Infrastructure management device, infrastructure management system, infrastructure management method, and infrastructure management program

Abstract

To provide an infrastructure management device, an infrastructure management system, an infrastructure management method and an infrastructure program capable of monitoring a state of an infrastructure without needing addition of a facility to the infrastructure.SOLUTION: In an infrastructure management system 4, an infrastructure management device 3 includes a management schedule determination unit 32 for determining management contents being contents about management of an infrastructure corresponding to an object in accordance with a type of the object included in a photographic image photographed by a user, and a management schedule output unit 33 for outputting the management contents.SELECTED DRAWING: Figure 1

Description

Technical Field

[0006] , , , ,

[0005] , , , , ,

[0001] The present disclosure relates to an infrastructure management device, an infrastructure management system, an infrastructure management method, and an infrastructure management program for managing infrastructure.

Background Art

[0002] Infrastructure such as rivers and roads is facilities and equipment that form the basis of life. Infrastructure such as rivers and roads is monitored for its environment and condition by administrators. In the case of rivers, not only structures such as levees and floodgates, but also the entire river area, including high-water areas and low waterways, realizes flood control functions, and the entire river area can be considered as infrastructure.

[0003] Patent Document 1 discloses a levee break monitoring method in which an optical fiber cable is laid on a levee, and the change over time in the strain of the laid optical fiber cable is observed with an optical fiber strain measuring device to detect a change in the state of the levee that triggers a levee break.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the levee break monitoring method of Patent Document 1, although the change in the state of the levee can be monitored, it is necessary to lay an optical fiber cable on the levee, and additional equipment is required for the infrastructure.

[0006] The present disclosure has been made in view of the above, and an object thereof is to obtain an infrastructure management device capable of monitoring the state of infrastructure without requiring additional equipment for the infrastructure.

Means for Solving the Problems

[0007] In order to solve the aforementioned problems and achieve the objectives, the infrastructure management device relating to this disclosure is: A data acquisition unit receives a species determination result from a species determination device that determines the species of plants included in images taken by the user of infrastructure. Using the species determination result and data for determining the species of plants to be eradicated, the unit determines whether the plant corresponding to the species determination result is a target for eradication. For plants determined to be targets for eradication, the unit estimates the fruiting period using the species determination result corresponding to that plant and data for determining the fruiting period for each plant species. The unit determines the eradication period to be a certain period before the estimated fruiting period, and sets an eradication work schedule that includes the determined eradication period. A management content determination unit that determines the management content, Extermination work schedule It includes a management content output unit that outputs the following: The species determination device receives the captured image from the user's user terminal device and determines the species based on the comparison result between the captured image and the corresponding image for each plant species. [Effects of the Invention]

[0008] The infrastructure management device described herein has the effect of being able to monitor the status of the infrastructure without requiring the addition of equipment to the infrastructure. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows an example configuration of the infrastructure management system according to Embodiment 1. [Figure 2] Sequence diagram showing an example of processing in the infrastructure management system of Embodiment 1 [Figure 3] A flowchart showing an example of the type determination process in the type determination device of Embodiment 1. [Figure 4] A flowchart showing an example of processing in the infrastructure management device of Embodiment 1. [Figure 5] A diagram showing an example of data for determining the timing of extermination in Embodiment 1. [Figure 6] This figure shows an example of the target determination result stored in the result storage unit of Embodiment 1. [Figure 7] A schematic diagram showing an example of a section, which is a unit of work area in Embodiment 1. [Figure 8] This figure shows an example of the determination result for the type of captured data that was determined to be protected in Embodiment 1. [Figure 9] This figure shows an example configuration of the pest control timing determination unit in Embodiment 1 when using machine learning to estimate the fruiting period. [Figure 10] A schematic diagram illustrating an example of a neural network. [Figure 11]Figure showing a configuration example of a computer system that realizes the infrastructure management device of Embodiment 1 [Figure 12] Figure showing a configuration example of the infrastructure management system of Modification 1 in Embodiment 1 [Figure 13] Figure showing a configuration example of the infrastructure management system of Modification 2 in Embodiment 1 [Figure 14] Sequence diagram showing an example of processing in the infrastructure management system of Modification 2 of Embodiment 1 [Figure 15] Figure showing a configuration example of the infrastructure management system according to Embodiment 2 [Figure 16] Flowchart showing an example of processing in the infrastructure management device of Embodiment 2 [Figure 17] Figure showing a configuration example of the infrastructure management system according to Embodiment 3 [Figure 18] Flowchart showing an example of the determination process of the recommended shooting location in Embodiment 3 [Figure 19] Figure showing an example of the recommended shooting location in Embodiment 3

Modes for Carrying Out the Invention

[0010] Hereinafter, an infrastructure management device, an infrastructure management system, an infrastructure management method, and an infrastructure management program according to an embodiment will be described in detail based on the drawings.

[0011] Embodiment 1. FIG. 1 is a diagram showing a configuration example of an infrastructure management system according to Embodiment 1. The infrastructure management system 4 of the present embodiment acquires shooting data shot by a user from the user terminal device 1, and manages the infrastructure using the acquired shooting data. In the present embodiment, an example in which the infrastructure to be managed by the infrastructure management system 4 is a river will be described, but the infrastructure to be managed is not limited to a river, and may be other infrastructure such as a road or power facilities. In FIG. 1, one user terminal device 1 is shown, but the number of user terminal devices 1 is not limited, and one or more may be used.

[0012] Furthermore, user terminal device 1 may be managed or owned by the same administrator as infrastructure management device 3. The following describes an example where a general user, separate from the administrator of infrastructure management device 3, manages or owns user terminal device 1. Additionally, infrastructure management system 4 may acquire photographic data captured by a drone or vehicle-mounted camera and use it for infrastructure management, without going through user terminal device 1.

[0013] In this embodiment, the infrastructure management system 4 collects image data of the infrastructure taken by the user, such as images of plants and animals in a river. Animals include insects, amphibians, reptiles, and birds. Based on the image data taken by the user, the infrastructure management system 4 determines the species of organisms present in the river. This allows river managers to manage the river environment and flood control functions. Furthermore, if plants or animals to be eradicated are present in the river, the infrastructure management system 4 creates a schedule for eradication work. The river is defined as at least a part of a river area, including, for example, floodplains, low-water channels, and embankments.

[0014] In rivers, invasive plant species are eradicated from the perspectives of flood control, maintaining water utilization functions, and environmental protection. For example, the invasive black locust (Robinia pseudoacacia) forms tall forests in river channels, obstructing the safe flow of floodwaters. It can also cause further obstruction of flow by becoming driftwood. The invasive species Chinese hawkweed (Epipogium aquilinum), when densely growing in gravel riverbeds, promotes sand deposition, leading to forest formation and obstructing the safe flow of floodwaters. Furthermore, the invasive water hyacinth (Eichhornia crassipes) and duckweed (Dicranopteris erythrosora) cover the water surface, obstructing water flow, and when they die and decompose, they cause water quality deterioration. In addition, invasive woody plants and deep-rooted herbaceous plants can invade and proliferate on embankment slopes, weakening the embankments. Moreover, the presence of invasive species can hinder the growth of native species, so eradication of invasive species is also carried out from an environmental protection perspective. The targets for eradication are, for example, invasive species, but are not limited to them; any species whose eradication is desirable from the standpoint of flood control, maintenance of water utilization functions, or environmental protection is acceptable.

[0015] Furthermore, the eradication of invasive plant species must be carried out at an effective time. For example, if invasive plant species are eradicated after fruiting, it may actually spread the seeds and exacerbate the damage, and the work required to prevent seed dispersal, such as burning the seeds, will increase. Therefore, in order to carry out eradication work efficiently, it is desirable to understand what types of plants are present in the river and to determine the most effective time for eradication as accurately as possible. Specific examples of effective times include a certain period after germination. In this embodiment, by acquiring photographic data taken by the user from the user terminal device 1 and using it for river management, infrastructure management can be achieved without requiring monitoring by workers or adding equipment to the infrastructure itself, such as laying fiber optic cables. Below, an example of using the fruiting period as an effective time for eradication work will be described, but the effective time for eradication work may be a certain period after germination or other times, or it may be both the fruiting period and other times. Even when the effective time for eradication work is other than the fruiting period, the same processing can be performed as when the effective time for eradication work is the fruiting period.

[0016] Furthermore, monitoring and extermination may be carried out not only for plants but also for animals. In this case, the infrastructure management system 4 may similarly determine the type of animal and create a management schedule for the extermination of the target animal. In other words, plants are just one example of objects to be monitored in infrastructure management, and the objects are, for example, at least one of plants and animals. Moreover, the infrastructure management system 4 of this embodiment can also be applied when the managed object is infrastructure other than rivers. For example, when the managed infrastructure is a road, extermination of plants and animals may be carried out to maintain the function of the road, ensure convenience, and protect the environment. Also, power towers and power lines, which are power facilities, may affect plants or animals, and extermination of plants and animals may be carried out to avoid such effects. The infrastructure to which the infrastructure management system 4 of this embodiment can be applied is not limited to these.

[0017] River administrators should, for example, inform users in advance that they are collecting photographic data of the river. This notification can be posted on a webpage, displayed on posters or flyers in public places, or by any other method.

[0018] User terminal device 1 is a terminal device managed by the user, such as a smartphone, mobile phone, tablet, or personal computer. User terminal device 1 includes an imaging unit 11 and an imaging data output unit 12. The imaging unit 11 is a camera or the like, which captures images and outputs the imaging data obtained from the imaging to the imaging data output unit 12. The imaging data output unit 12 transmits the imaging data to the infrastructure management system 4.

[0019] The shooting data is data that represents the captured image, and the shooting data is accompanied by information indicating the location and date and time of shooting. The addition of the shooting location and date and time may be performed by the shooting unit 11 or by a function unit not shown in the user terminal device 1. The shooting date and time may be determined using the date and time management function of the user terminal device 1 or may be entered by the user. If the user terminal device 1 has a location detection unit that detects the current location, such as a GPS (Global Positioning System) receiver, the current location detected by the location detection unit can be used as the shooting location. Alternatively, the shooting location may be entered by the user. In Figure 1, an example is shown in which the user terminal device 1 is equipped with the shooting unit 11, but the user may take a picture using a shooting device such as a camera separate from the user terminal device 1, and the user terminal device 1 will acquire the shooting data from the shooting device and transmit the acquired shooting data to the infrastructure management system 4. In this case, if the shooting data taken by the shooting device is acquired by the user terminal device 1 without delay after shooting, at least one of the shooting date and time and shooting location may be added by the shooting device.

[0020] As shown in Figure 1, the infrastructure management system 4 comprises a type determination device 2 and an infrastructure management device 3. A user terminal device 1 may also be included in the infrastructure management system 4. The type determination device 2 comprises a shooting data acquisition unit 21, a type determination unit 22, a type notification unit 23, and a type data storage unit 24.

[0021] The image data acquisition unit 21 acquires image data by receiving it from the user terminal device 1 and outputs the acquired image data to the species determination unit 22. The species data storage unit 24 stores species determination data, which is data for determining the species of plants contained in the image shown by the image data. The species determination data is, for example, an image corresponding to each species. The species data is not limited to this and may be a trained model for determining species from image data. The trained model is generated by machine learning. Supervised learning can be used as the machine learning method, but is not limited to this.

[0022] The species determination unit 22 uses the captured data to determine the species of the object contained in the captured image. Specifically, it uses the species determination data stored in the species data storage unit 24 to determine the species of the plant contained in the image indicated by the captured data received from the captured data acquisition unit 21, and outputs the species determination result, which is the species determination result, to the species notification unit 23 along with the corresponding captured data. Hereinafter, the plant contained in the image indicated by the captured data, that is, the plant contained in the image captured by the capture corresponding to the captured data, will also be referred to as the plant contained in the captured data. For example, if the species determination data consists of images for each species, the species determination unit 22 compares the captured data with the images for each species, and by comparing them with the images to which the species is associated, it determines the species of the plant contained in the captured data.

[0023] The species notification unit 23 notifies the infrastructure management device 3 of the species determination result received from the species determination unit 22 by transmitting the species determination result to the infrastructure management device 3. As described above, an example of determining the species of a plant has been explained here, but similarly, when determining the species of an animal, the species data storage unit 24 stores data for species determination to identify the species of the animal, and the species determination unit 22 uses the data for species determination stored in the species data storage unit 24 to determine the species of the animal included in the image shown by the image data received from the image data acquisition unit 21. The species notification unit 23 transmits the corresponding image data along with the species determination result to the infrastructure management device 3. The species notification unit 23 does not need to transmit the image data if the image data is not being used by the infrastructure management device 3. Alternatively, the species notification unit 23 may not transmit the image data to the infrastructure management device 3, but instead transmit information indicating the shooting location corresponding to the image data, or information indicating the shooting date and location corresponding to the image data. The shooting date and location corresponding to the image data are added to the image data as described above. The captured data may be transmitted from the user terminal device 1 to the infrastructure management device 3. Furthermore, the captured data is not limited to that transmitted from the user terminal device 1 as described above; it may also be captured by a camera mounted on a drone or vehicle.

[0024] As shown in Figure 1, the infrastructure management device 3 comprises a data acquisition unit 31, a management schedule determination unit 32, and a management schedule output unit 33. The data acquisition unit 31 receives the captured data and the corresponding type determination result from the type determination device 2, acquires the captured data and type determination result, and outputs the acquired captured data and type determination result to the management schedule determination unit 32. The management schedule determination unit 32 determines the management content, which is the content related to the management of the infrastructure corresponding to the object, according to the type of object included in the captured image taken by the user. decisionThis is a department. Below, we will describe an example in which the management content includes a management schedule, but the management content is not limited to a management schedule; it may also include the content of the work, or other things. The management schedule determination unit 32 determines the river management schedule using, for example, the photographic data and type determination results received from the data acquisition unit 31, and outputs the determined management schedule to the management schedule output unit 33.

[0025] As shown in Figure 1, the management schedule determination unit 32 includes a control target determination unit 321, a result storage unit 322, a control timing determination unit 323, a work location determination unit 324, a schedule determination unit 325, a control type data storage unit 326, and a control timing data storage unit 327. The control type data storage unit 326 stores control type data indicating the type of plant to be controlled. The control type data may be input to the infrastructure management device 3 by an input means (not shown) and stored in the control type data storage unit 326, or it may be received from another device (not shown) and stored in the control type data storage unit 326. The control type data is pre-stored in the control type data storage unit 326, but it may be updated. Details of the types of plants to be controlled will be described later.

[0026] The pest control target determination unit 321 uses the species determination result, that is, the species of the target object included in the captured image, to determine whether or not the target object is a target for pest control. In detail, the pest control target determination unit 321 receives the captured data and species determination result from the data acquisition unit 31, and determines whether the species of plant included in the captured data is a target for pest control based on the species determination result and the pest control species data stored in the pest control species data storage unit 326. If the pest control target determination unit 321 determines that the target object is a target for pest control, it stores the corresponding species determination result, along with the date and time of shooting and the shooting location (information indicating the date and time of shooting and the shooting location) included in the captured data, as the target determination result in the result storage unit 322. The pest control target determination unit 321 may also store the captured data itself corresponding to the species determination result in the result storage unit 322. Alternatively, the pest control type data storage unit 326 may store protection type data, which indicates the type of plant to be protected, and the pest control target determination unit 321 may determine whether the type of plant included in the photographed data is a protected plant based on the type determination result and the protection type data stored in the pest control type data storage unit 326.

[0027] The extermination timing data storage unit 327 stores extermination timing data, which is data used to determine the extermination timing. The extermination timing determination unit 323 determines the extermination timing based on the extermination timing data stored in the extermination timing data storage unit 327 and the target judgment results stored in the result storage unit 322, and stores the determined extermination timing as a target judgment result in the result storage unit 322. The extermination timing determination unit 323 stores the extermination timing as a target judgment result in the result storage unit 322 by, for example, adding the extermination timing to the target judgment results stored in the result storage unit 322. The work location determination unit 324 determines the work location based on the shooting location in the target judgment results stored in the result storage unit 322, and stores the determined work location as a target judgment result in the result storage unit 322. The work location determination unit 324 stores the work location as a target judgment result in the result storage unit 322 by, for example, adding the work location to the target judgment results stored in the result storage unit 322. The work area may be the same as the filming location, or the river under management may be divided into multiple sections in advance, and the section including the filming location may be designated as the work area.

[0028] The schedule determination unit 325 determines a management schedule using the target determination results stored in the result storage unit 322 and outputs the determined management schedule to the management schedule output unit 33. The management schedule is, for example, a work schedule (extermination work schedule) for extermination work on plants to be exterminated. The management schedule is not limited to this and may also be a work schedule related to the protection of plants to be protected. The work related to protection may be, for example, the work of managing where the plants to be protected are located, and may also be the work of creating or updating management information that shows where each type of plant to be protected is located. For example, when the determination result that a plant is to be protected is stored in the result storage unit 322, the work schedule may be determined to create or update the management information. Alternatively, for protected plants, no work schedule may be created, and the fact that the determination result of the type of plant to be protected, the shooting location, and the shooting date and time are stored in the result storage unit 322 as the target determination result may itself be considered the work related to protection.

[0029] If the type determination device 2 transmits a type determination result to the infrastructure management device 3 each time it receives a single image data, and the infrastructure management device 3 determines a management schedule each time it receives a type determination result, the work location and extermination timing included in the target determination result may be used as the management schedule as is. Alternatively, the timing for determining the management schedule may be predetermined, and when the timing for determining the management schedule arrives, the schedule determination unit 325 may determine the management schedule using one or more target determination results stored in the result storage unit 322. The timing for determining the management schedule may be at predetermined intervals, at the time when a certain number of new target determination results have been stored, or at any other time.

[0030] The management schedule output unit 33 outputs the management schedule received from the management schedule determination unit 32. The management schedule output unit 33 may output the management schedule by, for example, displaying the management schedule, or by sending the management schedule to a terminal device that does not display the management schedule. When the management schedule is sent to a terminal device, the terminal device displays the management schedule. Infrastructure administrators and workers who perform infrastructure maintenance can understand the management schedule by checking the management schedule displayed on the infrastructure management device 3 or the terminal device.

[0031] Next, the operation of this embodiment will be described. Figure 2 is a sequence diagram showing an example of processing in the infrastructure management system 4 of this embodiment. As shown in Figure 2, the user terminal device 1 transmits the shooting data, including the date and time of shooting and the location of shooting, to the type determination device 2 (step S1).

[0032] The species determination device 2 performs species determination (step S2). Specifically, the species determination device 2 determines the species of the plant contained in the received photographic data. Details of the species determination will be described later. The species determination device 2 transmits the photographic data and the species determination result to the infrastructure management device 3 (step S3).

[0033] The infrastructure management device 3 performs a determination of whether the target is for extermination (step S4). Specifically, the infrastructure management device 3 determines whether the type indicated by the type determination result received from the type determination device 2 is a target for extermination. Details of the determination of whether the target is for extermination will be described later. As mentioned above, in step S4, the infrastructure management device 3 may also determine whether the type indicated by the type determination result received from the type determination device 2 is a target for protection. Alternatively, it may determine whether it is a target for extermination and then determine whether it is a target for protection.

[0034] Next, the infrastructure management device 3 determines the timing and location of the extermination (step S5). Specifically, the infrastructure management device 3 uses the photographic data corresponding to the type determination result that has been determined to be the target of extermination to determine the timing and location of the extermination.

[0035] Next, the infrastructure management device 3 determines the management schedule (step S6). Specifically, the infrastructure management device 3 determines the management schedule using the determined extermination timing and work location.

[0036] As described above, the user uses the user terminal device 1 to photograph a river, which is an example of infrastructure managed by the infrastructure management system 4. The infrastructure management system 4 collects photographic data corresponding to the images of the river taken by the user. A system may be in place to reward users who cooperate in collecting photographic data. For example, a user who transmits photographic data from the user terminal device 1 to the infrastructure management system 4 may be given points. Alternatively, multiple categories of data to be collected may be defined in advance, and users may gain a sense of satisfaction and accomplishment by taking photographic data corresponding to the defined categories. The categories may be plant species or locations. For example, the infrastructure management system 4 may define multiple plant species as targets for collection in advance and present images of each of the multiple plant species. This encourages users to take images of as many plant species as possible from among the multiple species. Alternatively, the infrastructure manager may divide the river into locations and similarly present the location categories to the user. This encourages users to take images of as many locations as possible from among the multiple location categories.

[0037] Furthermore, the infrastructure management system 4 may notify the user terminal device 1 of the determination result for the type corresponding to the user terminal device 1. The infrastructure management system 4 may also store the determination result for the type and the shooting location for each user, and may award points or other rewards to users who send shooting data corresponding to all of multiple categories, or a predetermined number of categories, from the user terminal device 1. For example, when a user sends shooting data to the infrastructure management system 4 for the first time using the user terminal device 1, the user may register user identification information that identifies the user through user registration, and the infrastructure management system 4 may identify the user using the user identification information. The infrastructure management system 4 is not limited to this, and may also identify the user by the identification information of the user terminal device 1. Furthermore, the infrastructure management device 3 may present categories for which shooting data has already been collected and prompt the user to take shooting data for categories for which data has not yet been collected. The processing of presenting various information regarding benefits to these user terminal devices 1 and granting benefits to users may be performed by the infrastructure management device 3, by the type determination device 2, or by a separate device from the type determination device 2 and the infrastructure management device 3, which may perform these processes.

[0038] Next, the operation of the type determination device 2 will be described. Figure 3 is a flowchart showing an example of the type determination process in the type determination device 2 of this embodiment. The type determination device 2 determines whether or not it has acquired photographic data taken by the user from the user terminal device 1 (step S11), and if it has not acquired photographic data (step S11 No), it repeats step S11. In detail, in step S11, the photographic data acquisition unit 21 determines whether or not it has acquired photographic data taken by the user from the user terminal device 1.

[0039] If it determines that image data has been acquired (Step S11 Yes), the type determination device 2 determines the type using the image data and the type determination data stored in the type data storage unit 24 (Step S12). Specifically, if the image data acquisition unit 21 determines that image data has been acquired, it outputs the acquired image data to the type determination unit 22 and the type notification unit 23. The type determination unit 22 then determines the type using the image data and the type determination data stored in the type data storage unit 24, and outputs the type determination result to the type notification unit 23.

[0040] The species data is, for example, images of each plant species. The species determination unit 22 compares the images shown in the captured data with the images of each plant species, and based on the comparison results, determines the species of the plant included in the captured data to be the species corresponding to the image with the highest similarity among the images in the species data. The method for calculating similarity can be any method, for example, a method using AKAZE (Accelerated KAZE) features, a method using a histogram of pixel values, a method using a correlation coefficient, a method using features after frequency transformation, or any other method. The species determination unit 22 may also calculate the similarity of images using a trained model that infers image similarity, generated by machine learning. In this case, the species data consists of images of each species and a trained model. The features used as input in machine learning may be features extracted from the image, or the image itself. Machine learning can be, for example, supervised learning, but is not limited to this. The species determination unit 22 may also generate the trained model, or the trained model may be generated by another learning device not shown.

[0041] Alternatively, instead of a pre-trained model for inferring image similarity, a pre-trained model for inferring type from image features or the image itself may be used. In this case, the type data is the pre-trained model, and the type data does not necessarily include images for each type. In this case as well, the type determination unit 22 may generate the pre-trained model, or the pre-trained model may be generated by another learning device (not shown).

[0042] After step S12, the type notification unit 23 of the type determination device 2 transmits the type determination result along with the captured data to the infrastructure management device 3 (step S13). As described above, instead of the captured data, the type notification unit 23 may transmit to the infrastructure management device 3 information indicating the shooting location corresponding to the captured data, or information indicating the shooting date and time and shooting location corresponding to the captured data.

[0043] Next, the operation of the infrastructure management device 3 will be described. Figure 4 is a flowchart showing an example of processing in the infrastructure management device 3 of this embodiment. The infrastructure management device 3 determines whether or not it has received a type determination result (step S21). In detail, the data acquisition unit 31 determines whether or not it has received a type determination result from the type determination device 2. If a type determination result has not been received (step S21 No), the infrastructure management device 3 repeats step S21.

[0044] If the type determination result is received (Step S21 Yes), the infrastructure management device 3 uses the type determination result and the data for determining the type of extermination stored in the extermination type data storage unit 326 to determine whether the type indicated by the type determination result is a target for extermination (Step S22). In detail, when the type determination result is received, the data acquisition unit 31 outputs the received type determination result to the extermination target determination unit 321, and the extermination target determination unit 321 uses the type determination result and the data for determining the type of extermination stored in the extermination type data storage unit 326 to determine whether the type indicated by the type determination result is a target for extermination. The data acquisition unit 31 also receives the captured data along with the type determination result and outputs the received captured data to the extermination target determination unit 321. The following describes an example in which the infrastructure management device 3 receives captured data, but if the infrastructure management device 3 does not use the image of the captured data itself, as described above, it may receive information indicating the shooting location corresponding to the captured data, or information indicating the shooting date and time and shooting location corresponding to the captured data, instead of the captured data.

[0045] The data used for determining the type of pest to be eradicated is, for example, data indicating the type of pest to be eradicated. The type of pest to be eradicated may be an invasive species. For example, data listing species such as black locust, large-flowered coreopsis, wild cucumber, large rudbeckia, large river vernalis, Chinese hawkweed, tall goldenrod, Japanese honeysuckle, water hyacinth, and water hyacinth is stored in the eradication type data storage unit 326 as data for determining the type of pest to be eradicated. The eradication target determination unit 321 determines that the type indicated by the type determination result is the type to be eradicated if the type determination result matches the type indicated by the eradication type determination data.

[0046] If the result of the determination in step S22 is that the target is to be exterminated (step S23 Yes), the infrastructure management device 3 stores the determination result as the target determination result (step S24). Specifically, in step S24, the extermination target determination unit 321 extracts the shooting date and time and shooting location attached to the shooting data corresponding to the type determination result that has been determined to be to be exterminated, and stores the type determination result and the extracted shooting date and time and shooting location as the target determination result in the result storage unit 322. The extermination target determination unit 321 also stores the shooting data in the result storage unit 322. Here, the target determination result includes the shooting date and time and shooting location, but the target determination result is not limited to this and may also include the type determination result and information for identifying the corresponding shooting data. Also, if the management schedule is determined each time a type determination result corresponding to one piece of shooting data is received, there is only one piece of shooting data used to determine the management schedule, so the target determination result does not need to include information for identifying the shooting data.

[0047] Next, the infrastructure management device 3 estimates the timing of fruiting using the captured data and the data for determining the timing of pest control stored in the pest control timing data storage unit 327, determines the timing of pest control using the estimation result, and stores the timing of pest control (step S25). In detail, for example, the pest control timing determination unit 323 estimates the timing of fruiting using the target determination result stored in the result storage unit 322 and the data for determining the timing of pest control stored in the pest control timing data storage unit 327, and determines the timing of pest control using the estimation result of the timing of fruiting.

[0048] Figure 5 shows an example of data for determining the timing of pest control in this embodiment. As shown in Figure 5, the data for determining the timing of pest control includes, for example, the fruiting time for each species. In the example shown in Figure 5, the data for determining the timing of pest control also includes the pest control method, but if the pest control method is not species-dependent, the pest control method does not need to be included in the data for determining the timing of pest control. In addition, the pest control method for each species may be stored separately in the infrastructure management device 3 from the data for determining the timing of pest control.

[0049] The extermination timing determination unit 323 extracts the fruiting period for the type corresponding to the target judgment result stored in the result storage unit 322 from the data for determining the extermination timing stored in the extermination timing data storage unit 327, and uses the extracted fruiting period as the estimated fruiting period. The extermination timing determination unit 323 determines the extermination timing to be a period earlier than the estimated fruiting period. For example, it may determine the extermination timing to be a certain period before the fruiting period, such as half a month before the fruiting period. This certain period may be set for each type, or it may be the same value regardless of the type. This certain period may also be input by an administrator or the like to the infrastructure management device 3. For example, if the fruiting period is from June to August, the extermination timing will be determined to be half a month before June 1st, which is the start date of the June-August period. The extermination timing may also be determined with a range. Furthermore, if there are multiple extermination methods, the extermination timing may be determined for each extermination method. Furthermore, since the target determination result stored in the result storage unit 322 is determined based on the photographic data, the estimation of the fruiting period using the target determination result is an example of estimating the fruiting period based on the species determined using the photographic data. In addition, the extermination period determination unit 323 estimates the fruiting period using the target determination result and estimates the extermination period using the estimated fruiting period, thus determining the extermination period based on the species determined using the photographic data.

[0050] In this example, the data for determining the timing of extermination includes the fruiting period for each species, but the data for determining the timing of extermination may also include the timing of extermination for each species. In this case, the extermination timing determination unit 323 will use the data for determining the timing of extermination stored in the extermination timing data storage unit 327 to determine the timing of extermination corresponding to the species indicated by the species determination result.

[0051] The extermination timing determination unit 323 stores the extermination timing in the result storage unit 322 by, for example, adding the determined extermination timing to the target determination result stored in the result storage unit 322. Figure 6 is a diagram showing an example of the target determination result stored in the result storage unit 322 of this embodiment. In the example shown in Figure 6, the target determination result is shown after the extermination timing has been added to the target determination result in step S25. In the example shown in Figure 6, the target determination result includes, for each photographed data, the shooting location, the shooting date and time, the type determination result, the fruiting time (estimated fruiting time), and the extermination timing (the extermination timing determined in step S25). In Figure 6, information corresponding to multiple photographed data is stored as the target determination result, but if the management schedule is determined each time a type determination result corresponding to one photographed data is received, it is sufficient to store information corresponding to one photographed data. Also, if the management schedule is determined each time a type determination result corresponding to one photographed data is received, the type determination result may be passed from the extermination timing determination unit 323 to the work location determination unit 324 without going through the result storage unit 322.

[0052] Furthermore, while this example describes estimating the fruiting time using pre-stored fruiting times for each species, as will be discussed later, the fruiting time may also be estimated using machine learning with photographic data and reference images. In this case, the data used to determine the eradication timing includes the trained model.

[0053] Returning to the explanation of Figure 4, the infrastructure management device 3 then determines the work location based on the shooting location associated with the shooting data and stores the work location (step S26). In detail, for example, the work location determination unit 324 determines the work location based on the shooting location in the target determination result stored in the result storage unit 322, and stores the work location in the result storage unit 322 by adding the determined work location to the target determination result stored in the result storage unit 322. Note that the work location may be the same as the shooting location. In this case, in step S26, the work location may not be newly stored, and the already stored shooting location may be used as the work location.

[0054] Furthermore, the work area may be indicated by a pre-defined section. Figure 7 is a schematic diagram showing an example of a section, which is the unit of the work area in this embodiment. As shown in Figure 7, for example, the river may be pre-divided into sections such as section #1 to #6, and the work area determination unit 324 may determine the section to which the shooting location belongs as the work area. Note that in Figure 7, each section is shown as including both the left and right banks of the river, but for example, the left and right sides of the river may be defined as separate sections, and the definition of a section is not limited to the example shown in Figure 7.

[0055] Returning to the explanation of Figure 4, the infrastructure management device 3 determines whether or not it is time to determine the management schedule (step S27). More specifically, the schedule determination unit 325 determines whether or not it is time to determine the management schedule. For example, if the management schedule is determined periodically, the schedule determination unit 325 determines that it is time to determine the management schedule when the elapsed time since the previous management schedule determination process reaches a predetermined time. Alternatively, for example, the management schedule determination process may be performed each time the infrastructure management device 3 receives a type determination result and processes from step S25 to step S26 are performed, or the management schedule determination process may be performed each time a predetermined number of target determination results corresponding to the shooting data are stored in the result storage unit 322. The timing for determining the management schedule is not limited to these examples and may be determined in any way.

[0056] If it is not the timing to determine the management schedule (step S27 No), the infrastructure management device 3 repeats the process from step S21. If it is the timing to determine the management schedule (step S27 Yes), the infrastructure management device 3 determines the management schedule based on the determined extermination timing and work location (step S28). Specifically, for example, the schedule determination unit 325 determines the management schedule using the work location and extermination timing in the target determination result stored in the result storage unit 322. The management schedule is, for example, a schedule for the extermination of the target plant, and is a schedule that indicates when and where the extermination will be carried out. After the management schedule has been determined, the target determination result stored in the result storage unit 322 may be erased or may remain stored. If the target determination result remains stored in the result storage unit 322, when determining the management schedule in step S28, the management schedule may be determined by referring to the newly added target determination result, and the management schedule may be updated if it is necessary to update an already determined management schedule.

[0057] Furthermore, when determining the management schedule in step S28, if the result storage unit 322 stores the result of the determination of the target of the protected species, as described later, the management schedule may be determined taking into consideration the result of the determination of the target of the protected species. For example, the schedule determination unit 325 may determine the management schedule to prioritize extermination if plants of the protected species are present at or around the extermination work site. Also, if plants of the protected species are present at or around the extermination work site, the schedule determination unit 325 may determine the extermination method to be one that exterminates the target of extermination while protecting the protected plants.

[0058] The infrastructure management device 3 outputs the determined management schedule (step S29) and repeats the process from step S21. Specifically, in step S29, the schedule determination unit 325 notifies the management schedule output unit 33 of the determined management schedule, and the management schedule output unit 33 outputs the management schedule. As described above, the management schedule output unit 33 may display the management schedule, or it may transmit the management schedule to another device that is not shown.

[0059] If the result of the determination in step S22 is not that the target is for extermination (step S23 No), the infrastructure management device 3 uses the type determination result and the data for determining protection type stored in the extermination type data storage unit 326 to determine whether the type indicated by the type determination result is a target for protection (step S30). In detail, the extermination target determination unit 321 uses the type determination result and the data for determining protection type stored in the extermination type data storage unit 326 to determine whether the type indicated by the type determination result is a target for protection. Here, it is assumed that the extermination type data storage unit 326 stores data for determining protection type, in addition to data for determining extermination type, which indicates the type of target for protection.

[0060] The data used for determining the protected species may, for example, be native species. For example, data listing species such as Dianthus superbus, Bupleurum falcatum, and Scutellaria baicalensis is stored in the eradication species data storage unit 326 as data for determining the protected species. The eradication target determination unit 321 determines that the species indicated by the species determination result is a protected species if the species determination result matches the species indicated by the data for determining the protected species.

[0061] If the result of the determination in step S30 is that the target is not subject to protection (step S31 No), the infrastructure management device 3 repeats the process from step S21. If the result of the determination in step S30 is that the target is subject to protection (step S31 Yes), the infrastructure management device 3 stores the determination result and the shooting location associated with the shooting data (step S32), and repeats the process from step S21. Specifically, in step S32, the extermination target determination unit 321 extracts the shooting date and time and shooting location attached to the shooting data corresponding to the type determination result that was determined to be subject to protection, and stores the type determination result and the extracted shooting date and time and shooting location in the result storage unit 322 as the target determination result for the target of protection. Here, the shooting date and time are included in the type determination result, but they do not have to be included.

[0062] Figure 8 shows an example of the type determination result for photographic data that has been determined to be protected in this embodiment. As shown in Figure 8, the type determination result for each photographic data shows the shooting location, shooting date and time, and type determination result. By checking the type determination result for protected items, river managers can manage where protected plants are located and manage the river environment. In addition, when protective work is to be carried out to protect protected items, after step S32, the schedule determination unit 325 creates a work schedule for the protective work as a management schedule using the type determination result for protected items, and then proceeds to step S29, in which step S29 the work schedule for the protective work may also be output. Protective work is an example of management content. Protective work includes, for example, removing pests, mowing surrounding grass to make it easier for native species to grow, and transplanting to propagate. Protective work may be determined by the type of native species. For example, in order to protect Dianthus superbus, pests are eradicated to suppress the occurrence of Dianthus superbus seed weevils that eat the seeds. If the grass is not mowed, tall weeds will grow and destroy the plant, so mowing is performed to protect the plant. Plants such as *Oenothera biennis* are propagated by transplanting plant bodies, but there is an optimal time for transplanting, so transplanting is performed at the appropriate time to protect plants such as *Oenothera biennis*. These protective measures are examples, and protective measures are not limited to these examples. Instead of step S22, the infrastructure management device 3 may perform a determination (step S30) of whether the type indicated by the type determination result is a target for protection, using the type determination result and the data for determining the protection type stored in the eradication type data storage unit 326.

[0063] Next, an example of the pest control timing determination unit 323 estimating the fruiting period using machine learning will be described. Figure 9 is a diagram showing an example of the configuration of the pest control timing determination unit 323 in this embodiment when the fruiting period is estimated using machine learning. In the example shown in Figure 9, the pest control timing determination unit 323 comprises a trained model generation unit 401, an inference unit 402, and a determination unit 403.

[0064] The inference unit 402 reads the trained model stored in the extermination timing data storage unit 327, inputs the captured data to the read trained model to estimate the period until fruiting, and estimates the fruiting time by adding the estimated period until fruiting time to the date and time of capture. The trained model is a trained model for inferring the fruiting time of an object from the captured data, i.e., the captured image, and is generated by the trained model generation unit 401, for example, as follows. Note that the trained model may also be a trained model for estimating the fruiting time from the captured data and the date and time of capture, in which case the fruiting time estimation result can be obtained by inputting the captured data and the date and time of capture to the trained model. A trained model is generated for each species, and the inference unit 402 performs inference using the trained model of the species indicated by the species determination result corresponding to the captured data. Note that here we give an example in which a trained model is generated for each species, but it is not limited to this, and a common trained model may be used regardless of the species by generating a trained model that also takes the species as input data. The decision unit 403 determines the timing of eradication based on the fruiting period estimated by the inference unit 402.

[0065] The trained model generation unit 401 generates a trained model using multiple training datasets, each containing captured data and corresponding ground truth data, and stores the generated trained model in the eradication timing data storage unit 327. The generation of the trained model is performed before the infrastructure management device 3 performs the processing shown in Figure 4. The trained model may be updated after it has been generated by retraining using a new training dataset.

[0066] The photographic data input to the trained model generation unit 401 may be training data acquired by an administrator or worker for training purposes, photographic data taken by a user, or data taken by a worker during pest control work. The ground truth data is the period from when the corresponding photographic data is taken until fruiting occurs. For example, by having an administrator or worker periodically take photographs of the same location from before fruiting until fruiting occurs, ground truth data can be obtained for each photographic data. In addition, if photographic data taken by a user is taken from before fruiting until fruiting occurs, ground truth data can also be obtained from this photographic data, and it can be used as a training dataset.

[0067] The pre-trained model is generated in the pre-trained model generation unit 401 by, for example, supervised learning. Any supervised learning algorithm can be used, but for example, a neural network model can be used. A neural network consists of an input layer made up of multiple neurons, an intermediate layer (hidden layer) made up of multiple neurons, and an output layer made up of multiple neurons. The intermediate layer may be one layer or two or more layers.

[0068] Figure 10 is a schematic diagram illustrating an example of a neural network. For example, in a three-layer neural network like the one shown in Figure 10, when multiple inputs are input to the input layer (X1-X3), these values ​​are multiplied by weights W1 (w11-w16) and input to the hidden layer (Y1-Y2), and the result is further multiplied by weights W2 (w21-w26) and output from the output layer (Z1-Z3). This output result varies depending on the values ​​of weights W1 and W2.

[0069] In this embodiment, the relationship between the captured data and the ground truth data is learned by adjusting weights W1 and W2 so that the output from the output layer when captured data is input approaches the ground truth data. Note that the machine learning algorithm is not limited to neural networks, and may be a support vector machine, a CNN (Convolutional Neural Network), or any other algorithm.

[0070] In the example shown in Figure 9, the extermination timing determination unit 323 includes a trained model generation unit 401. However, a separate learning device for generating trained models may be provided in addition to the infrastructure management device 3, and the learning device may also include a trained model generation unit 401. In this case, the extermination timing determination unit 323 does not need to include a trained model generation unit 401, and the trained model generation unit 401 of the learning device generates the trained model in the same manner as described above. The trained model generated by the learning device is then stored in the extermination timing data storage unit 327 of the extermination timing determination unit 323.

[0071] As mentioned above, the trained model may be updated by retraining, and for retraining, photographic data taken by workers during extermination work and the corresponding ground truth data may be used.

[0072] Furthermore, even when the species determination unit 22 in the species determination device 2 described above determines the species using machine learning, the species determination device 2 includes a trained model generation unit and an inference unit, similar to the extermination timing determination unit 323 shown in Figure 9. In this case, the correct data in the training dataset is the species.

[0073] In the example shown in Figure 4, the work location was determined based on the shooting location corresponding to the shooting data. However, if the eradication work in the managed river is carried out continuously without dividing it into separate work locations, the work location does not need to be determined. In other words, step S26 shown in Figure 4 does not need to be performed. Also, in the example shown in Figure 4, the type of protected object is determined, but processing related to the protected object does not need to be performed. In other words, steps S30 to S32 shown in Figure 4 do not need to be performed.

[0074] The above mainly describes an example of creating a work schedule for plant eradication, but similarly, the infrastructure management system 4 can determine the type of animal and generate an eradication work schedule for the target animal. In the case of animal eradication, the eradication method and location are determined for each type based on the type determined from the photographic data, and the photographic data does not necessarily have to be used to determine the timing of eradication.

[0075] In the example described above, a species determination device 2 and an infrastructure management device 3 are provided, but the infrastructure management device 3 may also have the functions of the species determination device 2. That is, the infrastructure management device 3 may include a shooting data acquisition unit 21 and a species determination unit 22, and the species determination result and shooting data may be output from the species determination unit 22 to the extermination target determination unit 321.

[0076] Next, the hardware configuration of the infrastructure management device 3 in this embodiment will be described. In this embodiment, the infrastructure management device 3 functions as an infrastructure management device 3 when a computer program, which is a computer program describing the processing in the infrastructure management device 3, is executed on the computer system. Figure 11 is a diagram showing an example of the configuration of a computer system that realizes the infrastructure management device 3 in this embodiment. As shown in Figure 11, this computer system comprises a control unit 101, an input unit 102, a storage unit 103, a display unit 104, a communication unit 105, and an output unit 106, which are connected via a system bus 107.

[0077] In Figure 11, the control unit 101 is a processor such as a CPU (Central Processing Unit) and executes a program describing the processing in the infrastructure management device 3 of this embodiment. Note that a part of the control unit 101 may be implemented by dedicated hardware such as a GPU (Graphics Processing Unit) or FPGA (Field-Programmable Gate Array). The input unit 102 consists of, for example, a keyboard and mouse, and is used by the user of the computer system to input various information. The storage unit 103 includes various types of memory such as RAM (Random Access Memory) and ROM (Read Only Memory), as well as storage devices such as a hard disk, and stores the program to be executed by the control unit 101, necessary data obtained during processing, etc. The storage unit 103 is also used as a temporary storage area for the program. The display unit 104 consists of a display, LCD (Liquid Crystal Display Panel), etc., and displays various screens to the user of the computer system. The communication unit 105 is a receiver and transmitter that perform communication processing. The output unit 106 is a printer, speaker, etc. Note that Figure 11 is just one example, and the configuration of the computer system is not limited to the example shown in Figure 11.

[0078] Here, an example of the operation of the computer system until the program of this embodiment becomes executable will be described. In the computer system with the above configuration, for example, a computer program is installed in the storage unit 103 from a CD-ROM or DVD-ROM set in a CD (Compact Disc)-ROM drive or DVD (Digital Versatile Disc)-ROM drive (not shown). When the program is executed, the program read from the storage unit 103 is stored in the main memory area of ​​the storage unit 103. In this state, the control unit 101 performs processing as the infrastructure management device 3 of this embodiment according to the program stored in the storage unit 103.

[0079] In the above explanation, a program describing the processing in the infrastructure management device 3 is provided on a CD-ROM or DVD-ROM as the recording medium. However, the explanation is not limited to this, and depending on the configuration of the computer system, the capacity of the program to be provided, a program provided via a transmission medium such as the Internet via the communication unit 105 may also be used.

[0080] The infrastructure management program of this embodiment causes a computer system to perform, for example, the steps of determining management content, which is content related to the management of infrastructure corresponding to an object, according to the type of object included in a photograph taken by the user, and outputting the management content.

[0081] The pest control target determination unit 321, pest control timing determination unit 323, work location determination unit 324, and schedule determination unit 325 shown in Figure 1 are realized by the execution of a computer program stored in the storage unit 103 shown in Figure 11 by the control unit 101 shown in Figure 11. The storage unit 103 shown in Figure 11 is also used to realize the pest control target determination unit 321, pest control timing determination unit 323, work location determination unit 324, and schedule determination unit 325 shown in Figure 1. The result storage unit 322, pest control type data storage unit 326, and pest control timing data storage unit 327 shown in Figure 1 are part of the storage unit 103 shown in Figure 11. The data acquisition unit 31 shown in Figure 1 is realized by the communication unit 105 shown in Figure 11. The management schedule output unit 33 shown in Figure 1 is realized by at least one of the communication unit 105 and the display unit 104 shown in Figure 11. Furthermore, the infrastructure management device 3 may be realized by multiple computer systems. For example, the infrastructure management device 3 may be realized by a cloud computer system.

[0082] The type determination device 2 is similarly implemented by a computer system with the configuration shown in Figure 11, for example. The user terminal device 1 is similarly implemented by a computer system with the configuration shown in Figure 11, for example. The type determination unit 22 shown in Figure 1 is implemented by the control unit 101 shown in Figure 11 executing a computer program stored in the storage unit 103 shown in Figure 11. The type data storage unit 24 shown in Figure 1 is part of the storage unit 103 shown in Figure 11. The shooting data acquisition unit 21, type notification unit 23, and shooting data output unit 12 shown in Figure 1 are implemented by the communication unit 105 shown in Figure 11. The shooting unit 11 shown in Figure 1 is implemented by a shooting device such as a camera (not shown).

[0083] <Example 1> Next, we will describe the infrastructure management system of Modification 1 in this embodiment. Figure 12 is a diagram showing an example of the configuration of the infrastructure management system of Modification 1 in this embodiment. As shown in Figure 12, the infrastructure management system 4a of Modification 1 in this embodiment is the same as the infrastructure management system 4 shown in Figure 1, except that it is equipped with an infrastructure management device 3a instead of an infrastructure management device 3. Components that have the same functions as the infrastructure management system 4 shown in Figure 1 are denoted by the same reference numerals as in Figure 1, and redundant explanations are omitted. The following will mainly describe the differences from the example shown in Figure 1.

[0084] The infrastructure management device 3a includes a data acquisition unit 31 similar to the example shown in Figure 1, a management schedule determination unit 32a, a management schedule output unit 33 similar to the example shown in Figure 1, and a weather information acquisition unit 34. The management schedule determination unit 32a is the same as the management schedule determination unit 32 in the example shown in Figure 1, except that it includes an extermination timing determination unit 323a instead of an extermination timing determination unit 323.

[0085] The weather information acquisition unit 34 acquires weather information by receiving weather information from the weather information providing device 5 and outputs the acquired weather information to the extermination timing determination unit 323a. The weather information acquisition unit 34 may also acquire weather information by receiving input of weather information from an administrator or worker. The weather information may be, for example, information indicating the weather such as sunny, cloudy, or rainy, or sunshine hours, or a combination of weather information and sunshine hours. The weather information may be, for example, forecast values, but is not limited to this, and may be observed actual values, or a combination of actual values ​​and forecast values. The weather information acquisition unit 34 may acquire weather information periodically, or may receive updated weather information when the weather information is updated. The extermination timing determination unit 323a may, for example, store weather information for a predetermined period of time called the weather reflection period, use the stored information to calculate an index used to estimate the fruiting time, and estimate the fruiting time using the species judgment result, the data for determining the extermination timing, and the calculated index. The weather reflection period may be a predetermined period specified by date, a predetermined future period starting from the present time or the date and time of shooting, or any other period. Furthermore, the weather reflection period may be defined separately for each category.

[0086] For example, if the weather information is sunshine hours, the pest control timing determination unit 323a calculates the cumulative value of sunshine hours for the weather reflection period as an index. Then, in step S25 described above, the pest control timing determination unit 323a corrects the estimated fruiting period using the species determination result and the data for determining the pest control timing stored in the pest control timing data storage unit 327, and determines the pest control timing using the corrected fruiting period. In this way, the pest control timing determination unit 323a estimates an effective timing for pest control, such as the fruiting period, using weather information in addition to species information. For example, if the data for determining the pest control timing includes the fruiting period for each species, since this fruiting period is determined based on standard weather, the cumulative value of sunshine hours for the weather reflection period corresponding to standard weather is set as a reference index, and the estimated result of the fruiting period is corrected using the reference index and the calculated index. The correction method may be to calculate the number of correction days by multiplying the index value calculated from the reference index by a predetermined coefficient, and add the number of correction days to the fruiting period estimated using the data for determining the pest control timing. For example, if the value obtained by subtracting the standard index from the calculated index is negative, it means that the amount of sunshine is longer than the standard index, so the number of corrected days will also be a negative value, and the corrected fruiting period will be earlier than the fruiting period in the data used to determine the eradication period. Note that the correction may also be made based on the ratio of the standard index to the calculated index, and the specific method for determining the number of corrected days from the weather information for the weather reflection period is not limited to these examples. Furthermore, the correction method may be determined for each species. In addition, if the weather information is information indicating the weather such as sunny, cloudy, or rainy, for example, sunny, cloudy, and rainy may each be scored, and the sum of the scores for the weather reflection period may be calculated as the index.

[0087] In the example above, the infrastructure management device 3a uses weather information for the weather reflection period by accumulating weather information, but it is not limited to this, and the weather information acquisition unit 34 may acquire weather information for the weather reflection period each time the fruiting period is estimated. Also, as described above, when using cumulative values ​​as indicators, new information can be added to the calculated indicator, so the weather information used to calculate the indicator may be deleted without being accumulated.

[0088] Furthermore, when the pest control timing determination unit 323a estimates the fruiting period using machine learning, the estimation result obtained by machine learning may be corrected based on weather information, or weather information for the weather reflection period may be added as input data. In the latter case, a trained model is generated by adding weather information as input data, and when estimating the fruiting period, the estimated fruiting period is obtained by inputting the photographic data and weather information for the weather reflection period into the trained model. Alternatively, an index for the weather reflection period described above is calculated, and a trained model is generated by adding the index as input data, and when estimating the fruiting period, the estimated fruiting period is obtained by inputting the photographic data and the index into the trained model.

[0089] The infrastructure management device 3a in the modified example 1 of Embodiment 1 is implemented by a computer system, similar to the infrastructure management device 3. The extermination timing determination unit 323a is implemented by executing a computer program stored in the storage unit 103 shown in Figure 11 by the control unit 101 shown in Figure 11. The storage unit 103 shown in Figure 11 is also used to implement the extermination timing determination unit 323a. The weather information acquisition unit 34 shown in Figure 1 is implemented by the communication unit 105 shown in Figure 11. Furthermore, the infrastructure management device 3a may be implemented by multiple computer systems. For example, the infrastructure management device 3a may be implemented by a cloud computer system. Also, the infrastructure management device 3a may have the function of the type determination device 2.

[0090] In the modified example 1 of Embodiment 1, the timing of fruiting can be estimated by taking weather conditions into consideration, thereby improving the accuracy of the fruiting timing estimation and allowing for a more appropriate scheduling of pest control work.

[0091] <Modification 2> Next, we will describe the infrastructure management system of Modification 2 in this embodiment. Figure 13 is a diagram showing an example of the configuration of the infrastructure management system of Modification 2 in this embodiment. As shown in Figure 13, the infrastructure management system 4b of Modification 2 in this embodiment is the same as the infrastructure management system 4 shown in Figure 1, except that it is equipped with a user terminal device 1a and an infrastructure management device 3b instead of the user terminal device 1 and the infrastructure management device 3. Components that have the same functions as the infrastructure management system 4 shown in Figure 1 are denoted by the same reference numerals as in Figure 1, and redundant explanations are omitted. The following will mainly describe the differences from the example shown in Figure 1.

[0092] Infrastructure management device 3b is the same as infrastructure management device 3 shown in Figure 1, except that a result notification unit 35 is added. User terminal device 1a is the same as user terminal device 1 shown in Figure 1, except that a result acquisition unit 13 and a display unit 14 are added.

[0093] Figure 14 is a sequence diagram showing an example of processing in the infrastructure management system 4a of Modification 2 of this embodiment. Steps S1 to S6 are the same as in the example shown in Figure 2. As shown in Figure 14, when the infrastructure management device 3b of Modification 2 makes a determination on whether to exterminate a target, it sends a determination result notification indicating the result of the extermination determination to the user terminal device 1a (step S7). Specifically, the extermination target determination unit 321 notifies the result notification unit 35 of the determination result of whether the type determination result corresponding to the image data transmitted from the user terminal device 1a is an extermination target, the result notification unit 35 generates a determination result notification indicating the determination result, and sends the determination result notification to the user terminal device 1a. The type determination device 2 transmits the identification information of the user terminal device 1a that transmitted the image data to the infrastructure management device 3b along with the image data, and the extermination target determination unit 321 notifies the result notification unit 35 of the identification information of the user terminal device 1a along with the determination result of whether or not it is an extermination target. Furthermore, the extermination target determination unit 321 notifies the result notification unit 35 of the type determination result in addition to the determination result of whether or not the object is an object to be exterminated, and the result notification unit 35 may include the type determination result in the determination result notification. Also, the extermination target determination unit 321 notifies the result notification unit 35 of the determination result of whether or not the type determination result corresponding to the photographed data transmitted from the user terminal device 1a is a protected object, that is, information indicating whether or not the object is an object to be exterminated, and the result notification unit 35 may generate a determination result notification including the determination result of whether or not the object is a protected object and transmit it to the user terminal device 1a. Furthermore, if the determination result is that the object is an object to be exterminated, the extermination target determination unit 321 also notifies the result notification unit 35 of an extermination instruction indicating the extermination method, and the result notification unit 35 may include an extermination instruction indicating the extermination method in the determination result notification.

[0094] When the user terminal device 1a receives a judgment result notification, it displays the received judgment result notification (step S8). Specifically, the result acquisition unit 13 receives the judgment result notification, outputs the received judgment result notification to the display unit 14, and the display unit 14 displays the judgment result notification. Figure 14 shows an example in which the photographed data transmitted by the user terminal device 1a includes a plant to be eradicated, and in step S8, the user terminal device 1a displays an eradication instruction. If the photographed data transmitted by the user terminal device 1a does not contain a plant to be eradicated, in step S8, the user terminal device 1a displays a judgment result indicating that the plant is not to be eradicated. This allows the user to understand that the photographed plant is to be eradicated and to eradicate the plant according to the displayed eradication instruction. Note that the eradication method performed by the user may differ from the eradication method of the eradication work planned as part of the management schedule. For example, the eradication method performed by the user may be picking, while the eradication method of the eradication work planned as part of the management schedule may be topsoil removal or ground leveling. The specific methods of eradication are not limited to this example. For example, some plant species are effectively removed during the germination and seedling stages. If the plant species identification result is such a species, the user can be notified of the eradication method and asked to carry out the eradication to encourage their cooperation. For example, when informing users about the collection of photographic data, the request for cooperation in eradication can also be made to encourage user cooperation. Furthermore, the infrastructure management device 3a may include the specific eradication procedure in the notification of the identification result.

[0095] Furthermore, notifying the user that a plant is a protected species, or notifying the user of the species determination results, can increase user interest and encourage cooperation in collecting photographic data. Also, if the user is notified that a plant is a protected species, and if plants to be eradicated and plants to be protected are mixed in the user's vicinity, the user can photograph multiple plants, and the user terminal device 1a can transmit this photographic data to determine whether each plant is a protected species or an eradicated species. This allows the user to eradicate plants while protecting plants that are to be eradicated.

[0096] In the example shown in Figure 14, the infrastructure management device 3b sends a decision result notification to the user terminal device 1a. However, the infrastructure management device 3b may send the decision result notification to the type determination device 2, and the type determination device 2 may then send the decision result notification to the corresponding user terminal device 1a. Furthermore, the modified examples 1 and 2 of Embodiment 1 may be combined so that the infrastructure management device 3a described as modified example 1 sends the decision result notification to the user terminal device 1a.

[0097] In the modified example 2 of Embodiment 1, the infrastructure management device 3b is implemented by a computer system, similar to the infrastructure management device 3. The result notification unit 35 is implemented by the communication unit 105 shown in Figure 11. In the modified example 2 of Embodiment 1, the user terminal device 1a is implemented by a computer system, similar to the user terminal device 1. The result acquisition unit 13 is implemented by the communication unit 105 shown in Figure 11. The display unit 14 is implemented by the display unit 104 shown in Figure 11. Furthermore, the infrastructure management device 3b may be implemented by multiple computer systems. For example, the infrastructure management device 3b may be implemented by a cloud computer system. Also, the infrastructure management device 3b may have the functions of the type determination device 2.

[0098] In the examples described above, the infrastructure management systems 4, 4a, and 4b use photographic data taken by the user to determine the species of organisms such as plants and use this information for infrastructure management. However, as mentioned above, the systems may also use photographic data taken using drones or vehicles to determine the species of organisms. In other words, the infrastructure management systems 4, 4a, and 4b can, for example, determine the management content, which is related to the management of the infrastructure corresponding to the plant, according to the species of plant included in the photographed image.

[0099] As described above, the infrastructure management systems 4, 4a, and 4b acquire photographic data taken by the user from the user terminal devices 1 and 1a, determine the type of plants and other objects included in the acquired photographic data, and create a management schedule for infrastructure management based on the determination result. This makes it possible to monitor the status of the infrastructure without requiring the addition of equipment to the infrastructure.

[0100] Embodiment 2. Figure 15 shows an example configuration of an infrastructure management system according to Embodiment 2. The infrastructure management system 4c of this embodiment includes an infrastructure management device 3c. A user terminal device 1 may also be included in the infrastructure management system 4c. In this embodiment, the infrastructure managed by the infrastructure management system 4c is a river, and the infrastructure management device 3c acquires photographic data from the user terminal device 1 corresponding to waterways and drainage pumps, driftwood (garbage), etc., such as embankments, sandbars, sluice gates, etc., photographed by the user, and uses the acquired photographic data to create a repair work schedule as a management schedule. That is, in this embodiment, the objects in the photographic images taken by the user include, for example, at least one of embankments, sandbars, waterways, drainage pumps, and driftwood. In the following, an example of facilities and equipment in a river as the infrastructure managed is described, but it is not limited to this and may be other infrastructure such as roads or power facilities. Hereafter, components having the same function as in Embodiment 1 are denoted by the same reference numerals as in Embodiment 1, and redundant descriptions are omitted.

[0101] The configuration and operation of the user terminal device 1 are the same as in Embodiment 1. The infrastructure management device 3c comprises a data acquisition unit 31a, a management schedule determination unit 36, and a management schedule output unit 33 similar to that in Embodiment 1. The data acquisition unit 31a acquires the captured data by receiving the captured data from the user terminal device 1 and passes the acquired captured data to the management schedule determination unit 36.

[0102] The management schedule determination unit 36 ​​is an example of a management content determination unit that determines management content, which is the content related to the management of infrastructure corresponding to an object, according to the type of object. In this embodiment, the management content is, for example, a repair work schedule for repairing the object, or the content of the repair. The management schedule determination unit 36 ​​includes an object extraction unit 361, a repair target determination unit 362, a change confirmation unit 363, a result storage unit 364, a schedule determination unit 365, an object extraction data storage unit 366, a repair determination data storage unit 367, and an object data storage unit 368.

[0103] The target extraction unit 361 uses the target extraction data stored in the target extraction data storage unit 366 to determine the type of managed object from the image shown by the captured data, such as embankments, sandbars, sluice gates and other waterways and drainage pumps, and driftwood (garbage). It then extracts partial data corresponding to the portion showing the managed object and outputs the partial data to the repair target determination unit 362. Managed objects are not limited to the above examples and may be any objects that require monitoring for the repair of facilities and equipment. The target extraction data may be images for each managed object, or it may be text defining the managed object. If the target extraction data is images for each managed object, the target extraction unit 361 extracts the portion showing the managed object by determining the similarity between the captured data and the respective images of the target extraction data stored in the target extraction data storage unit 366. Machine learning may be used for this extraction.

[0104] The repair target determination unit 362 extracts repair targets using the repair determination data stored in the repair determination data storage unit 367 and the partial data. For example, if the target is a levee, the repair targets may be defects, cracks, or overhangs in the stone wall; if the target is a sandbar, the repair targets may be the size (the ratio the sandbar occupies to the width of the river); if the target is a waterway such as a sluice gate and a drainage pump, the repair targets may be the size of the sediment; and if the target is driftwood, the repair targets may be the size, but are not limited to these. For example, if the partial data corresponds to a levee, the repair target determination unit 362 extracts the part corresponding to the repair target, such as defects, cracks, or overhangs in the stone wall. The repair determination data may be images for each repair target, or it may be text data that defines the repair targets to be extracted from the images for each repair target. The repair target determination unit 362, for example, if there is a part in the image shown by the partial data that is highly similar to an image of a missing stone wall, extracts that part as a repair target and determines that the repair target is a missing stone wall of the embankment. Machine learning may be used to determine the repair item.

[0105] Furthermore, the repair target determination unit 362 calculates a numerical value indicating the condition corresponding to the repair target and stores the calculated value along with the repair target and the shooting location in the target data storage unit 368. The numerical value is, for example, the area or length of the defect if the repair target is a defect in the stone wall of an embankment, or the area of ​​the deposit if the repair target is the size of the sediment in a waterway such as a sluice gate and drainage pump. The repair target determination unit 362 also outputs the calculated numerical value, the repair target, and the shooting location to the change confirmation unit 363.

[0106] The change confirmation unit 363 confirms the change using the numerical value received from the repair target determination unit 362 and past numerical values ​​stored in the target data storage unit 368 that correspond to the same location and the same repair target. Specifically, the change confirmation unit 363 stores the difference between the numerical value received from the repair target determination unit 362 and the past numerical value as the change amount in the result storage unit 364.

[0107] Furthermore, the change confirmation unit 363 determines the repair target type, which is the type of deterioration over time, based on the amount of change. In other words, in this embodiment, the change confirmation unit 363 is a type determination unit that determines the type of deterioration over time. For example, if the amount of change is greater than or equal to a first threshold, the change confirmation unit 363 determines that the deterioration over time is great; if the amount of change is less than the first threshold and greater than or equal to a second threshold, the deterioration over time is moderate; and if the amount of change is less than the second threshold, the deterioration over time is small. In this case, the repair target type is great, medium, or small. In other words, the repair target type is a type that indicates the degree of deterioration over time in the object. The change confirmation unit 363 stores the repair target type, along with the corresponding managed object, repair target, and shooting location, in the result storage unit 364.

[0108] The schedule determination unit 365 determines the repair work schedule as a management schedule by, for example, determining the work timing based on the repair target type, determining the work location based on the shooting location, and determining the content of the repair work based on the management target and the repair target, and outputs the determined management schedule to the management schedule output unit 33. For example, the schedule determination unit 365 creates a repair work schedule based on the premise that if the repair target type is large, the repair work will be carried out within one month; if the repair target type is medium, the repair work will be carried out within one year; and if the repair target type is small, no repair work will be carried out.

[0109] In this embodiment, the content of the repair work is determined based on the type of repair target, such as defects, cracks, overhangs in the stone wall, and the size of deposits in waterways and drainage equipment such as sluice gates. The repair target determination unit 362 is also an example of a type determination unit that determines the type of repair target. The repair target type in this embodiment may be only the type of deterioration over time, only the type of repair target, or a combination of both. In other words, the repair target type is at least one of the type of deterioration over time and the type of repair target.

[0110] Figure 16 is a flowchart showing an example of processing in the infrastructure management device 3c of this embodiment. The infrastructure management device 3c determines whether or not it has acquired image data captured by the user from the user terminal device 1 (step S41). In detail, the data acquisition unit 31a determines whether or not it has received image data from the user terminal device 1.

[0111] If the system has not acquired image data captured by the user from the user terminal device 1 (step S41 No), the infrastructure management device 3c repeats step S41. If the system has acquired image data captured by the user from the user terminal device 1 (step S41 Yes), it extracts the target object from the image data (step S42). Specifically, in step S42, the target extraction unit 361 uses the target extraction data stored in the target extraction data storage unit 366 to extract partial data corresponding to the portion of the image in the image data that shows the target object, and outputs the partial data to the repair target determination unit 362.

[0112] Next, the infrastructure management device 3c extracts the items to be repaired (step S43). Specifically, the repair item determination unit 362 extracts the items to be repaired using the repair determination data and partial data stored in the repair determination data storage unit 367, calculates a numerical value indicating the state corresponding to the item to be repaired, and stores the calculated numerical value along with the item to be repaired and the shooting location in the target data storage unit 368.

[0113] Next, the infrastructure management device 3c checks for changes (step S44). Specifically, the change confirmation unit 363 stores the difference between the numerical value received from the repair target determination unit 362 and the past numerical value stored in the target data storage unit 368 corresponding to the same location and the same repair target as the numerical value, as the change amount in the result storage unit 364.

[0114] Next, the change confirmation unit 363 determines the type of repair target (step S45). Specifically, the change confirmation unit 363 determines the type of repair target, which is at least one of the type of aging deterioration and the type of repair target, and stores the determination result as the type determination result in the result storage unit 364.

[0115] Next, the infrastructure management device 3c determines the work location based on the shooting location associated with the shooting data and determines the work timing based on the repair target type (step S46). Specifically, the schedule determination unit 365 determines the work location based on the shooting location stored in the result storage unit 364, determines the work timing based on the repair target type stored in the result storage unit 364, and stores the determined work timing and work location in the result storage unit 364. The work timing corresponding to the repair target type may be predetermined or may be entered by the manager or worker.

[0116] Next, the infrastructure management device 3c determines whether or not it is time to determine the management schedule (step S47). Specifically, the schedule determination unit 365 determines whether or not it is time to determine the management schedule, similar to step S27 in Embodiment 1.

[0117] If it is the timing for determining the management schedule (Step S47 Yes), the infrastructure management device 3c determines the management schedule based on the determined work time and work location (Step S48). Specifically, the schedule determination unit 365 determines the management schedule based on the determined work time and work location and outputs the determined management schedule to the management schedule output unit 33 (Step S49).

[0118] The infrastructure management device 3c performs step S49 in the same manner as step S29 in Embodiment 1, and repeats the processing from step S41. Also, if it is determined in step S47 that it is not the timing for determining the management schedule (step S47 No), the infrastructure management device 3c repeats the processing from step S41.

[0119] The infrastructure management device 3c of this embodiment is implemented by a computer system, similar to the infrastructure management device 3 of Embodiment 1. The target extraction unit 361, repair target determination unit 362, change confirmation unit 363, and schedule determination unit 365 shown in Figure 15 are implemented by the control unit 101 shown in Figure 11 executing a computer program stored in the storage unit 103 shown in Figure 11. The storage unit 103 shown in Figure 11 is also used to implement the target extraction unit 361, repair target determination unit 362, change confirmation unit 363, and schedule determination unit 365 shown in Figure 15. The result storage unit 364, target extraction data storage unit 366, repair determination data storage unit 367, and target data storage unit 368 shown in Figure 15 are part of the storage unit 103 shown in Figure 11. The data acquisition unit 31a shown in Figure 15 is implemented by the communication unit 105 shown in Figure 11. The management schedule output unit 33 shown in Figure 15 is implemented by at least one of the communication unit 105 and the display unit 104 shown in Figure 11. Furthermore, the infrastructure management device 3c may be implemented by multiple computer systems. For example, the infrastructure management device 3c may be implemented by a cloud computing system.

[0120] Furthermore, the infrastructure management device 3c of this embodiment may also have any of the functions of the infrastructure management devices 3, 3a, and 3b described in Figures 1, 12, and 13 of Embodiment 1. For example, the infrastructure management system 4c may have the type determination device 2 of Embodiment 1 added, and the infrastructure management device 3c may have the management schedule determination unit 32 described in Embodiment 1 added. The data acquisition unit 31a acquires the image data and type determination result from the type determination device 2 and outputs the acquired image data and type determination result to the management schedule determination unit 32. Furthermore, the infrastructure management device 3c of this embodiment may also have functions that combine the modifications 1 and 2 of Embodiment 1. Furthermore, the infrastructure management device 3c may also have the functions of the type determination device 2.

[0121] As described above, the infrastructure management system 4c acquires photographic data taken by the user from the user terminal device 1, determines the type of repair target of the managed object included in the acquired photographic data, and creates a management schedule for infrastructure management based on the determination result. This makes it possible to monitor the status of the infrastructure without requiring the addition of equipment to the infrastructure.

[0122] Embodiment 3. Figure 17 shows an example configuration of an infrastructure management system according to Embodiment 3. The infrastructure management system 4d of this embodiment includes a type determination device 2 and an infrastructure management device 3d, similar to those in Embodiment 1. In this embodiment, the infrastructure management system 4d notifies the user terminal device 1b of the estimated shooting location, acquires the shooting data taken by the user from the user terminal device 1b, and manages the infrastructure using the acquired shooting data. In this embodiment, an example is described in which the infrastructure managed by the infrastructure management system 4d is a river, but as with Embodiment 1, the infrastructure managed is not limited to rivers and may be other infrastructure such as roads or power facilities. Although Figure 17 shows one user terminal device 1b, there is no restriction on the number of user terminal devices 1b; one or more are sufficient. The user terminal device 1b may also be included in the infrastructure management system 4d. Hereafter, components having the same functions as in Embodiment 1 are denoted by the same reference numerals as in Embodiment 1, and redundant descriptions are omitted.

[0123] The infrastructure management device 3d is the same as the infrastructure management device 3 of Embodiment 1, except that a shooting location output unit 37, a shooting location determination unit 38, and a location determination data acquisition unit 39 are added.

[0124] The location determination data acquisition unit 39 acquires location determination data, which is data for determining a shooting location recommended to the user, and outputs the acquired location determination data to the shooting location determination unit 38. For example, the location determination data acquisition unit 39 extracts work locations from the target determination results of the pest control targets stored in the result storage unit 322, and uses the extracted work locations as location determination data. Here, it is assumed that past target determination results are stored in the result storage unit 322. Alternatively, the determined management schedule may be stored in the result storage unit 322, and the location determination data acquisition unit 39 may extract work locations from the pest control work management schedule stored in the result storage unit 322, and use the extracted work locations as location determination data. In places where the target plants for pest control have been detected in the past, the target plants may grow repeatedly, and in plant control, removal work may be carried out continuously for several years. For this reason, it is desirable to continuously monitor places where the target plants for pest control have been detected once. Therefore, by recommending locations previously designated as work sites to users as shooting locations, it is possible to promote continuous monitoring of areas where the target plants for extermination have been detected in the past. Similarly, in the case of animals, it is effective to repeatedly monitor areas where the target animals for extermination have been detected in the past.

[0125] Furthermore, the location determination data acquisition unit 39 may acquire hazard maps as location determination data. The location determination data acquisition unit 39 may acquire hazard maps by receiving them from the data providing device 6 that provides hazard maps, or it may accept input of information indicating priority monitoring locations based on hazard maps from managers, workers, etc. The hazard map may be, for example, a flood hazard map, and the areas of the river under monitoring where flood damage is expected will be designated as recommended shooting locations (recommended shooting locations). Alternatively, the areas including the locations assumed to be flood inundation points when creating the flood hazard map may be designated as recommended shooting locations. By designating the areas where flood damage is expected or the areas around the locations assumed to be flood inundation points as recommended shooting locations, it is possible to focus monitoring on areas susceptible to the effects of disasters, and it is possible to promote the eradication of plants that affect these areas. Furthermore, the location determination data is not limited to hazard maps; priority monitoring locations may also be designated. Specific examples of priority monitoring locations include sandbag storage areas, evacuation facilities, areas where inland flooding from manholes is anticipated, and coastal areas prone to flooding from storm surges.

[0126] Furthermore, the location determination data acquisition unit 39 may acquire location information of the insured object as location determination data. The location determination data acquisition unit 39 may acquire location information of the insured object by receiving location information of the insured object from the data providing device 6 that provides location information of the insured object, or it may accept input of location information of the insured object from managers, workers, etc. By recommending the area around the insured object as a shooting location, the insured object can be monitored. Also, by recommending the location of the insured object as a shooting location to the policyholder, the policyholder can be alerted to the object. For this reason, the insurance company may give benefits such as a reduction in insurance premiums or the awarding of points to policyholders who take photographic data of the object. Furthermore, the insured object may be an object covered by fire insurance or flood insurance. In addition to location information of the insured object, the location determination data may also include contract details. For example, it may include the type of object and the structural class of the object. For example, detached houses have a higher risk of flood damage compared to apartments.

[0127] Furthermore, the location determination data acquisition unit 39 may acquire information indicating the address of the life insurance policyholder as location determination data. The location determination data acquisition unit 39 may acquire information indicating the address of the life insurance policyholder by receiving information indicating the address of the life insurance policyholder from the data provision device 6 that provides information indicating the address of the life insurance policyholder, or it may accept input of information indicating the address of the life insurance policyholder from an administrator, worker, etc. By encouraging life insurance policyholders to take photographs near their address, it is possible to promote the health of the policyholders. In addition, premium reductions or point accrual may be implemented depending on the number of locations photographed by the policyholder, the number of types of plants photographed, etc.

[0128] The location determination data may be one of the following: information indicating the location of a photograph corresponding to an image in which an object to be exterminated was previously detected; a hazard map; location information of an insured property; and information indicating the address of a life insurance policyholder. It may also be two or more of these. The information indicating the location of a photograph corresponding to an image in which an object to be exterminated was previously detected may be a location where an object of a type previously determined to be an object to be exterminated was photographed, or a work location where extermination work was previously carried out.

[0129] The shooting location determination unit 38 determines a recommended shooting location using the location determination data received from the location determination data acquisition unit 39, and outputs the determined recommended shooting location to the shooting location output unit 37. For example, if the location determination data is a past work location, the shooting location determination unit 38 will designate the area including the past work location as the recommended shooting location. If the location determination data is a hazard map, the shooting location determination unit 38 will designate the area where damage is expected as the recommended shooting location. Furthermore, if the location determination data is location information of an object covered by property insurance, the shooting location determination unit 38 will designate the area including the location indicated by that location information as the recommended shooting location. Furthermore, if the location determination data is information indicating the address of a life insurance policyholder, the shooting location determination unit 38 will designate the area including the location indicated by that information as the recommended shooting location.

[0130] The recommended shooting locations may be common to all users or may be determined individually for each user. For example, if the location determination data is a past work location or a hazard map, the recommended shooting locations may be common to all users. If the location determination data is location information of an insured property or information indicating the address of a life insurance policyholder, the recommended shooting locations may be determined individually for each user. When the recommended shooting locations are determined individually for each user, the shooting location determination unit 38 outputs the recommended shooting locations to the shooting location output unit 37 along with the corresponding user identification information. When the recommended shooting locations are determined individually for each user, the location determination data also includes the user's identification information. The user's identification information may be the user's email address or user identification information predetermined by the registration process for using the infrastructure management system 4d.

[0131] The shooting location output unit 37 outputs the recommended shooting location to the user terminal device 1b by transmitting the recommended shooting location received from the shooting location determination unit 38 to the user terminal device 1b.

[0132] User terminal device 1b is the same as user terminal device 1 of Embodiment 1, except that a display unit 14 and a shooting location acquisition unit 15 are added. The shooting location acquisition unit 15 acquires the shooting location by receiving the shooting location recommended from the infrastructure management device 3d and outputs the acquired shooting location to the display unit 14. The display unit 14 displays the shooting location. Note that the display unit 14 has the same reference numerals as the display unit 14 of Modification 2 of Embodiment 1 described above because it has the same function of displaying the received information. The user can take a photograph of the recommended shooting location by confirming the displayed shooting location.

[0133] Figure 18 is a flowchart showing an example of the process for determining the recommended shooting location in this embodiment. The infrastructure management device 3d acquires location determination data (step S51). Specifically, the location determination data acquisition unit 39 acquires location determination data as described above and outputs the acquired location determination data to the shooting location determination unit 38.

[0134] Next, the infrastructure management device 3d determines the recommended shooting location using the location determination data (step S52). Specifically, the shooting location determination unit 38 determines the recommended shooting location using the location determination data and outputs the determined recommended shooting location to the shooting location output unit 37.

[0135] Next, the infrastructure management device 3d outputs the determined recommended shooting location to the user terminal device 1b (step S53), and terminates the process. Specifically, the shooting location output unit 37 transmits the recommended shooting location received from the shooting location determination unit 38 to the user terminal device 1b. The recommended shooting location may also be transmitted to the user terminal device 1b via the type determination device 2.

[0136] Figure 19 shows an example of a recommended location for photography in this embodiment. The work area 601 shown in Figure 19 indicates a location where pest control work has been carried out in the past. Circles of the same shape but without the label 601 also indicate locations where pest control work has been carried out in the past. In this case, for example, the infrastructure management device 3d recommends photography in the section from bridge α to bridge β on River A and in the section from bridge γ to bridge δ on River B, since pest control work has been carried out in the past in these sections. Figure 19 is just one example, and the method for determining the recommended location for photography is not limited to this example.

[0137] The infrastructure management device 3d in this embodiment is implemented by a computer system, similar to the infrastructure management device 3 in Embodiment 1. The shooting location determination unit 38 and the location determination data acquisition unit 39 shown in Figure 17 are implemented by executing a computer program stored in the storage unit 103 shown in Figure 11 by the control unit 101 shown in Figure 11. The storage unit 103 shown in Figure 11 is also used to implement the shooting location determination unit 38 and the location determination data acquisition unit 39 shown in Figure 17. The communication unit 105 shown in Figure 11 may be used to implement the location determination data acquisition unit 39. The shooting location output unit 37 shown in Figure 17 is implemented by the communication unit 105 shown in Figure 11. Furthermore, the infrastructure management device 3d may be implemented by multiple computer systems. For example, the infrastructure management device 3d may be implemented by a cloud computer system.

[0138] Furthermore, the infrastructure management device 3d may also have the functions of the type determination device 2. Also, the infrastructure management device 3d of this embodiment may determine the extermination timing by further considering weather information, similar to Modification 1 of Embodiment 1, or it may notify the user terminal device 1b whether or not it is a target for extermination, similar to Modification 2 of Embodiment 1. Furthermore, the infrastructure management device 3d of this embodiment may have functions that combine Modification 1 and Modification 2 of Embodiment 1. Also, the infrastructure management device 3d may further have the functions of the infrastructure management device 3c described in Embodiment 2.

[0139] As described above, in this embodiment, the infrastructure management device 3d performs the same processing as in Embodiment 1 and outputs recommended shooting locations to the user terminal device 1b. This provides the same effects as in Embodiment 1 and allows the user to be prompted to take photos at locations appropriate to their purpose.

[0140] The configurations shown in the above embodiments are merely examples, and it is possible to combine them with other known technologies, combine different embodiments, and omit or modify parts of the configuration without departing from the gist of the invention. [Explanation of symbols]

[0141] 1,1a,1b User terminal device, 2 Type determination device, 3,3a,3b,3c,3d Infrastructure management device, 4,4a,4b,4c,4d Infrastructure management system, 5 Weather information provision device, 6 Data provision device, 11 Shooting unit, 12 Shooting data output unit, 13 Result acquisition unit, 14 Display unit, 15 Shooting location acquisition unit, 21 Shooting data acquisition unit, 22 Type determination unit, 23 Type notification unit, 24 Type data storage unit, 31,31a Data acquisition unit, 32,32a,36 Management schedule determination unit, 33 Management schedule output unit, 34 Weather information acquisition unit, 35 Result notification unit, 37 Shooting location output unit, 38 Shooting location determination unit, 39 Location determination data acquisition unit, 321 Extermination target determination unit, 322,364 Result storage unit, 323,323a Extermination timing determination unit, 324 Work location determination unit, 325, 365 Schedule determination unit, 326 Extermination type data storage unit, 327 Extermination timing data storage unit, 361 Target extraction unit, 362 Repair target determination unit, 363 Change confirmation unit, 366 Target extraction data storage unit, 367 Repair determination data storage unit, 368 Target data storage unit, 401 Trained model generation unit, 402 Inference unit, 403 Determination unit.

Claims

1. A data acquisition unit receives a species determination result, which is the species determination result, from a species determination device that determines the species of plants contained in images taken by the user of infrastructure. A management content determination unit determines whether a plant corresponding to the aforementioned type determination result is a target for eradication, using the aforementioned type determination result and eradication type determination data indicating the type of plant to be eradicated, estimates the fruiting period for the plant that is determined to be a target for eradication using the aforementioned type determination result corresponding to the plant and eradication timing determination data indicating the fruiting period for each type of plant, determines the eradication period to be a certain period before the estimated fruiting period, and determines an eradication work schedule that includes the determined eradication period. A management content output unit that outputs the aforementioned extermination work schedule, Equipped with, The aforementioned type determination device is an infrastructure management device characterized by receiving the captured image from the user's user terminal device and determining the type based on the comparison result between the captured image and the image corresponding to that type for each type of plant.

2. A data acquisition unit that receives images of infrastructure taken by the user from the user's user terminal device, A species determination unit that determines the species of plant included in the captured image based on the comparison result between the captured image and the corresponding image for each species of plant, A management content determination unit determines whether a plant corresponding to the type determination result is a target for eradication, using the type determination result which is the type determined by the type determination unit and eradication type determination data which indicates the type of plant to be eradicated, estimates the fruiting period for the plant that is determined to be a target for eradication, uses the type determination result corresponding to the plant and eradication timing determination data which indicates the fruiting period for each type of plant, determines an eradication period a certain period before the estimated fruiting period to be the eradication period for the plant, and determines an eradication work schedule which includes the determined eradication period. A management content output unit that outputs the aforementioned extermination work schedule, An infrastructure management device characterized by comprising the following features.

3. A weather information acquisition unit acquires weather-related information, which includes at least one of weather information and sunshine duration, from a weather information providing device that provides weather-related information. Equipped with, The infrastructure management device according to claim 1, characterized in that the management content determination unit corrects the fruiting period calculated using the type determination result and the extermination type determination data based on the difference between an index that quantifies weather information during a predetermined period and a standard index that corresponds to a predetermined standard weather.

4. A data acquisition unit receives the species determination result, which is the result of determining the species of plants contained in the captured images taken by the user of infrastructure, from a species determination device that calculates the species determination result using the captured images, and receives the captured images from the species determination device. A management content determination unit determines whether a plant corresponding to the aforementioned type determination result is a target for eradication, using the aforementioned type determination result and eradication type determination data indicating the type of plant to be eradicated, estimates the fruiting period of the plant using a trained model for inferring the fruiting period of the plant from the captured image for the plant that is determined to be a target for eradication, determines an eradication period a certain period before the estimated fruiting period to be the eradication period for the plant, and determines a management schedule including the determined eradication period. A management content output unit that outputs the aforementioned management schedule, Equipped with, The aforementioned species determination device is characterized in that it determines the species determination result based on the comparison result between the captured image and the image corresponding to that species for each plant species.

5. The data acquisition unit receives the shooting location corresponding to the captured image from the type determination device, The infrastructure management device according to claim 1, characterized in that the management content determination unit determines the location of the extermination work in the extermination work schedule to be a location that includes the shooting location, based on the shooting location corresponding to the captured image.

6. The infrastructure management device according to any one of claims 1 to 3, characterized in that the management content determination unit determines whether or not the plant is a protected plant using the plant species included in the captured image and protected plant species data.

7. The infrastructure management device according to claim 6, characterized in that the plant to be protected is a native plant species.

8. The data acquisition unit receives identification information of the user terminal device that is the source of the captured image from the type determination device, The infrastructure management device according to claim 1, characterized in that, based on the identification information of the user terminal device that transmitted the captured image, it notifies the user terminal device that transmitted the captured image corresponding to the plant of information indicating whether or not the plant is a target for extermination.

9. The infrastructure management device according to any one of claims 1 to 5, characterized in that the infrastructure is a river.

10. A location determination data acquisition unit acquires location determination data that indicates recommended shooting locations, A shooting location determination unit determines a recommended shooting location, which is a recommended shooting location, using the aforementioned location determination data. A shooting location output unit that notifies the user terminal device of a user who has registered the aforementioned recommended shooting location in advance, An infrastructure management device according to any one of claims 1 to 5, characterized by comprising:

11. The aforementioned location determination data is a hazard map. The infrastructure management device according to claim 10, characterized in that the shooting location determination unit designates an area where damage is expected in the hazard map as the recommended shooting location.

12. The aforementioned location determination data is information indicating the location of the insured object of the property insurance, The infrastructure management device according to claim 10, characterized in that the shooting location determination unit sets the location of the insured object of the damage insurance as the recommended shooting location.

13. The aforementioned location determination data is information indicating the address of the life insurance policyholder. The infrastructure management device according to claim 10, characterized in that the shooting location determination unit designates the river closest to the address of the life insurance policyholder as the recommended shooting location.

14. A result storage unit that stores the work location determined by the management content determination unit, Equipped with, A shooting location determination unit sets the work location stored in the result storage unit as a recommended shooting location, which is a recommended shooting location. A shooting location output unit that notifies the user terminal device of a user who has registered the aforementioned recommended shooting location in advance, The infrastructure management device according to claim 5, characterized by comprising:

15. A species determination device comprising: a data acquisition unit that receives a captured image taken by the user from the user's user terminal device; a species determination unit that determines the species based on a comparison result between the captured image and an image corresponding to that species for each species of plant; and a species notification unit that transmits the species determination result, which is the species determination result, to an infrastructure management device predetermined as the destination for transmission, The aforementioned infrastructure management device, Equipped with, The aforementioned infrastructure management device is A data acquisition unit that receives the classification determination result from the classification determination device, A management content determination unit determines whether a plant corresponding to the aforementioned type determination result is a target for eradication, using the aforementioned type determination result and eradication type determination data indicating the type of plant to be eradicated, estimates the fruiting period for the plant that is determined to be a target for eradication using the aforementioned type determination result corresponding to the plant and eradication timing determination data indicating the fruiting period for each type of plant, determines the eradication period to be a certain period before the estimated fruiting period, and determines an eradication work schedule that includes the determined eradication period. A management content output unit that outputs the aforementioned extermination work schedule, An infrastructure management system characterized by having the following features.

16. An infrastructure management method in an infrastructure management device, The steps include receiving a species determination result, which is the result of the species determination, from a species determination device that determines the species of plants contained in images taken by the user of infrastructure, The steps include: determining whether a plant corresponding to the aforementioned species determination result is a target for eradication using the species determination result and eradication species determination data indicating the species of the plant to be eradicated; estimating the fruiting period for a plant determined to be a target for eradication using the species determination result corresponding to that plant and eradication timing determination data indicating the fruiting period for each species of plant; determining the eradication period for eradicating the plant to be a certain period before the estimated fruiting period; and determining an eradication work schedule that includes the determined eradication period. The steps include outputting the aforementioned pest control work schedule, Includes, The infrastructure management method is characterized in that the type determination device receives the captured image from the user's user terminal device and determines the type based on the comparison result between the captured image and the image corresponding to that type for each type of plant.

17. In the computer system, The steps include receiving a species determination result, which is the result of the species determination, from a species determination device that determines the species of plants contained in images taken by the user of infrastructure, The steps include: determining whether a plant corresponding to the aforementioned species determination result is a target for eradication using the species determination result and eradication species determination data indicating the species of the plant to be eradicated; estimating the fruiting period for a plant determined to be a target for eradication using the species determination result corresponding to that plant and eradication timing determination data indicating the fruiting period for each species of plant; determining the eradication period for eradicating the plant to be a certain period before the estimated fruiting period; and determining an eradication work schedule that includes the determined eradication period. The steps include outputting the aforementioned pest control work schedule, A program that executes, The aforementioned type determination device is an infrastructure management program characterized by receiving the captured image from the user's user terminal device and determining the type based on the comparison result between the captured image and the image corresponding to that type for each type of plant.

Images