. "MAN" is an abbreviation for metropolitan area network. The network may include at least one wireless network, at least one optical network, or any combination thereof. The wireless network may be, for example, an ad hoc network, a cellular network, a wireless LAN, a satellite communication network, or a terrestrial microwave network. "LAN" is an abbreviation for local area network.

[0012] 1 shows one information processing device D, but alternatively, there may be any number of information processing devices D. The processing executed by the information processing device D may be executed by a plurality of information processing devices D in a distributed arrangement.

[0013] The information processing device D is a general-purpose computer such as a PC, a server computer such as a cloud server, or a dedicated computer. "PC" is an abbreviation for personal computer.

[0014] An overview of this embodiment will be explained. This embodiment relates to a device that presents maintenance and management guidelines for facilities based on the installation status of social infrastructure facilities deployed across a surface and the characteristics of the surrounding region (i.e., area). The information processing device D of this embodiment has the following functions: Function 1. A function to predict the amount of facilities required in a given area based on information about the surrounding area, such as population, land use type, zoning, and building area. Function 2. A function to predict the degree of corrosion of facilities based on digitized facility information and information about the installation location of the facilities. Function 3. A function to determine the priority of inspection, repair, and renewal for each area based on the prediction results of Functions 1 and 2 above.

[0015] The details of this embodiment will now be described.

[0016] The information processing device D includes a storage unit 1, a construction unit 2, an input unit 3, a prediction unit 4, a determination unit 5, and an output unit 6. The storage unit 1 includes an equipment database 11, a regional information database 12, and a predictor database 13. The equipment database 11 includes equipment information. The regional information database 12 includes service demand-related data and corrosion-related data. In FIG. 1, the flow of information between functions is as follows: Flow of equipment information F1 Flow of regional information F2 Flow of predictor data F3 Flow of prediction processing F4

[0017] The information processing device D may be, for example, a geographic information system (GIS) that can manage data with location information and handle it visually, or a system that can be incorporated into other systems as part of it.

[0018] Each functional unit of the information processing device D will be described.

[0019] The memory unit 1 stores various information used in this system as well as the results of processing executed by each unit. The memory unit 1 includes an equipment database 11 that stores equipment information on equipment that can be the target of prediction and its related equipment. The memory unit 1 also includes a regional information database 12 that stores service demand-related data and corrosion-related data for the region where the equipment is located or the region where the equipment is being constructed. In the regional information database 12, service demand-related data and corrosion-related data are generated for each arbitrary region to be evaluated. The memory unit 1 includes areas that store information generated by each functional unit, such as the predictor.

[0020] The construction unit 2 is a predictor construction unit and a functional unit that generates an equipment quantity predictor and a corrosion predictor. The construction unit 2 generates an equipment quantity predictor by performing machine learning based on the equipment information and service demand-related data stored in the storage unit 1. The construction unit 2 generates a corrosion predictor by performing machine learning based on the equipment information and corrosion-related data stored in the storage unit 1. The construction unit 2 can function at any timing independent of the flow of the prediction process as long as the equipment database 11 and the regional information database 12 are stored in the storage unit 1. Specifically, by the construction unit 2 preparing each predictor in advance, the prediction unit 4 can quickly perform predictions utilizing a wide range of equipment information and regional information.

[0021] The input unit 3 is a functional unit that selects a facility to be predicted and a prediction target area. The input unit 3 selects a facility displayed on a map or a list, etc., and refers to the information of the facility, or selects the selected facility as the prediction target facility. The input unit 3 extracts the prediction target area to which the facility belongs.

[0022] The prediction unit 4 is a functional unit that predicts the facility quantity and the corrosion degree. The prediction unit 4 calculates the predicted facility quantity using the service demand-related data stored in the memory unit 1 and the facility quantity predictor in response to the selection of a prediction target area in the input unit 3. By calculating the predicted facility quantity, the prediction unit 4 can present a maintenance guideline that takes into account the facility quantity that will be required in the relevant area in the future or the magnitude of the social impact. The prediction unit 4 calculates the corrosion degree of the facility using the facility information, corrosion-related data, and corrosion predictor stored in the memory unit 1 in response to the selection of the prediction target facility in the input unit 3. By calculating the corrosion degree of the facility, the prediction unit 4 can present a maintenance guideline that takes into account the operation required for the maintenance of the facility and spare facilities.

[0023] The determination unit 5 is a functional unit that determines the maintenance guidelines. The determination unit 5 may determine the inspection frequency of the equipment in question based on the corrosion level of the equipment acquired from the prediction unit 4. The determination unit 5 may determine the priority of repairs and updates for the area in question based on the predicted equipment quantity and corrosion level of the equipment acquired from the prediction unit 4. The determination unit 5 may determine the amount of updates and construction for the area in question based on the predicted equipment quantity and corrosion level of the equipment acquired from the prediction unit 4.

[0024] The output unit 6 is a functional unit that displays the information stored in the memory unit 1 and the prediction results or judgment results. The output unit 6 outputs any information based on location information for the information stored in the memory unit 1, such as the facility database 11 and the local information database 12, to a map or a file. The output unit 6 outputs any information based on location information for the prediction results or judgment results to a map or a file.

[0025] The storage unit 1 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The semiconductor memory is, for example, a RAM, a ROM, or a flash memory. "RAM" is an abbreviation for random access memory. "ROM" is an abbreviation for read only memory. RAM is, for example, an SRAM or a DRAM. "SRAM" is an abbreviation for static random access memory. "DRAM" is an abbreviation for dynamic random access memory. ROM is, for example, an EEPROM. "EEPROM" is an abbreviation for electrically erasable programmable read only memory. Flash memory is, for example, an SSD. "SSD" is an abbreviation for solid-state drive. Magnetic memory is, for example, an HDD. "HDD" is an abbreviation for hard disk drive. The storage unit functions, for example, as a main storage device, an auxiliary storage device, or a cache memory.

[0026] The functions of the construction unit 2, input unit 3, prediction unit 4, determination unit 5, and output unit 6 are performed by a control unit. The control unit includes, for example, one or more general-purpose processors including a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). The control unit may include one or more dedicated processors specialized for specific operations. Instead of including a processor, the control unit may include one or more dedicated circuits. The dedicated circuits may be, for example, an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). The control unit may include an ECU (Electronic Control Unit). The control unit controls the communication unit to send and receive any information.

[0027] The processes executed by the functional units of the information processing device D will be described.

[0028] 2 shows a map of areas A1 to A9 in which facilities S1 to S4 and manholes M1 to M5 are installed. As an example, facilities S1 to S4 are conduits that house communication cables.

[0029] The equipment database 11 allows data to be extracted for each piece of equipment. The equipment database 11 stores equipment information associated with each piece of equipment. The equipment information includes at least one of the following information: Location information (line) Connected equipment information Pipe type Number of pipes Joint type Length Construction year Past inspection results (e.g., repair defects)

[0030] In the regional information database 12, it is possible to extract data for each area to be evaluated (for example, size L[m]×L[m]). In the regional information database 12, service demand-related data and corrosion-related data are stored in association with each area. The service demand-related data includes at least one of the following information: Area information (polygon) (i.e., location information) Population, population density Number of employees Land use type, its area Use zone, its building area Energy consumption Number of other services used

[0031] The corrosion-related data includes at least one of the following information: Area information (polygon) (i.e., location information), Water system (river basin), Surrounding soil, Surrounding surface geology, Micro-topography, Elevation, Average precipitation, Average temperature

[0032] The input unit 3 selects any facility as the prediction target facility from the facilities included in the facility information. The input unit 3 extracts, as the prediction target area, an area that most requires the function of the prediction target facility based on the location information or connected facilities of the selected prediction target facility. For example, in this embodiment, area A5, in which manhole M4, which is the connected facility of facility S2, is installed, is the region that most requires the function of facility S2. The input unit 3 sets area A5 as the prediction target area.

[0033] [Construction of an equipment quantity predictor] Fig. 3 shows a map of areas A1 to A9 in which equipment T1 to T4 and manholes M1 to M5 are installed. As an example, equipment T1 to T4 here are communication cables housed in equipment S1 to S4 shown in Fig. 2.

[0034] The construction unit 2 combines the facility information and the service demand-related data based on their location information. Here, the facility information may be information associated with another facility (here, a communication cable) that is located at a position corresponding to (for example, the same position as) the facility to be predicted (here, a pipeline) and that is more closely linked to the demand in the area. The facility information does not have to be the same type of facility (here, a pipeline) as the facility to be predicted. The construction unit 2 performs the above combination for each facility and generates learning data for facility quantity prediction. In the learning data for facility quantity prediction, the facility information for facility T1 is combined with the service demand-related data for area A3. The service demand-related data for facility T2 is combined with the service demand-related data for area A5. The service demand-related data for facility T3 is combined with the service demand-related data for area A8.

[0035] The construction unit 2 performs machine learning based on the learning data for facility quantity prediction, and generates a facility quantity predictor that can calculate the predicted facility quantity for a corresponding area from the service demand-related data. In the machine learning, information on the number of lines in use, which is included in the facility information, is used as information indicating the facility quantity. In other words, the facility quantity predictor is a function of the service demand-related data.

[0036] As an additional example or alternative example, the construction of the equipment quantity predictor may be performed in an area that does not include the prediction target equipment and the prediction target area. In this case, equipment information of equipment other than the prediction target equipment is stored in association with the prediction target equipment in the storage unit 1. Service demand-related data for an area other than the prediction target area is stored in association with the prediction target area in the storage unit 1. The equipment information and the service demand-related data are used to construct the equipment quantity predictor. By performing a statistical approach using the predictor, it is possible to calculate predicted equipment quantities even for areas where no equipment actually exists.

[0037] [Construction of a corrosion predictor] The construction unit 2 combines equipment information and corrosion-related data based on their location information. The construction unit 2 performs the combining for each piece of equipment to generate learning data for corrosion prediction. In the learning data for corrosion prediction, equipment information for equipment S1 is combined with service corrosion-related data for area A3. Equipment information for equipment S2 is combined with corrosion-related data for area A5. Equipment information for equipment S3 is combined with corrosion-related data for area A8.

[0038] The construction unit 2 performs machine learning based on the learning data for corrosion prediction and constructs a corrosion predictor that can predict the corrosion level of equipment from information related to the progression of corrosion. In machine learning, as an example, information on past inspection results included in the equipment information is used as information indicating the corrosion level of the equipment. The corrosion-related data and information on the pipe type and construction year included in the equipment information are used as information related to the progression of corrosion. The corrosion level of the equipment is a function of the information related to the progression of corrosion.

[0039] Additionally or alternatively, the construction of the corrosion predictor may be performed in an area that does not include the prediction target equipment and prediction target area. In this case, equipment information of equipment other than the prediction target equipment is stored in association with the prediction target equipment in the memory unit 1. Corrosion-related data of an area other than the prediction target area is stored in association with the prediction target area in the memory unit 1. The equipment information and the corrosion-related data are used to construct the corrosion predictor. By performing a statistical approach using the predictor, it is possible to calculate the corrosion level of equipment even in areas where no equipment actually exists.

[0040] [Facility Capacity Prediction] The prediction unit 4 inputs service demand-related data for the prediction target area into the facility capacity predictor and calculates the predicted facility capacity required in the prediction target area. Here, if the facility type differs between the facility to be predicted and the facility capacity predictor, the prediction unit 4 converts the facility type using a conversion formula. By providing a conversion process, even if the facility to be predicted is one that is not easily linked directly to demand, the predicted facility capacity can be predicted using facility information for other facilities that are more easily linked to demand. This allows the prediction unit 4 to calculate the facility capacity that will be required in the relevant area in the future. For example, while an increase in the number of communication users results in an increase in the number of communication lines (e.g., communication cables), this does not necessarily mean an increase in the number of communication lines. In this case, when using service demand-related data for the surrounding area, the prediction unit 4 predicts the facility capacity based on information about the communication lines. As an example of a conversion method, a conversion formula derived from the relationship between the facility specifications, etc., of facility S and facility T can be used. Specifically, regarding the number of optical cable lines that can be accommodated in a conduit, there is a limit to the number of optical cable lines that can be accommodated in one conduit. Based on this relationship, the prediction unit 4 may perform conversion using the following conversion formula: predicted facility capacity (i.e., number of conduits) = predicted facility capacity (i.e., number of lines in use) / number of lines in use that can be accommodated per conduit

[0041] For example, the prediction unit 4 inputs service demand-related data for the prediction target area (area A5) into the equipment quantity predictor and calculates the predicted equipment quantity of the communication cable (equipment T2) housed in the prediction target equipment (equipment S2).

[0042] [Prediction of Corrosion Degree] The prediction unit 4 inputs information related to the progress of corrosion to a corrosion predictor, and calculates the corrosion degree of the equipment as the prediction target equipment.

[0043] [Determination of Maintenance Guidelines] The determination unit 5 can perform the following three determinations for the equipment to be predicted. Each determination is independent. The determination unit 5 can arbitrarily select the determination to be performed.

[0044] 1. Determination of Inspection Frequency As shown in Fig. 4, the determination unit 5 determines the future inspection frequency based on the corrosion level of the equipment. The determination unit 5 realizes economical operation taking into account the deterioration and failure rate of the equipment. Specifically, if the determination unit 5 determines that the corrosion level of the equipment is higher than the reference value, it sets the inspection frequency higher. If the determination unit 5 determines that the corrosion level of the equipment is lower than the reference value, it sets the inspection frequency lower.

[0045] 2. Determining the Priority of Repairs and Updates The determination unit 5 compares the current equipment capacity with the predicted equipment capacity to determine the priority of repairs and updates. The determination unit 5 realizes repair and update operations that take into account economy and responsiveness. Specifically, when the determination unit 5 determines that the current equipment capacity≦predicted equipment capacity holds, it determines that there is expected to be a shortage of equipment in the future, and sets a high priority for repairs and updates.

[0046] On the other hand, if the determining unit 5 determines that the current equipment capacity is greater than the predicted equipment capacity, it determines that the amount of unused equipment is expected to increase in the future, and sets the priority of repair and renewal low.

[0047] Additionally or alternatively, the determination unit 5 can perform a comparison taking into consideration the deterioration and failure rate of the equipment by multiplying the predicted equipment capacity by a coefficient α. Here, the coefficient α may be calculated from "safety coefficient × equipment failure rate" if the equipment failure rate, etc. is known, or may be calculated from "safety coefficient × corrosion level of the equipment" in other cases.

[0048] 5, the determination unit 5 determines the priority of repairs and upgrades based on whether the following relationship holds: Current facility capacity≦Predicted facility capacity×α and whether the current facility capacity is higher than the reference value. The determination unit 5 realizes operations that minimize the social impact of service outages.

[0049] 3. Determination of the Amount of Renewal and Construction The determination unit 5 determines the amount of equipment to be renewed and constructed in the future by multiplying the predicted equipment amount by α as in the following formula: Amount of Equipment to be Renewed and Constructed = Predicted Equipment Amount × α Here, the method for calculating α may be the same as the method for calculating α in the above "Determination of Priority of Repair and Renewal."

[0050] 6 illustrates a flowchart of processing executed by the input unit 3 of the information processing device D. In S1, the input unit 3 selects an arbitrary facility as a prediction target facility from the facilities included in the facility information. In S2, the input unit 3 extracts, as a prediction target area, an area that most requires the functions of the prediction target facility based on the location information of the selected prediction target facility or the connected facilities and service demand related data, etc.

[0051] 7 illustrates a flowchart of the processing executed by the construction unit 2. This processing is independent of the input unit 3 or the prediction unit 4, and may be executed regardless of the processing of selecting a prediction target executed by the input unit 3. This processing needs to be executed before the prediction unit 4 predicts the facility capacity.

[0052] In S11, the construction unit 2 combines the facility information and the service demand-related data based on their respective location information to generate learning data for facility quantity prediction. In S12, the construction unit 2 performs machine learning based on the learning data for facility quantity prediction to generate a facility quantity predictor that can calculate the predicted facility quantity for the relevant area from the service demand-related data. The construction unit 2 stores the data of the facility quantity predictor in the storage unit 1.

[0053] 8 illustrates a flowchart of the process executed by the construction unit 2. This process is independent of the input unit 3 and the prediction unit 4, and may be executed regardless of the process of selecting a prediction target executed by the input unit 3. This process must be executed before the prediction unit 4 predicts the corrosion degree.

[0054] In S21, the construction unit 2 combines the facility information and the corrosion-related data based on their respective location information to generate learning data for corrosion prediction. In S22, the construction unit 2 performs machine learning based on the learning data for corrosion prediction to generate a corrosion predictor that can calculate the corrosion level of the facility from information related to the progression of corrosion. The construction unit 2 stores the corrosion predictor in the memory unit 1.

[0055] 9 is a flowchart of the process executed by the prediction unit 4. This process can be executed after the prediction target area is identified by the input unit 3 and the facility quantity predictor is constructed by the construction unit 2.

[0056] In S31, the prediction unit 4 inputs service demand-related data for the prediction target area into the facility quantity predictor to calculate the predicted facility quantity for the prediction target area. In S32, the prediction unit 4 determines whether the facility type of the predicted facility quantity calculated by the facility quantity predictor is the same as the facility type of the facility to be predicted. If the answer is No in S32, the prediction unit 4 converts the facility type in S33 using a relational expression for the facility specifications of both facilities. If the answer is Yes in S32, the prediction unit 4 does not execute S33.

[0057] 10 is a flowchart illustrating the process executed by the prediction unit 4. This process can be executed after the equipment to be predicted is identified by the input unit 3 and the corrosion predictor is constructed by the construction unit 2.

[0058] In S41, the prediction unit 4 inputs the equipment information of the equipment to be predicted and the corrosion-related data around the equipment to the corrosion predictor, and predicts the corrosion degree of the equipment to be predicted.

[0059] 11 is a flowchart illustrating the process executed by the determination unit 5. This process can be performed after the predicted facility capacity and the facility corrosion level in the prediction target area are determined.

[0060] In S51, the determination unit 5 determines the inspection frequency using the corrosion degree of the equipment, and outputs the determination result of the inspection frequency.

[0061] In S52, the determination unit 5 determines the priority of repairs and updates using the predicted equipment quantity, the corrosion degree of the equipment, and equipment information of the equipment to be predicted (e.g., the current equipment quantity and failure rate), and outputs the determination result.

[0062] In S53, the determination unit 5 determines the amount of renewal and construction using the predicted equipment amount, the corrosion degree of the equipment, or the equipment information of the prediction target (for example, the failure rate), and outputs the determination result.

[0063] The above-mentioned determination processes are independent and can be performed individually.

[0064] As described above, according to this embodiment, the information processing device D performs an operation including performing at least one of determining the inspection frequency, determining the priority of repairs and updates, and determining the amount of updates and construction for the equipment to be predicted, based on the predicted equipment volume or the predicted corrosion level. With this configuration, the information processing device D can predict the equipment volume appropriate for the area where the equipment is installed, thereby setting an equipment maintenance policy (e.g., inspection, repair, update) for each area and operating economical maintenance and management of the equipment.

[0065] According to the present embodiment, the operation of the control unit includes extracting, from the equipment information of the equipment, an area that most requires the functions of the equipment to be predicted as the prediction target area. With this configuration, the information processing device D accurately extracts the prediction target area, thereby improving the accuracy of facility quantity prediction.

[0066] Furthermore, according to this embodiment, the facility information includes facility information associated with other facilities located at a location corresponding to the facility to be predicted and linked to demand in the area. In the information processing device D, the operation of the control unit includes predicting the predicted facility capacity using a conversion formula derived from the relationship between the facility specifications when the facility to be predicted and the other facilities are of different types. With this configuration, the information processing device D can improve the accuracy of facility capacity prediction even when the facility to be predicted is not easily linked directly to demand.

[0067] The present disclosure is not limited to the above-described embodiments. For example, two or more blocks shown in the block diagram may be integrated, or one block may be divided. Two or more steps shown in the flowchart may be executed in parallel or in a different order, instead of being executed in chronological order as described, depending on the processing capabilities of the device executing each step, or as needed. Other modifications are possible within the scope of the present disclosure.

[0068] The information processing device D of this embodiment can also be realized by a computer and a program. Furthermore, in the above embodiment, a program that executes all or part of the functions or processing of the information processing device D can be recorded on a computer-readable recording medium or provided via a network. Computer-readable recording media include non-transitory computer-readable media, such as magnetic recording devices, optical discs, magneto-optical recording media, or semiconductor memories. The program can be distributed, for example, by selling, transferring, or lending portable recording media, such as Secure Digital (SD) cards, Digital Versatile Discs (DVDs), or Compact Disc Read Only Memory (CD-ROMs), on which the program is recorded. The program can also be distributed by storing the program in the storage of a server and transmitting the program from the server to another computer via a network. The program can also be provided as a program product. The present disclosure can also be realized as a program executable by a processor. Some or all of the functions of the information processing device D can be realized by a programmable circuit or a dedicated circuit. Some or all of the functions of the information processing device D can be realized by hardware.

[0069] The following additional notes are provided regarding the above-described embodiments.

[0070] (Supplementary Item 1) An information processing device including a control unit, wherein the control unit performs operations including: selecting a prediction target facility, extracting a prediction target area from the prediction target facility, constructing an equipment quantity predictor that predicts a predicted equipment quantity required in the prediction target area based on facility information associated with the prediction target facility and service demand-related data associated with the prediction target area, constructing a corrosion predictor that predicts a corrosion level of the prediction target facility based on the facility information associated with the prediction target facility and corrosion-related data associated with the prediction target area, and performing at least one of determining an inspection frequency, determining a priority of repairs and updates, and determining an amount of updates and construction for the prediction target facility based on the predicted predicted equipment quantity or the predicted corrosion level. (Supplementary Item 2) In the information processing device described in Supplementary Item 1, the operations include extracting an area that most requires the functions of the prediction target facility from the facility information of the prediction target facility as the prediction target area. (Supplementary Item 3) In the information processing device according to Supplementary Item 1 or 2, the facility information includes facility information associated with other facilities that are located at a position corresponding to the facility to be predicted and that are linked to area demand. (Supplementary Item 4) In the information processing device according to Supplementary Item 3, the operation includes predicting the predicted facility amount using a conversion formula derived from a relationship between facility specifications when the facility to be predicted and the other facilities are of different types of facility.

[0071] D. Information processing device

Claims

1. An information processing apparatus including a control unit, wherein the control unit: selects a facility to be predicted; extracts a prediction target area from the facility to be predicted; constructs a facility quantity predictor that predicts the quantity of predicted facilities required in the prediction target area based on the facility information associated with the facility to be predicted and the service demand-related data associated with the prediction target area; constructs a corrosion predictor that predicts the corrosion degree of the facility to be predicted based on the facility information associated with the facility to be predicted and the corrosion-related data associated with the prediction target area; performs at least one of determining an inspection frequency, determining a priority for repair and update, and determining a quantity for update and construction for the facility to be predicted based on the predicted quantity of the predicted facilities or the predicted corrosion degree; An information processing apparatus that executes an operation including the above.

2. The information processing apparatus according to claim 1, wherein the operation includes extracting, as the prediction target area, an area that most requires the function of the facility to be predicted from the facility information of the facility to be predicted.

3. The information processing apparatus according to claim 1, wherein the facility information includes facility information associated with other facilities existing at a position corresponding to the facility to be predicted and interlocking with the demand in the area.

4. The information processing apparatus according to claim 3, wherein the operation includes predicting the quantity of the predicted facilities using a conversion formula derived from the relationship of the facility specifications when the facility types of the facility to be predicted and the other facilities are different.

Images