Information providing device, trained model, information providing method, and program

Abstract

To provide information useful for a user.SOLUTION: An information providing device comprises: an acquisition unit which acquires an image obtained by capturing a target area; and a processing unit which acquires information about a first area which is obtained from the image and can be greened in future, and provides information about the first region to another device in order to display the information about the first region on a display unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Conventionally, a plant placement support system has been disclosed that includes a database that stores numerical information on various plants and the size, shape, and area of ​​the green parts of the various plants, a means for inputting locations in the office where plants are to be placed, a means for inputting the locations of multiple users, a means for inputting a desired green view rate, a processing means for combining the various plants stored in the database so that the desired green view rate matches the average green view rate of the multiple users, and placing the plants in the input locations (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-147434 A Summary of the Invention [Problem to be solved by the invention]

[0004] The above techniques sometimes fail to provide useful information to users. For example, it is sometimes impossible to easily obtain information about areas that can be revegetated in the future from images.

[0005] The present invention has been made in consideration of the above circumstances, and has an object to provide an information providing device, a trained model, an information providing method, and a program that can provide useful information to users. For example, an object is to easily provide information on areas that can be revegetated in the future from an image. [Means for solving the problem]

[0006] In order to achieve the above object, the present invention provides the following means. (1) One aspect of the present invention is an information providing device that includes an acquisition unit that acquires an image of a target area, and a processing unit that acquires information about a first area that can be greened in the future from the image, and provides information about the first area to another device so that the information about the first area can be displayed on a display unit. (2) In the information providing device described above, the processing unit analyzes the image to identify the first area and a second area in the image that has already been greened. (3) In the information providing device, the processing unit derives an index indicating a degree to which the target region is included in a region in the image that is different from a target region corresponding to the first region and the second region. (4) In the above information providing device, the processing unit causes information indicating the indicator to be displayed on a display unit of a terminal device of a user. (5) In the above-mentioned information providing device, the processing unit displays the image on a display unit of a user's terminal device in a manner that allows areas of the image corresponding to the first area and the second area to be distinguished from other areas. (6) In the above-mentioned information providing device, the processing unit inputs the image to a trained model and outputs information indicating the indicator based on information output by the trained model, and the trained model is a model trained to output information indicating the first area, the second area, and the different area in the image when the image of a landscape is input. (7) In the above information providing device, the trained model performs image segmentation on the input image and outputs information indicating areas corresponding to the first region, the second region, and the different region. (8) In the above information providing device, the trained model is a model trained with training data, and the training data is information that corresponds to the image with information in which a region corresponding to the first region is assigned a label indicating the first region, information in which a region corresponding to the second region is assigned a label indicating the second region, and information in which a region corresponding to the different region is assigned a label indicating the different region. (9) In the above information providing device, the image is an image of a scene including a parking lot. (10) In the above-mentioned information providing device, the acquisition unit further acquires location information of the landscape of the image, and the processing unit refers to information that corresponds the location information with information of an organization that supports greening, and provides to another device, in addition to information regarding the first area, information about the supporting organization that corresponds to the location information of the image. (11) Another aspect of the present invention is a model that, when an image of a target area is input, performs image segmentation on the image and outputs information that divides the image into a first area that can be greened in the future, a second area that has already been greened, and other areas, and is a trained model that has learned information that associates the image with information in which an area corresponding to the first area contained in the image has been assigned a label indicating the first area, information in which an area corresponding to the second area has been assigned a label indicating the second area, and information in which an area different from the first area and the second area has been assigned a label indicating the different area. (12) Another aspect of the present invention is an information provision method in which a computer acquires an image of a target area, acquires information about a first area that can be greened in the future from the image, and provides information about the first area to another device to display the information about the first area on a display unit. (13) Another aspect of the present invention is a program that causes a computer to acquire an image of a target area, acquire information about a first area that can be greened in the future from the image, and provide information about the first area to another device so that the information about the first area can be displayed on a display unit. (14) In the above program, this is a program implemented as a subroutine included in the application programming interface. Effect of the Invention

[0007] The information providing device, the trained model, the information providing method, or the program of the present invention can provide useful information to a user. For example, information on areas that can be easily revegetated in the future can be provided from an image. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 illustrates an example of a configuration of an information providing system. [Diagram 2] 2 is a diagram illustrating an example of a functional configuration of an information providing device 100. FIG. [Diagram 3] 2 is a sequence diagram showing an example of a flow of processes executed by the user terminal device 10 and the information providing device 100. FIG. [Figure 4] 2A to 2C are diagrams showing an example of an image acquired by the user terminal device 10 and an example of an image displayed on a display unit. [Diagram 5] 4 is a flowchart showing an example of the flow of processing executed by the information providing device 100. [Figure 6] 13 is a diagram showing an example of an image input to a potential greening area recommendation AI model 160 and an example of an image output by the potential greening area recommendation AI model 160. FIG. [Figure 7] FIG. 2 illustrates an example of a functional configuration of a learning device 200. [Figure 8] 13 is a diagram showing an example of an output result of a potential greening area recommendation AI model 160 according to the first modified example. FIG. [Figure 9] FIG. 13 is a diagram showing an example of an image provided in Modification Example 2. [Figure 10] FIG. 13 is a diagram showing an example of the contents of construction company information 170. [Figure 11] FIG. 13 is a diagram showing an example of a provided image IM4. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, with reference to the drawings, embodiments of an information providing device, a trained model, an information providing method, and a program of the present invention will be described.

[0010] [overview]

[0011] For example, buildings and facilities are sometimes evaluated taking into consideration people and the environment. Greening is one element in this evaluation. Greening has an impact on the environment and human activities, such as suppressing the heat island effect and promoting human health. In this way, efforts are being made to promote greening. However, to date, there has been insufficient consideration given to providing users with information on areas that are potentially suitable for greening. For example, there has been insufficient consideration given to providing areas that are potentially suitable for greening or indicators related to areas that are potentially suitable for greening. This has made it difficult for users to obtain useful information on greening.

[0012] In this embodiment, an information providing device obtains an image of a target area, obtains information on a first area that can be greened in the future from the image, and provides information on the first area (e.g., information to be provided) to another device to display the information on the first area on a display unit. The information on the first area that can be greened in the future is, for example, information indicating the size or ratio of the first area in the image, or information indicating the range of the first area (e.g., IM2 in FIG. 4, which will be described later).

[0013] The information about the first area is information acquired, for example, using a trained model trained by machine learning (for example, a potential greening area recommendation AI model of an embodiment). The information about the first area may also be information acquired by other methods. For example, information about the first area identified from an image by a specific person using a terminal device may be used.

[0014] As described above, the user can distinguish areas in the image where potential greening is possible from other areas and can recognize indicators related to areas where potential greening is possible. In other words, the user can obtain useful information. The user can refer to the above information to make plans for greening and to take on greening efforts.

[0015] [Overall configuration] 1 is a diagram showing an example of the configuration of an information providing system. The information providing system 1 includes, for example, a user terminal device 10, an information providing device 100, and a learning device 200. These devices can communicate with each other via, for example, a network NW. The network includes, for example, the Internet, a Wide Area Network (WAN), a Local Area Network (LAN), a telephone line, a public line, a dedicated line, a provider device, a wireless base station, and the like.

[0016] [User terminal device] The user terminal device 10 is a computer device having a communication function and a display function, such as a smartphone, a personal computer, or a tablet terminal. The user terminal device 10 includes, for example, a communication unit that is a communication interface for communicating with the information providing device 100, and a display unit that displays information. In the user terminal device 10, a processor such as a CPU (Central Processing Unit) executes a browser, an application program, and the like to perform various processes.

[0017] [Information provision device] FIG. 2 is a diagram showing an example of a functional configuration of the information providing device 100. The information providing device 100 functions as, for example, an application programming interface (API). The information providing device 100 includes, for example, a communication unit 110, an acquisition unit 120, a processing unit 130, a providing unit 140, and a storage unit 150. The acquisition unit 120 and the processing unit 130 are realized by, for example, a hardware processor such as a CPU executing a program (software). Some or all of these functional units may be realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (a storage device having a non-transient storage medium) of the information providing device 100, or may be stored in a removable storage medium such as a DVD or CD-ROM, and installed in the information providing device 100 by mounting the storage medium (non-transient storage medium) in a drive device. The program for realizing each of the above functions may be implemented as a subroutine included in an API. A subroutine is a program in which a process to be executed when called by an instruction written in another program is written. When the process written in the subroutine is executed, information on a part or all of the result of the process is returned to the calling program as a return value. The functional configuration of the processing unit 130 and the providing unit 140 combined is an example of a "processing unit".

[0018] The memory unit 150 may be realized by the various memory devices mentioned above, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The memory unit 150 stores a potential greening area recommendation AI model 160. The potential greening area recommendation AI model 160 is a model generated by the learning device 200 as described below. The communication unit 110 is a communication interface for communicating with other devices.

[0019] The acquisition unit 120 acquires an image of a target area. The image is, for example, an image provided by the user terminal device 10. The processing unit 130 acquires information on a first area that can be greened in the future, obtained from the image. The provision unit 140 provides information on the first area to another device (for example, the user terminal device 10) to display the information on the first area on a display unit. Details of these processes will be described later.

[0020] [Processing executed by the user terminal device and the information providing device] 3 is a sequence diagram showing an example of the flow of processing executed by the user terminal device 10 and the information providing device 100. First, the user terminal device 10 acquires an image of a landscape captured in response to a user's operation (step S10). Next, the user terminal device 10 transmits the acquired image to the information providing device 100 (step S12). Next, the information providing device 100 analyzes the image and acquires information to be provided to the user from the image (step S14). Details of this processing and the information to be provided will be described later.

[0021] Next, the information providing device 100 transmits the provided information to the user terminal device 10 (step S14). Next, the user terminal device 10 acquires the provided information and displays an image including the acquired provided information on the display unit (step S18).

[0022] 4 is a diagram showing an example of an image acquired by the user terminal device 10 and an image displayed on the display unit. Image IM1 is an image (an image of a landscape including a parking lot) acquired by the user terminal device 10 and provided to the information providing device 100. In the acquired image, the information providing device 100 identifies a greening area (second area) where greening has been performed and a future greening area (first area) where greening can be performed in the future. The information providing device 100 generates a specific image in a manner that allows these areas (greening area and area where greening is possible) to be distinguished from other areas.

[0023] Furthermore, the information providing device 100 derives the potential green view ratio by using the following formula (1). Potential green coverage rate = (area of ​​green areas + area of ​​future green areas) / area of ​​imaging range (1)

[0024] The potential green view ratio is an example of "an index indicating the degree to which the target area is included in an area different from the target area corresponding to the first area and the second area." The information providing device 100 may derive other indices related to future greening areas that can be greened in the future instead of (or in addition to) the potential green view ratio. For example, the ratio of future greening areas that can be greened in the future in the image, the area of ​​future greening areas that can be greened in the future, etc.

[0025] The information providing device 100 provides the provided information including the specific image and the potential green view rate to the user terminal device 10. The user terminal device 10 displays an image IM2 based on the provided information on a display unit. Note that in the above image IM2, the greening area and the future greening area are indicated with the same label, but they may be given different labels so that the user can distinguish them.

[0026] As described above, the user can easily obtain an image IM2 including the provided information provided by the information providing device 100 by transmitting an image captured using the user terminal device 10 to the information providing device 100.

[0027] [Processing performed by the information providing device] FIG. 5 is a flowchart showing an example of the flow of the process executed by the information providing device 100. First, the acquisition unit 120 of the information providing device 100 acquires an image provided by the user terminal device 10 (step S100). Next, the processing unit 130 of the information providing device 100 inputs the acquired image to the potential greening area recommendation AI model 160 (step S202). Next, the processing unit 130 acquires information output by the potential greening area recommendation AI model 160 (step S204). Next, the processing unit 130 uses the acquired information to generate information to be provided (step S206), and provides the information to be provided to the user terminal device 10 (step S208). Then, the user terminal device 10 can display the image IM2 of FIG. 4 on the display unit. This ends the process of one routine of this flowchart.

[0028] FIG. 6 is a diagram showing an example of an image input to the potential greening area recommendation AI model 160 and an image output by the potential greening area recommendation AI model 160. The image input to the potential greening area recommendation AI model 160 is, for example, an image IM1 acquired by the user terminal device 10. The image output by the potential greening area recommendation AI model 160 is, for example, an image IM3 in which a label of a greening area, a label of a future greening area, and labels of other areas are associated with each other for each area of ​​the image (for example, for each pixel). The potential greening area recommendation AI model is a model that assigns a label corresponding to each area (pixel) using image segmentation. The processing unit 130 generates an image included in the image IM2 based on each label of the image IM3, or derives a potential green view rate by tallying up the size of the area to which a desired label is assigned. The image IM3 may be provided to a user.

[0029] As described above, the processing unit 130 can derive the potential greening area ratio and the future greening area by utilizing the potential greening area recommendation AI model 160.

[0030] [Learning device] FIG. 7 is a diagram showing an example of the functional configuration of the learning device 200. The learning device 200 includes a communication unit 210, an information acquisition unit 220, a learning unit 230, an information provision unit 240, and a storage unit 250. In the learning device 200, for example, the information acquisition unit 220, the learning unit 230, and the information provision unit 240 are realized by a hardware processor such as a CPU executing a program (software). Some or all of these functional units may be realized by hardware (including circuitry) such as an LSI, ASIC, FPGA, or GPU, or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (a storage device having a non-transient storage medium) of the learning device 200, or may be stored in a removable storage medium such as a DVD or CD-ROM, and may be installed in the learning device 200 by mounting the storage medium (non-transient storage medium) in a drive device.

[0031] The storage unit 250 may be realized by the various storage devices described above, or an EEPROM, a ROM, a RAM, etc. The storage unit 250 stores learning data 260 and a potential greening area recommendation AI model 270 (potential greening area recommendation AI model 160) that has learned the learning data. The communication unit 210 is a communication interface for communicating with other devices.

[0032] The information acquisition unit 220 acquires learning data 260 input by a user or provided from another device, and stores the acquired learning data 260 in the storage unit 250. The learning unit 230 uses the learning data 260 to train a pre-learned model (not shown) stored in the storage unit 250 to generate a potential greening area recommendation AI model 270. For example, the learning unit 230 uses the learning data 260 to train a pre-learned public AI model for image segmentation (not shown, a trained AI model trained with learning data other than the learning data 260 such as the COCO dataset) stored in the storage unit 250 to generate a potential greening area recommendation AI model 270. The pre-learned AI model and the potential greening area recommendation AI model 270 are AI models that perform image segmentation and output labels corresponding to areas (e.g., pixels).

[0033] The learning data is information in which an image is associated with information in which a label indicating a future greening area (first area) is assigned to an area included in the image that corresponds to a future greening area (first area), information in which a label indicating a greening area (second area) is assigned to an area included in the image that corresponds to a greening area (second area), and information in which a label indicating a different area is assigned to an area included in the image that corresponds to a different area (an area different from the future greening area and the greening area). The future greening area of ​​the learning data may be, for example, a parking lot. The future greening area of ​​the learning data may also be, for example, a wall of a building, a vacant lot, or other area where greening is expected to be possible.

[0034] When an image of a captured landscape is input, the learning unit 230 trains the pre-learning model (for example, by adjusting each parameter included in the model) so as to output information indicating the future greening area, the greening area, and the different area in the image, and generates a potential greening area recommendation AI model. As a result, the potential greening area recommendation AI model 270 performs image segmentation on the input image and outputs information indicating areas corresponding to the future greening area, the greening area, and the different area.

[0035] Here, the labeled image, which is the inference result output by the potential greening area recommendation AI model 270, was compared with the labeled image, which is the correct answer data. Specifically, the labels of the pixels of the correct answer data image were compared with the labels of the same pixels in the inference result for multiple images, and the average of these correct answers was calculated, resulting in an accuracy rate of about 92%. In other words, it was confirmed that about 92% of the labels assigned to the pixels in the output result of the potential greening area recommendation AI model 270 were correct labels.

[0036] The information providing unit 240 provides the information providing device 100 with the potential greening area recommendation AI model 270 capable of performing inference with high accuracy as described above.

[0037] In the above example, a label according to the type of future greening area (first area) or greening area (second area) may be assigned to the correct answer data, and learning may be performed. For example, a future greening area of ​​a wall may be assigned a different label than a future greening area of ​​a parking lot. Also, a greening area of ​​trees may be assigned a different label than a greening area of ​​vegetation smaller than trees. By learning learning data with labels assigned in this way, it is possible to generate a potential greening area recommendation AI model that can output information on future greening areas or greening areas that are more finely divided.

[0038] For example, when an image is input, the potential greening area recommendation AI model outputs information indicating the future greening area of ​​the parking lot, the future greening area of ​​the wall, the greening area of ​​trees, and the greening area of ​​grass and shrubs in the image. This allows the information providing device 100 to provide the user terminal device 10 with an image showing these areas in a distinguishable manner. Furthermore, the information providing device 100 may provide the user terminal device 10 with an image in a manner corresponding to a user's operation. For example, when a user performs an operation requesting the provision of an image in which the future greening area of ​​the parking lot and the future greening area of ​​the wall can be distinguished, the information providing device 100 provides the user terminal device 10 with an image corresponding to the operation.

[0039] Furthermore, the information providing device 100 may determine a future greening area according to a user's operation as the target future greening area. For example, when an operation is performed indicating that the future greening area of ​​the wall surface is not the target, the information providing device 100 does not set the future greening area of ​​the wall surface as the future greening area, but sets the future greening area of ​​the parking lot as the future greening area, and generates an image, a potential green view ratio, and the like.

[0040] By dividing the labels as described above, the information providing device 100 can provide information that is more desired by the user and can increase the degree of freedom in the information to be provided.

[0041] <Variation 1> In the above example, the image input to the potential greening area recommendation AI model 160 has been described as an image captured from the ground, but instead (or in addition) the image may be captured from a location other than the ground. For example, the image may be an image captured from the sky (aerial photograph), or may be an image captured from the rooftop of a building. For example, when an image is input to the potential greening area recommendation AI model 160, the potential greening area recommendation AI model 160 classifies the image into a greening area and a future greening area according to the learning result, such as a parking lot, a vacant lot, or a building rooftop.

[0042] FIG. 8 is a diagram showing an example of an output result of the potential greening area recommendation AI model 160 of the first modification. As shown in FIG. 8, an image in which a label indicating that an area estimated to be a parking lot or a vacant lot is a future greening area and an image in which a label indicating that the area is a greened area are added are derived. The potential greening area recommendation AI model 160 is a model in which learning data is learned in the same manner as the above-mentioned concept. The learning data of the first modification is information in which an image captured from the sky or an image captured from a rooftop of a building and the like are associated with information in which a label indicating a future greening area (first area) is added to an area corresponding to a future greening area (first area), information in which a label indicating a greening area (second area) is added to an area corresponding to a greening area (second area), and information in which a label indicating a different area is added to an area corresponding to a different area (an area different from the future greening area and the greening area) are added.

[0043] For example, when an image of the ground captured from the sky is input, the learning unit 230 trains the pre-learning model so as to output information indicating the future greening area, the greening area, and the above-mentioned different area in the image, thereby generating a potential greening area recommendation AI model. As a result, the potential greening area recommendation AI model 270 performs image segmentation on the image captured from the sky, and outputs information indicating areas corresponding to the future greening area, the greening area, and the different area.

[0044] As described above, in the first modification, the information providing device 100 can derive the future greening area and the potential green coverage ratio (potential green view ratio) even for an image captured from a place other than the ground. This information is expected to be used in planning greening of cities and towns.

[0045] <Variation 2> In the above example, the image with the potential green view rate and each area labeled is provided to the user. In addition to (or instead of) this, information obtained from the future greening area, such as the CO2 absorption amount and the degree of increase in the CO2 absorption amount, may be provided to the user. FIG. 9 is a diagram showing an example of an image provided in the second modification. The CO2 absorption amount is an index indicating the amount of CO2 absorbed by the greening of the future greening area and the greening area. For example, the processing unit 130 of the information providing device 100 derives the CO2 absorption amount by applying a preset coefficient to the size of the future greening area and the greening area, or by using a function that derives an index from the above size. The processing unit 130 may also derive an index indicating the degree of increase in the CO2 absorption amount corresponding to the greening area and the future greening area relative to the CO2 absorption amount corresponding to the greening area.

[0046] In this way, the information providing device 100 can provide the user with information that is more useful to the user.

[0047] <Variation 3> In the above example, the image with the potential green view rate and each area labeled is provided to the user. In addition to this (or instead), information on an organization that supports greening, such as a construction company that performs greening according to the location of the landscape in the image, may be provided. The supporting organization may be, for example, a company that performs greening construction, an organization that accepts consultations regarding greening, or various other organizations. The supporting organization (support organization) according to the location may be, for example, a support organization in the vicinity of the location, or a construction company that can perform construction at the location. For example, the information providing device 100 further acquires location information of the landscape in the image, refers to support organization information (construction company information) in which the location information is associated with information on an organization that supports greening, and provides information on the supporting organization corresponding to the location information of the image to another device in addition to information on the first area.

[0048] The storage unit 250 of the information providing device 100 stores, for example, construction company information 170. Fig. 10 is a diagram showing an example of the contents of the construction company information 170. The construction company information 170 is, for example, information in which location information is associated with information on a construction company corresponding to the location information. The information on the construction company is, for example, the name, contact information, website address, estimated cost per unit plot, etc. of the construction company.

[0049] For example, the information providing device 100 acquires an image and location information (location information of the scenery of the image) where the image was captured from the user terminal device 10. The information providing device 100 refers to the construction company information 170 to identify the construction company corresponding to the location information. The location information may be location information associated by a function that automatically associates the location information of the user terminal device 10 when an image is captured, or may be location information provided to the information providing device 100 by a user. The location information may also be location information obtained from the characteristics of the image (such as buildings and scenery included in the image). For example, the location may be obtained by using a server device that provides a service of estimating the location where the image was captured when an image is provided.

[0050] The information providing device 100 provides the information of the construction company identified as described above to the user terminal device 10. Fig. 11 is a diagram showing an example of the provided image IM4. In addition to the potential green view rate and an image with each area labeled, the image IM4 further includes information on the construction company corresponding to the location information, information indicating the size (area) of the area that can be greened, an estimated cost of greening the area that can be greened using the construction company, a link button to the homepage of the construction company, a button for requesting an estimate from the construction company, and the like.

[0051] For example, the information providing device 100 estimates the area of ​​the area that can be greened from the size of a predetermined object such as a vehicle in an image or the width between parking lot partition lines, and multiplies the estimated area by a set amount to obtain a rough estimate. For example, when the estimate button is operated, an input form for requesting an estimate is displayed on the display unit of the user terminal device 10, and the user can request an estimate by inputting the necessary information into the input form.

[0052] As described above, the information providing device 100 can provide the user with information on the construction company corresponding to the position where the image was captured, thereby improving convenience for the user.

[0053] According to the embodiment described above, the information providing device 100 is equipped with an acquisition unit that acquires an image of a target area, and a processing unit that acquires information about a first area that can be greened in the future from the image, and provides information about the first area to another device so that the information about the first area can be displayed on a display unit, thereby making it possible to provide useful information to a user.

[0054] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0055] 1. Information providing system, 10. User terminal device, 100. Information providing device, 120. Acquisition unit, 130. Processing unit, 140. Provision unit, 160. Potential greening area recommendation AI model, 200. Learning device, 230. Learning unit, 260. Learning data, 270. Potential greening area recommendation AI model

Claims

1. An acquisition unit that acquires an image of a target area; a processing unit that acquires information about a first area that can be greened in the future, obtained from the image, and provides information about the first area to another device so that the information about the first area can be displayed on a display unit; and An information providing device comprising:

2. The processing unit includes: analyzing the image to identify the first area and a second area in the image that has already been greened; 2. The information providing device according to claim 1.

3. The processing unit includes: deriving an index indicating a degree to which the target region is included in a region in the image that is different from a target region corresponding to the first region and the second region; 3. The information providing device according to claim 2.

4. The processing unit includes: displaying information indicating the indicator on a display unit of a terminal device of the user; 4. The information providing device according to claim 3.

5. The processing unit includes: displaying the image on a display unit of a terminal device of a user in such a manner that an area corresponding to the first area and the second area can be distinguished from other areas in the image; 4. The information providing device according to claim 3.

6. The processing unit includes: The image is input into a trained model, and information indicating the index is output based on information output by the trained model; The trained model is a model trained to output information indicating the first area, the second area, and the different area in the image when the image in which a landscape is captured is input, 6. An information providing device according to claim 3.

7. The trained model performs image segmentation on the input image and outputs information indicating areas corresponding to the first area, the second area, and the different area.

7. The information providing device according to claim 6.

8. The trained model is a model trained with training data, The learning data is information in which the image is associated with information in which a label indicating the first region is assigned to a region corresponding to the first region, information in which a label indicating the second region is assigned to a region corresponding to the second region, and information in which a label indicating the different region is assigned to a region corresponding to the different region, the information being included in the image.

7. The information providing device according to claim 6.

9. The image is an image of a scene including a parking lot.

6. An information providing device according to claim 1.

10. The acquisition unit further acquires location information of the scenery of the image, The processing unit refers to information in which the location information is associated with information about an organization that supports greening, and provides information about the organization that supports greening, which corresponds to the location information of the image, in addition to information about the first area, to another device.

6. An information providing device according to claim 1.

11. When an image of a target area is input, image segmentation is performed on the image, and information is output that divides the image into a first area that can be greened in the future, a second area that has already been greened, and other areas, a model that has learned information in which the image is associated with information in which a label indicating the first region is assigned to a region corresponding to the first region, information in which a label indicating the second region is assigned to a region corresponding to the second region, and information in which a label indicating the different region is assigned to a region different from the first region and the second region, the information being associated with the image; Trained model.

12. The computer Obtaining an image of the region of interest; acquiring information on a first area that can be greened in the future, obtained from the image, and providing information on the first area to another device so as to display the information on the first area on a display unit; Information provision method.

13. On the computer, Obtaining an image of an area of ​​interest; acquiring information on a first area that can be greened in the future, obtained from the image, and causing another device to provide information on the first area so as to display the information on the first area on a display unit; program.

14. Implemented as subroutines contained in an application programming interface, The program according to claim 13.

Images