System, program, and method

Abstract

The present invention provides a system with which it is possible to identify a first region in which a change has occurred and identify a second region within the first region.　Provided is a system that comprises at least one computer device. The system comprises: a first region identification means for identifying a first region in which a change in region has occurred, the first region being identified on the basis of a first image which is captured at a first time, and a second image which is captured at a second time and in which at least some region within the first image is captured; a selection reception means for receiving selection of a second region within the first region on the basis of a third image in which at least part of the first region is captured, the first image, or the second image; and an address identification means for identifying an address that corresponds to the second region. The first image, the second image, and / or the third image are captured by imaging the ground from the sky.

Description

System, Program, and Method

[0001] The present invention relates to a system, a program, and a method.

[0002] It is disclosed to determine whether a house in an aerial photograph or a satellite image is an empty house based on machine learning data for estimating an empty house in an image generated based on pixel information of the site of an empty house (see, for example, Patent Document 1).

[0003] International Publication No. 2019 / 225597

[0004] The present invention can solve, for example, any of the following problems. A first problem of the present invention is to provide a system capable of specifying a first area in which a change has occurred and specifying a second area within the first area. A second problem of the present invention is to provide a system capable of specifying a first area in which a change has occurred and further specifying an owner of real estate corresponding to an address corresponding to the first area from the address corresponding to the first area.

[0005] The object of the present invention is: [1] A system comprising at least one computer device, comprising: a first region identification means for identifying a first region in which a change has occurred, based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; a selection receiving means for accepting the selection of a second region within the first region, based on a third image capturing at least a portion of the first region, the first image, or the second image; and an address identification means for identifying an address corresponding to the second region, wherein the first image, the second image, and / or the third image are images taken of the ground from above; [2] A system comprising at least one computer device, comprising: first region identification means for identifying a first region in which a change has occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; and second region identification means for identifying a second region in the first region that satisfies predetermined conditions based on a third image capturing at least a portion of the first region, wherein the first image, the second image, and the third image are images taken of the ground from above; [3] The system according to [1] or [2], wherein the first image and the second image are images with lower resolution than the third image; [4] The system according to [1] or [2], wherein the third image is an optical image taken during the day, and the first image and the second image are optical images, infrared images, or SAR images taken at night; [5] The first time is on a different day than the second time and is later than the second time. The system according to any one of [1] to [4], wherein the first image and the second image are images taken during a predetermined time period; [6] The system according to any one of [2] to [5], wherein the second area identification means identifies a second area in the first area where a predetermined change has occurred, and / or a second area having the attributes of a predetermined real estate, based on the third image;[7] The system according to [6], wherein the second area identification means uses a machine learning-trained predictive model to identify a second area where a predetermined change has occurred, with image data relating to a photograph taken of the ground from above as input data, and information regarding the position in the photograph and the change in the area corresponding to that position as output data; [8] The system according to [6] or [7], wherein the second area identification means uses image data relating to a photograph taken of the ground from above as input data, and a machine learning-trained predictive model to identify a second area having predetermined real estate attributes, with information regarding the position in the photograph and the attribute of real estate in the area corresponding to that position as output data; [9] The system according to any one of [2] to [8], wherein the second area identification means identifies a second area in the first area where a change occurred, based on the third image taken at the third time and the fourth image taken at the fourth time and which captures at least a part of the first area, and the first and second images are lower-resolution captured images than the third and fourth images, or the third and fourth images are optical images taken during the day, and the first and second images are optical images, infrared images, or SAR images taken at night;

[10] The system according to [9], wherein the first time belongs to a different day than the second time and is later than the second time, the third time is after the first time, and the fourth time is before the second time;

[11] The system according to any one of [2] to

[10] , further comprising address identification means for identifying an address corresponding to the second area;

[12] A system according to any one of [1] to

[11] , wherein the address identification means identifies latitude and longitude corresponding to at least one location within the second area and identifies an address corresponding to the identified latitude and longitude;

[13] A system according to any one of [1] to

[12] , further comprising owner identification means that identifies the owner of real estate corresponding to the address identified by the address identification means based on the correspondence between an address and the owner of real estate corresponding to the address;

[14] A system comprising at least one computer device, comprising: first area identification means for identifying a first area in which a change has occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; address identification means for identifying an address corresponding to the first area; and owner identification means for identifying the owner of real estate corresponding to the address identified by the address identification means based on the correspondence between the address and the owner of real estate corresponding to the address, wherein the first image and the second image are images taken of the ground from above;

[15] The system according to

[13] or

[14] , wherein the owner identification means identifies the owner of real estate corresponding to the address identified by the address identification means when a predetermined change has occurred in the first area and / or when the first area has predetermined real estate attributes;

[16] The system according to any one of

[13] to

[15] , wherein the owner identification means identifies the owner of real estate corresponding to the address identified by the address identification means and the owner's contact information based on the correspondence between the address and the owner of real estate corresponding to the address and the owner's contact information;

[17] A system according to any one of

[13] to

[16] above, wherein the address identified by the address identification means is a land number, and the owner identification means identifies the owner of the real estate corresponding to the identified land number based on the correspondence between the land number and the owner of the real estate corresponding to the land number;

[18] A program in which a computer device functions as a first area identification means for identifying a first area in which a change has occurred, based on a first image taken at a first time and a second image taken at a second time which captures at least a part of the first image; a selection receiving means for accepting the selection of a second area of ​​the first area based on a third image which captures at least a part of the first area, the first image, or the second image; and an address identification means for identifying an address corresponding to the second area, wherein the first image, the second image, and / or the third image are images taken of the ground from above;

[19] A program in which a computer device functions as a first area identification means for identifying a first area where a change has occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image, and a second area identification means for identifying a second area within the first area that satisfies predetermined conditions based on a third image capturing at least a portion of the first area, wherein the first image, the second image, and the third image are images taken of the ground from above;

[20] A program in which a computer device functions as a first area identification means for identifying a first area where a change has occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image, an address identification means for identifying an address corresponding to the first area, and an owner identification means for identifying the owner of real estate corresponding to an address identified by the address identification means, based on the correspondence between an address and the owner of real estate corresponding to the address, wherein the first image and the second image are images taken of the ground from above;

[21] A method to be performed in a system comprising at least one computer device, comprising: a first region identification step of identifying a first region in which a change has occurred, based on a first image taken at a first time and a second image taken at a second time and which captures at least a portion of the first image; a selection acceptance step of accepting the selection of a second region of the first region based on a third image capturing at least a portion of the first region, the first image, or the second image; and an address identification step of identifying an address corresponding to the second region, wherein the first image, the second image, and / or the third image are images taken of the ground from above;

[22] A method to be performed in a system comprising at least one computer device, comprising: a first region identification step of identifying a first region in which a change has occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; and a second region identification step of identifying a second region in the first region that satisfies predetermined conditions based on a third image capturing at least a portion of the first region, wherein the first image, the second image, and the third image are images taken of the ground from above;

[23] A method to be performed in a system comprising at least one computer device, comprising: a first region identification step of identifying a first region in which a change occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; an address identification step of identifying an address corresponding to the first region; and an owner identification step of identifying an owner of real estate corresponding to an address identified by the address identification step, based on the correspondence between an address and the owner of real estate corresponding to the address, wherein the first image and the second image are images taken of the ground from above;

[0006] According to the present invention, it is possible to provide a system that can identify a first region where a change has occurred and identify a second region within that first region. Furthermore, according to the present invention, it is possible to provide a system that can identify a first region where a change has occurred and, furthermore, identify the owner of real estate corresponding to an address from the address corresponding to the first region.

[0007] This is a block diagram showing the system configuration according to an embodiment of the present invention. This is a block diagram showing the hardware configuration of a user terminal according to an embodiment of the present invention. This is a block diagram showing the hardware configuration of a server device according to an embodiment of the present invention. This is a diagram showing the real estate and owner identification process according to an embodiment of the present invention. This is a diagram illustrating the process of identifying an address according to an embodiment of the present invention. This is a diagram showing the real estate and owner identification process according to an embodiment of the present invention.

[0008] The following describes embodiments of the present invention, but the present invention is not limited to the following embodiments unless it contradicts the spirit of the invention. The order of each process constituting the flowchart described below is not limited to any order that does not cause contradictions or inconsistencies in the processing content, and it is also possible to omit some of the processes constituting the flowchart or to add new processes to each process constituting the flowchart, as long as it does not contradict the spirit of the invention. Furthermore, the device that is the main entity that executes each process constituting the flowchart can be changed to another device, as long as it does not contradict the spirit of the invention. In this case, it is possible to change the processing content so as not to cause contradictions or inconsistencies in the processing content.

[0009] [System Configuration] Figure 1 is a block diagram showing the configuration of a system according to an embodiment of the present invention. System 10 includes at least one computer device. System 10 may also include a user terminal 1, a server device 2, and an administrator terminal 3. The user terminal 1, the server device 2, and the administrator terminal 3 are connected to each other so as to be able to communicate with each other via a communication network 4. In System 10, any of the user terminal 1, the server device 2, and the administrator terminal 3 can function as an information processing device. When any of the user terminal 1, the server device 2, and the administrator terminal 3 functions as an information processing device, information is transmitted and received between at least two of these terminals as needed. The number of user terminals 1, the server device 2, and / or administrator terminals 3 is not particularly limited, as long as there is one or more.

[0010] The system 10 may consist of, for example, one computer device (standalone type), one or more server devices and one or more terminal devices (client-server type), or one host device and one or more guest devices (peer-to-peer type). Furthermore, the server device 2 may function in a distributed manner across multiple computer devices. For example, instead of the server device 2, a distributed ledger technology such as blockchain may be used.

[0011] [User Terminal] User terminal 1 is a terminal operated by a user of system 10. Figure 2 is a block diagram showing the hardware configuration of a user terminal according to an embodiment of the present invention. User terminal 1 comprises a control unit 11, RAM 12, storage unit 13, input unit 14, display unit 15, and communication interface 16, each connected by a bus.

[0012] The control unit 11 consists of a CPU and ROM. The control unit 11 executes programs stored in the storage unit 13 and controls the user terminal 1. The RAM 12 is the work area of ​​the control unit 11. The storage unit 13 is a storage medium for saving programs and data. The control unit 11 performs calculations based on the programs and data read from the RAM 12, as well as the data input by the input unit 14.

[0013] The display unit 15 has a display screen. The control unit 11 outputs a video signal for displaying an image on the display screen according to the result of the calculation processing. Here, the display screen of the display unit 15 may be a touch panel equipped with a touch sensor. In this case, the touch panel functions as an input unit 14.

[0014] The communication interface 16 can be connected to the communication network 4 wirelessly or via a wired connection, and can send and receive data with other computer devices via the communication network 4. Data received via the communication interface 16 is loaded into the RAM 12, and calculation processing is performed by the control unit 11.

[0015] [Server Device] Figure 3 is a block diagram showing the hardware configuration of a server device according to an embodiment of the present invention. The server device 2 comprises at least a control unit 21, a RAM 22, a storage unit 23, and a communication interface 24, each connected by an internal bus.

[0016] The control unit 21 consists of a CPU and ROM, and executes programs stored in the storage unit 23 to control the server device 2. The control unit 21 also has an internal timer for timing. The RAM 22 is the work area of ​​the control unit 21. The storage unit 23 is a storage area for saving programs and data. In other words, the storage unit 23 functions as a recording medium that stores programs. The control unit 21 reads programs and data from the RAM 22 and performs program execution processing based on information received from the user terminal 1 or the administrator terminal 3, respectively.

[0017] [Administrator Terminal] The administrator terminal 3 is a terminal operated by the administrator, operator, or provider of system 10. The administrator terminal 3 can have the same configuration as the user terminal 1. The administrator terminal 3 may, for example, include a control unit, RAM, storage unit, input unit, display unit, and communication interface, each connected by an internal bus.

[0018] The program may be stored on a recording medium such as a CD-ROM. In this case, the program stored on the recording medium may be installed on the user terminal 1, server device 2, or administrator terminal 3 to perform a predetermined function. Alternatively, the program may be distributed from a computer device outside the system. In this case, the program distributed from a computer device outside the system may be installed on the user terminal 1, server device 2, or administrator terminal 3 to perform a predetermined function.

[0019] [Real Estate and Owner Identification Processing] Next, a first embodiment of the real estate and owner identification processing in the system according to an embodiment of the present invention will be described. Figure 5 is a flowchart of the real estate and owner identification processing according to an embodiment of the present invention. Note that real estate is a concept that includes both land and buildings. In the following, for example, the case in which the system 10 consists of a user terminal 1 and a server device 2 will be described.

[0020] The user operates the input unit 14 of the user terminal 1 to identify the area where a change has occurred from the captured image and to start a real estate and owner identification process (hereinafter referred to as the "identification process") to identify the owner of the real estate corresponding to the identified area. First, the user operates the input unit 14 of the user terminal 1 to start dedicated application software for executing the identification process. The user enters a user ID and password to identify themselves into the user terminal 1. The server device 2 receives the user ID and password entered in the user terminal 1, authenticates the user, and allows the user to log in to system 10. Alternatively, the user may log in to system 10 by accessing the server device 2 from the user terminal 1 via a web browser.

[0021] Next, the user operates the input unit 14 of the user terminal 1 to input a request to start a specific process. The start request is transmitted from the user terminal 1 to the server device 2 and received by the server device 2. The start request may include information about a predetermined change to be specified, and / or information about the attributes of a predetermined property to be specified. Details of the predetermined change and the attributes of the predetermined property will be described later. The start request may also include information about the scope for searching for the predetermined change that has occurred and / or the scope for searching for property having the predetermined attributes in the specific process, as well as information about the period for the search.

[0022] When server device 2 receives a start request, it acquires the first image and the second image (step S1). The first and second images are images taken from above the ground. The images may be pre-stored in the storage unit 23 of server device 2, or they may be read by server device 2 from an external storage device that stores the images. Server device 2 may also acquire the images in cooperation with an external system that holds the images. The external system is, for example, a system composed of other computer devices. When coordinating with an external system, server device 2 sends an acquisition request for the first and second images to the other computer devices. The acquisition request includes information about the date and time the images to be acquired were taken and information about the area that was captured. The images are stored in association with the information about the date and time they were taken and the area that was captured.

[0023] The captured images are not particularly limited to images taken of the ground from above, but examples include aerial photographs and satellite images. Aerial photographs are photographs of the ground taken by a camera mounted on an aircraft. Satellite images are image data acquired by sensors mounted on artificial satellites. Satellite images include, for example, optical images (also called visible images), infrared images (also called thermal infrared images), or SAR (synthetic aperture radar) images (also called synthetic aperture radar images). Captured images may also be images created by combining multiple images into a single image. Furthermore, captured images include not only image data acquired as image data itself, but also image data obtained by processing data acquired by sensors.

[0024] The first image is an image taken at the first time. The second image is an image taken at the second time. The first time belongs to a different day than the second time. Also, the first time is a later time than the second time. Also, the second time may be a time that is more than a predetermined period before the first time. The predetermined period is not particularly limited and can be set as appropriate by the administrator or user. The predetermined period is preferably a period long enough to detect changes in the real estate, and may be a period on a daily, weekly, monthly, or yearly basis. Also, the first time may be the time when the most recently acquired image was taken, based on the time when the start request is entered on the user terminal 1 or when the server device 2 receives the start request. For example, if the predetermined period is one week, the second time will be one week before the first time. Note that in step S1, if there is no second image taken at a time that matches the predetermined period, a second image taken before the predetermined period may be acquired. If the start request includes information about the period to be searched, the first and second times are specified to match that period.

[0025] Furthermore, the first and second images may be images taken during a predetermined time period. Examples of predetermined time periods include the morning (between 9:00 and 12:00), the afternoon (between 12:00 and 15:00), the evening (between 16:00 and 18:00), and the nighttime (between 22:00 and 2:00). By using the first and second images taken during the same time period, it becomes easier to identify the first region in step S2 described later.

[0026] The second image is a captured image that photographs at least a portion of the first image. A captured image that photographs at least a portion of the first image means a captured image that photographs part or all of the area photographed by the first image. For example, if the first image is a photograph of City A and City B, then the photograph of City A is a captured image that photographs at least a portion of the first image. Note that multiple second images may be obtained for one first image, one second image may be obtained for multiple first images, and multiple second images may be obtained for multiple first images. A second image that is a captured image that photographs at least a portion of the first image is also called the second image corresponding to the first image.

[0027] The first image and the second image corresponding to the first image (also referred to as a set of the first and second images) are images taken of a predetermined area at different times or on different days. The set of the first and second images acquired in step S1 may be one or more. If two or more sets of the first and second images are acquired, some or all of the areas captured in each first image will be different.

[0028] The shooting range of the first and second images obtained in step S1 is not particularly limited and can be set as appropriate by the administrator or user. The shooting range may be the range corresponding to the information about the area to be searched included in the start request, or it may be a pre-set range. For example, if the area to be processed is entered as the information about the area to be searched in the start request, the first and second images corresponding to that area will be obtained. For example, if it is set in advance to search the 23 wards of Tokyo, the first and second images of the 23 wards of Tokyo will be obtained in step S1. Furthermore, the shooting range of the first and second images may be wider than that of the third image and the fourth image described later.

[0029] The first and second images may be images with a resolution of similar or lower resolution than the third and fourth images described later. The resolution of an image represents the distance on the ground corresponding to one side of a pixel, which is the smallest unit that makes up the image. For example, the resolution of the first and second images may be 5 km, and the resolution of the third and fourth images may be 1 m. Furthermore, it is preferable that the first and second images, or the third and fourth images, have the same resolution.

[0030] It is preferable that the first and second images, or the third and fourth images described later, have the same scale. Having the same scale means that the length in the real world corresponding to a unit distance (e.g., 1 inch) on the image is the same. Furthermore, the scale of the first and second images may be the same as that of the third and fourth images, or it may be smaller than that of the third and fourth images. The scale decreases as the length in the real world corresponding to a unit distance increases. For example, if the scale of the first and second images is 1 / 10,000, the scale of the third and fourth images may be 1 / 100.

[0031] The first image, the second image, the third image described later, and the fourth image described later may be optical images taken during the day, optical images taken at night (also called night light images), infrared images, or SAR images. In this case, it is preferable that the first and second images are lower resolution images than the third and fourth images. Alternatively, if the third and fourth images described later are optical images taken during the day, the first and second images may be optical images taken during the day, night light images, infrared images, or SAR images.

[0032] In step S1, once the first and second images are acquired, the server device 2 identifies the first region based on the first and second images (step S2).

[0033] The first region is the region where a change has occurred. The region where a change has occurred is the region in the real world where a predetermined change has occurred. A region is a concept that includes both an area with a predetermined range and a position that indicates a predetermined point. A region may correspond to a single pixel, or it may contain multiple pixels. A region may be represented as quadrilateral data selected from regions divided into a mesh at equal intervals, or as polygon data of a polygonal shape enclosed by lines.

[0034] The server device 2 compares images (for example, the first image and the second image) taken at different times in the same area with the same resolution, and can identify the area where a change has occurred if there is an area that satisfies predetermined conditions. The predetermined conditions are not particularly limited, but may include a change in the pixel (RGB or HSV) value within the area being greater than a predetermined value, or a difference being extracted by difference extraction.

[0035] For example, in step S2, first, the server device 2 performs alignment of the region shown in the first image with the region shown in the second image. Known processes can be applied to the alignment process. Next, the server device 2 determines whether predetermined conditions are met for each predetermined region in the first image and the second image. The predetermined region can be set as appropriate, but it may be a region corresponding to the resolution, or for example, a rectangular region containing nine pixels arranged in a 3x3 grid. The server device 2 can identify a part or all of the region that is determined to meet the predetermined conditions as the first region.

[0036] More specifically, let's describe an example where server device 2 uses RGB values ​​to identify a first region. RGB values ​​represent the color of a single pixel using R (red), G (green), and B (blue) values. Each of R, G, and B is represented by a value in the range of 256 levels from 0 to 255.

[0037] First, the server device 2 identifies the corresponding positions in the first and second images. For example, in each of the first and second images, the server device 2 identifies a group of pixels that have the same location (e.g., latitude and longitude) in the real world. The latitude and longitude of a pixel may be, for example, the latitude and longitude of the real-world location corresponding to the center position of the pixel. Next, the server device 2 identifies the amount of change of pixels within a window. A window is a portion that indicates a predetermined range within an image. A window is a rectangular portion containing multiple pixels. The number of pixels contained in one window can be appropriately designed according to the resolution of the image.

[0038] When determining the amount of change in pixels within a window, for example, server device 2 calculates the change in the RGB values ​​of pixels within the window. Specifically, for each pixel included in the window, the following calculation is performed between the corresponding pixels in the first and second images. First, server device 2 compares the pixels in the first and second images, adds the square of the difference in R values, the square of the difference in G values, and the square of the difference in B values, and multiplies these by the weighting values ​​within the window. Then, server device 2 can calculate the amount of change in pixels within the window by taking the square root of the multiplied values. The method of weighting within the window is not particularly limited, and known methods can be used. For example, weightings such as Gaussian filters and averaging filters can be used. The weighting values ​​can be set so that the weight increases towards the center of the window and decreases as you move away from the center.

[0039] After calculating the change in each pixel within the window, the server device 2 determines the change within the window by summing up all the pixel changes within the window. At this time, a weighted summation is performed within the window, so the change in the entire local area is reflected without depending on a single pixel. Next, the server device 2 moves the window up, down, left, or right (also called a sliding window) using a preset offset value, and similarly determines the change within the window. The window movement may be repeated until a predetermined range (e.g., 80%) or more of the first and second images have been processed.

[0040] Once the amount of change within each window is identified, the server device 2 performs a threshold determination for the amount of change within the window. For example, the server device 2 determines whether the amount of change within the window exceeds a predetermined threshold. If it exceeds the threshold, the server device 2 can identify that a change has occurred in the area included in the window that exceeded the threshold. The server device 2 can also identify this area as the first area where the change was detected. The first area may be the entire area of ​​the window, or it may be a part of the window identified by the offset value. For example, if the offset value is 1 pixel, the central 1 pixel within the identified window may be identified as the area where the change occurred. Alternatively, for example, if the offset value is 3 pixels, the central 3x3 area of ​​9 pixels within the identified window may be identified as the area where the change occurred.

[0041] When server device 2 generates polygon data, it identifies windows where the amount of change exceeds a threshold, similar to the above. For windows where the amount of change exceeds the threshold, server device 2 can generate polygon data by identifying the contour of the entire window or a portion of the window where changes have occurred.

[0042] Next, the server device 2 identifies the latitude and longitude (hereinafter referred to as latitude and longitude) of the first region identified in step S2 (step S3). The captured image acquired in step S1 is image data that allows for the identification of the latitude and longitude of each point or region in the captured image. Therefore, once the first region is identified in step S2, the server device 2 can identify the latitude and longitude corresponding to at least one location in the first region based on its position in the first or second image of the first region. The at least one location in the first region may be any predetermined point included in the first region in the first or second image. The predetermined point may be the center position within the identified first region. Also, if the first region is a rectangular area, the predetermined point may correspond to the top left, top right, bottom right, and bottom left points.

[0043] In step S3, when the latitude and longitude of the first area are specified, the server device 2 acquires a third image (step S4). The third image is a captured image of the ground taken from above, and is a captured image that captures at least a part of the first area. The third image may be a captured image that captures the entire first area. Since the captured image has the same meaning as the captured image described above, the description thereof is omitted.

[0044] Here, the third image is a captured image taken at the third time. The third time may be a time after the first time, may be a time before the second time, or may be a time between the second time and the first time. Also, the third image may be taken after the second time and within a predetermined period (for example, three days) from the first time, or may be the one with the most recent capture time. Regarding which third image to acquire, it may be specified according to the information on the change input in the start request and / or the information on the attributes of the real estate.

[0045] The captured image acquired in step S4 uses image data capable of specifying the capture date and time and the latitude and longitude of each point or each area in the captured image. Therefore, the server device 2 can specify the third image using the first time and / or the second time, and the latitude and longitude specified in step S3.

[0046] As described above, the third image may be a captured image with high resolution. As a captured image with high resolution, for example, the resolution may be 1 m or less. Also, the third image may be an optical image taken during the day.

[0047] Note that in step S4, when the server device 2 cooperates with an external system, the server device 2 transmits an acquisition request for the third image to another computer device. The acquisition request includes information on the capture date and time of the captured image to be acquired and information on the captured area (for example, the latitude and longitude specified in step S3). The external system that cooperates in step S4 and the external system that cooperates in step S1 may be the same system or different systems.

[0048] Note that the acquisition of the third image in step S4 may be executed according to an input when the user operates the user terminal 1. For example, in response to an input to the user terminal 1, a request for acquiring the third image may be transmitted, and thus the process of step S4 may be executed. Alternatively, the user inputs specific information capable of specifying the third image to the user terminal 1. Then, the specific information is transmitted from the user terminal 1 to the server device 2, and the server device 2 may acquire the third image based on the received specific information. The specific information includes, for example, information regarding the time when the captured image to be acquired was captured, information capable of specifying the first area, and the like. The information capable of specifying the first area is, for example, the latitude and longitude specified in step S3, the address corresponding to the first area, the place name corresponding to the first area, and the like.

[0049] When the third image is acquired in step S4, the server device 2 specifies a second area that satisfies a predetermined condition within the first area based on the third image. The predetermined condition may be, for example, that a predetermined change has occurred, or that it has a predetermined real estate attribute.

[0050] First, the server device 2 specifies a second area in which a predetermined change has occurred within the first area based on the third image (step S5). The change within the area specifies how the real estate has changed from what state to what state, or how it has changed from what state to what state, and the like.

[0051] The predetermined change is not particularly limited, and examples thereof include demolition, new construction, rebuilding, or repair. Demolition means that the building is disassembled and the building disappears from the area. New construction means building a building from an empty lot. Rebuilding means replacing the building with a new building. Repair means repairing the building, and for example, renovation and exterior work are applicable to repair.

[0052] The method by which the server device 2 identifies the second region where a predetermined change has occurred in the third image (captured image) is not particularly limited. For example, the server device 2 can use the first prediction model to identify the second region where a predetermined change has occurred based on the third image acquired in step S4. The first prediction model is a machine learning prediction model that takes image data (information such as RGB of each pixel constituting the image) in which a change (e.g., demolition, new construction, rebuilding, or repair) is clear from a reference (sample) captured image as input data, and information regarding the position within the captured image and the change in the region corresponding to that position as output data.

[0053] Here, image data showing the same change as the change identified in step S5 is used as input data. In this way, the server device 2 can identify the second region where a predetermined change occurred from the captured image. For example, if the third image is taken after the first time, the captured image of the region taken around the time the change was completed is used as input data. If the third image is taken before the second time, the captured image taken around the time the change occurred is used as input data. If the third image is taken between the second time and the first time, the captured image taken while the change was occurring is used as input data.

[0054] When server device 2 identifies demolition as a predetermined change, that is, when it identifies the location on the captured image corresponding to the area before demolition, the area during demolition, or the area after demolition, server device 2 uses a first prediction model that takes multiple image data of the area before demolition, the area during demolition, or the area after demolition, captured from above, as input data.

[0055] When server device 2 identifies new construction as a predetermined change, that is, when it identifies a location on the captured image corresponding to an area before construction begins, after construction begins, or during construction, or an area after completion, server device 2 uses a first prediction model that takes as input data multiple image data of the area before construction begins, after construction begins, or during construction, or after completion, of the building, as captured from above.

[0056] When server device 2 identifies rebuilding as a predetermined change, that is, when it identifies the location on the captured image corresponding to the area before the building is demolished, the area during the building's demolition, the area after construction has started or is under construction, or the area after the building's completion, server device 2 uses a first prediction model that takes as input data multiple image data of the area before the building is demolished, the area during the building's demolition, the area after construction has started or is under construction, or the area after the building's completion, all captured from above.

[0057] When server device 2 identifies repairs as a predetermined change, that is, when it identifies the location on the captured image corresponding to the area of ​​the building before repairs, the area of ​​the building during repairs, or the area of ​​the building after repairs, server device 2 uses a first prediction model that takes multiple image data of the area of ​​the building before repairs, the area of ​​repairs, or the area after repairs, captured from above, as input data.

[0058] The machine learning algorithm is not particularly limited and any known algorithm can be used, but it is preferable to use deep learning using a multilayer neural network. A multilayer neural network has an input layer, an output layer, and multiple hidden layers. Weights are assigned to the edges connecting the nodes in each layer. Each edge has a weight assigned to it corresponding to each input to the node. The weights corresponding to each input to the node are multiplied, and the value obtained by multiplying these weights is added to the bias. The resulting value is subjected to a nonlinear transformation using an activation function to calculate the activation value. The calculated activation value becomes the input value passed to the node of the next layer. The number of hidden layers can be designed as appropriate.

[0059] In step S5, when the server device 2 identifies a second region where a predetermined change has occurred, the server device 2 identifies a second region within the first region that has the attributes of a predetermined real estate based on the third image (step S6). The attributes identify the state of the real estate, how it is used, or what kind of buildings or facilities exist. In step S6, the server device 2 may also identify a second region having the attributes of a predetermined real estate from the second region where the predetermined change identified in step S5 has occurred.

[0060] The specified property attributes (also called specified attributes) are not particularly limited, but examples include vacant houses, idle land, parking lots, agricultural land, or material storage areas. A vacant house means a building that is not inhabited, and idle land means land that is not being used. A parking lot is land used as a place to park vehicles. Agricultural land is land used for agriculture, such as rice paddies and fields. A material storage area is land used as a place to store materials such as building materials.

[0061] Furthermore, a specified attribute may be the existence of a specified building. While not particularly limited, a specified building could be, for example, an apartment building, a house, or an office building. Additionally, a specified building could be one that is older than a specified number of years, or one that is younger than a specified number of years.

[0062] The method by which the server device 2 identifies the area corresponding to real estate having predetermined attributes in the third image (captured image) is not particularly limited. For example, the server device 2 can identify the area corresponding to real estate having predetermined attributes by identifying the attributes of real estate corresponding to each area of ​​the captured image based on information about the pixels constituting the captured image (information about RGB).

[0063] For example, the server device 2 can use the second prediction model to identify an area corresponding to real estate having predetermined attributes based on the third image acquired in step S4. The second prediction model is a machine learning prediction model that uses image data (information such as RGB of each pixel constituting the image) from a reference (sample) captured image in which the attributes of the real estate (e.g., vacant house, idle land, parking lot, agricultural land, or material storage area) are clear as input data, and information regarding the location within the captured image and the attributes of the real estate in the area corresponding to that location as output data. Here, image data having the same attributes as the predetermined attributes identified in step S6 is used as input data. In this way, the server device 2 can identify an area corresponding to real estate having predetermined attributes from the captured image.

[0064] When server device 2 identifies a vacant property with predetermined attributes, that is, when it identifies the location on the captured image corresponding to the vacant property, server device 2 uses a second prediction model that takes multiple image data of the vacant property taken from above as input data. In areas with snowfall, server device 2 can also use the condition of the snow accumulated on the house and its premises in the captured image as a factor in determining whether or not it is a vacant property.

[0065] Furthermore, when the server device 2 identifies an area on the third image that corresponds to land that is vacant land, a parking lot, or agricultural land, the server device 2 uses a second prediction model that takes multiple image data of each of the vacant land, parking lot, or agricultural land, taken from above, as input data.

[0066] The machine learning algorithms used are not particularly limited and publicly known algorithms can be used. Since the machine learning algorithms are the same as those described above, their explanation will be omitted.

[0067] Furthermore, if in step S5 the server device 2 does not identify the second area where a predetermined change has occurred, or if in step S6 the server device 2 does not identify the second area having the attributes of a predetermined property, the identification process ends.

[0068] On the other hand, in step S6, when the server device 2 identifies a second area having predetermined real estate attributes, the server device 2 identifies the latitude and longitude corresponding to at least one location in the identified second area based on the position in the third image of the second area that has been identified as having predetermined real estate attributes due to a predetermined change (step S7). Next, the server device 2 identifies the address of the real estate corresponding to the identified second area based on the position in the third image of the second area that has been identified as having predetermined real estate attributes due to a predetermined change (step S8). In step S8, the server device 2 may identify the address of the real estate corresponding to the latitude and longitude identified in step S7. Here, "address" is a concept that includes both residential address and land number. Residential address is an address established by a municipality based on the "Residential Address Act (Act No. 119 of 1962)," and land number is a number assigned to each property by the Legal Affairs Bureau.

[0069] The processing in steps S7 and S8 will now be explained. The storage unit 23 of the server device 2 has map data of the same region as the region where the third image (captured image) was taken pre-registered. In addition, the captured image acquired in step S4 is image data that allows for the identification of the latitude and longitude of each point or region in the captured image. The image data used is one in which the position and latitude and longitude within each image data are associated and stored. In the map data, the address (lot number or address) of each region or point is stored in association with the latitude and longitude of each region or point on the map.

[0070] Therefore, in steps S7 and S8, once the second region is identified, the server device 2 can identify the latitude and longitude corresponding to at least one location in the second region based on its position in the captured image of the second region, similar to step S3. The explanation that overlaps with step S3 is omitted. The server device 2 can refer to map data in which the addresses of each region or point are stored in association with the latitude and longitude of each region or point on the map, and identify the address (land number or address) corresponding to the latitude and longitude corresponding to at least one location in the identified second region.

[0071] In step S8, the user terminal 1 can identify the address of the real estate corresponding to the identified second area using a Cartesian coordinate system on a plane, in addition to using latitude and longitude to identify the address of the real estate corresponding to the identified second area. In this case, step S7 may be omitted. Figure 6 is a diagram illustrating the process of identifying an address according to an embodiment of the present invention. Map data 31 of the same area as the area where the captured image 32 (third image) was taken is pre-registered in the storage unit 23 of the server device 2.

[0072] In map data 31, the addresses of each property in this region are registered in association with the XY coordinates of a plane-based orthogonal coordinate system (XY coordinate system). A specific point in this region is set as the origin O. The north-south direction can be considered the Y-axis, with the north side being the first and second quadrants and the south side being the third and fourth quadrants. The east-west direction can be considered the X-axis, with the east side being the first and fourth quadrants and the west side being the second and third quadrants. The coordinates (X,Y) of the origin O can be represented as (0,0), and in Figure 6, the address of the origin O is registered as address E.

[0073] In step S2, a portion of the captured image 32 is identified as areas 33a and 33b, which correspond to real estate having predetermined attributes. By setting the scale of the map data 31 to the same scale as the captured image 32, and superimposing the points in the captured image 32 that correspond to specific points in the map data 31 with the origin O of the map data 31, and so that the direction of the captured image 32 and the direction of the map data 31 are the same, the address of each area in the captured image 32 can be identified. In other words, the map data 31 has addresses registered in association with XY coordinates, and according to this correspondence, the address of a region can be identified based on the XY coordinates of that region in the captured image 32. Here, the address of region 33a is address D, and the address of region 33b is address I.

[0074] If the address identified in step S8 is a residential address, the server device 2 identifies the land parcel corresponding to the residential address identified in step S7 based on the correspondence between residential addresses and land parcel numbers (step S9). The storage unit 23 of the server device 2 has an address master table registered in which land parcel numbers are stored in association with residential addresses, and by referring to the address master table, the server device 2 can identify the land parcel corresponding to the residential address identified in step S8.

[0075] Furthermore, if the processing in step S8 is performed based on photographic images of an area where the land number and address are the same, the processing in step S9 can be omitted. The land number identified in step S8 or S9 is used in step S11, described later, to identify the owner of real estate having a predetermined attribute. If the address identified in step S8 is a land number, step S9 is omitted, and the process proceeds from step S8 to step S10.

[0076] Next, the server device 2 identifies the relevant information corresponding to the address identified in step S8 based on the correspondence between the address and the relevant information corresponding to that address (step S10). The relevant information may include, for example, the land use zone of the property, building coverage ratio, floor area ratio, elementary and junior high schools in the school district, climate, projected future population, hazard information, and property valuation. In step S10, the relevant information corresponding to the identified latitude and longitude may also be identified based on the correspondence between the latitude and longitude and the relevant information corresponding to that latitude and longitude.

[0077] Land use zones for real estate are classifications of land use types defined in urban planning. Building coverage ratio is the percentage of a site on which a building can be constructed. Floor area ratio is the ratio of the building's floor area to the site area. The building coverage ratio and floor area ratio have upper limits set according to the land use zone of the real estate. Elementary and junior high schools in a designated school district are the elementary and junior high schools that prospective students in a designated area should attend. Climate refers to the average temperature, average precipitation, average snowfall, average sunshine, etc., of a designated area. Projected future population is an estimate of the future population of a designated area (for example, every five years). Hazard information is information about the risk of disasters for each designated area. Real estate valuation is information about the price of real estate. For example, real estate valuation includes the price of real estate calculated from publicly announced prices, road value, fixed asset tax valuation, and comparable sales prices in the surrounding area.

[0078] The method for identifying related information corresponding to an address or latitude and longitude is not particularly limited. The server device 2 may use data stored in which an address or latitude and longitude is associated with related information corresponding to said address or latitude and longitude to identify various related information corresponding to the latitude and longitude identified in step S7, or the address identified in step S8. Alternatively, the server device 2 may cooperate with a system composed of other computer devices to identify related information corresponding to the latitude and longitude identified in step S7, or the address identified in step S8. The control unit 11 may use open data to identify related information corresponding to the latitude and longitude identified in step S7, or the address identified in step S8. For example, the server device 2 may access a computer device that stores a database of related information provided by the Geospatial Information Authority of Japan or a local government, and receive related information corresponding to latitude and longitude or an address.

[0079] Next, the server device 2 identifies the owner of the real estate corresponding to the address identified in step S8 based on the correspondence between the address and the owner of the real estate corresponding to that address (step S11). The information regarding the identified real estate owner is stored in the storage unit 23 of the server device 2 in association with the information regarding the identified second area (step S12). The information regarding the owner is, for example, the name and contact information of the real estate owner. The information regarding the second area is, for example, the address of the second area (address and / or lot number), latitude and longitude, identified changes, and attributes of the real estate.

[0080] In step S11, the server device 2 may identify the owner and contact information of the real estate corresponding to the address identified in step S8, based on the correspondence between the address and the owner and contact information of the real estate corresponding to that address. If the server device 2 identifies a land parcel number in step S8 or S9, the server device 2 identifies the owner and contact information of the real estate corresponding to the identified land parcel number, based on the correspondence between the land parcel number and the owner of the real estate corresponding to the land parcel number.

[0081] The method for identifying the owner of the property corresponding to the address and the owner's contact information is not particularly limited, but it is preferable that the server device 2 uses data stored in association with the address and the owner of the property corresponding to that address to identify the owner of the property and their contact information. For example, the storage unit 23 of the server device 2 has an owner master table registered in association with the address (lot number) and stores the owner of the property corresponding to the address (lot number) and the owner of the property and their contact information. The server device 2 can identify the owner and their contact information corresponding to the address identified in step S8 or the lot number identified in step S8 or S9 by referring to the owner master table.

[0082] In addition, server device 2 may cooperate with a system consisting of other computer devices to identify the owner and their contact information corresponding to the land parcel number identified in step S8 or S9. In this case, server device 2 can cooperate with, for example, the online registration and deposit application system provided by the Ministry of Justice to identify the owner and their contact information corresponding to the address identified in step S8 or the land parcel number identified in step S8 or S9. Server device 2 can receive registration data from the online registration and deposit application system that records the owner and their contact information corresponding to the land parcel number.

[0083] The "owner" identified in step S11 is the owner's name. The contact information for the owner identified in step S11 is not limited to a landline phone number, mobile phone number, email address, fax number, address (residential address), postal code, etc. The identified owner's name and contact information are transmitted from the server device 2 to the user terminal 1 and displayed on the display unit 15 of the user terminal 1. This allows the user to contact the owner of real estate that has undergone a predetermined change and possesses predetermined attributes via telephone, email, fax, mail, etc. The choice of contact method can be appropriately changed depending on the purpose.

[0084] Next, in response to input from the user terminal 1, the server device 2 uses the contact information of the owner identified in step S11 to transmit predetermined information to the identified owner, that is, the owner of the property having the predetermined attributes (step S13). The identification process is completed by executing steps S1 to S13.

[0085] The predetermined information transmitted in step S13 is not particularly limited. The predetermined information can be stored in the storage unit 23 by the user operating the input unit 14 of the user terminal 1. The predetermined information stored in the storage unit 23 is read out when step S13 is executed.

[0086] The predetermined information transmitted to the property owner in step S13 can be appropriately modified according to the predetermined change, the type of predetermined attribute, the user's purpose, etc. For example, if the predetermined change is demolition, the server device 2 can send messages or proposals to the property owner for the sale of the property, a proposal to lease the land, a proposal to rebuild, etc. Also, for example, if the predetermined change is new construction or rebuilding, the server device 2 can send messages or proposals to the property owner for the proposal to rent the property, an introduction to a rental property agent, a proposal to install new equipment, etc. Also, for example, if the predetermined attribute is vacant land or an empty house, the server device 2 can send messages or proposals to the property owner for the sale of the property or a proposal to lease the land. Furthermore, the predetermined information may include the owner's name as the recipient and information regarding the property's address (lot number, street address) to identify which property the proposal pertains to.

[0087] In step S13, the method of transmitting the predetermined information is not particularly limited. For example, the predetermined information may be sent from the server device 2 to the identified owner via email or facsimile. The method of transmitting the predetermined information may be selected by the user by operating the input unit 14 of the user terminal 1.

[0088] Furthermore, instead of, or in addition to, the process of sending predetermined information to the property owner in step S13, the following may be performed: sending transmission information for sending predetermined information or sending information for sending a document to the owner identified in step S11 to another computer device; controlling the printing of the sending information onto a medium; and / or storing the sending information on a storage medium. The server device 2 can be appropriately designed to perform which of these processes after executing step S11. It is also possible to allow the user to select which of these processes to perform by operating the input unit 14 of the user terminal 1.

[0089] Server device 2 executes a process to send transmission information to another computer device for sending predetermined information to the owner identified in step S11. This enables the other computer device to send the predetermined information to the owner via email or facsimile. The transmission information includes the owner's name, contact information such as email address or facsimile number, and the address of the identified property (lot number, street address). Here, the other computer device may be operated by a different business or entity than the user.

[0090] Furthermore, the server device 2 executes a process to send delivery information for sending mail to the owner identified in step S11 to another computer device operated by another business operator, thereby enabling the mail to be sent to the owner by courier or postal service from the other business operator. The delivery information includes the owner's name, address (street address), contact information such as telephone number, and the address (lot number, street address) of the identified property. The contents of the mail can be changed as appropriate according to predetermined changes, predetermined attributes of the property, its purpose, etc. For example, if the predetermined attribute is idle land or an empty house, a message or proposal for selling, renting, or utilizing the property can be sent to the property owner.

[0091] The server device 2 executes a process to control the printing of delivery information (owner's name and address) for sending mail to the owner identified in step S11 onto a medium. For example, it can print a medium such as paper displaying the owner's name and address. By printing the owner's name and address on a medium such as paper and attaching it to the mailing, it becomes possible to send the mailing to the owner. The medium used here can be a sticker-like material with an adhesive coating on the back of the printed surface, which can be used by peeling off the release paper. The contents of the mailing can be changed as appropriate according to predetermined changes, predetermined attributes of the real estate, its purpose, etc.

[0092] The server device 2 can also perform processes such as storing delivery information (the owner's name and contact information, and the address (lot number) of the identified property) for sending the mail to the owner identified in step S11 on an external storage medium (e.g., optical disc, flash memory, hard disk). By handing over the external storage medium containing the delivery information to another business operator different from the user, it becomes possible for the other business operator to send the mail to the owner by courier or postal service. The contents of the mail can be changed as appropriate according to predetermined changes, predetermined attributes of the property, its purpose, etc.

[0093] Next, a second embodiment of the specific processing in the system according to the embodiment of the present invention will be described. The specific processing in the second embodiment differs from the specific processing in the first embodiment in that steps S4 to S6 are replaced with the following steps S21 to S24. Steps S1 to S3 and S7 to S13 are similar processes and will be omitted from explanation as necessary. In addition, the terms described in the first embodiment can be adopted to the extent necessary from those described in the first embodiment.

[0094] In the second embodiment, the processes in steps S1 to S3 described above are performed. In step S3, when the latitude and longitude of the first region are determined, the server device 2 acquires the third image and the fourth image (step S21). The fourth image is an image taken of the ground from above, and is an image that captures at least a part of the first region. The fourth image may be an image that captures the entire first region. The term "captured image" is synonymous with the "captured image" described above, so its explanation is omitted.

[0095] The fourth image is an image taken at the fourth time. If the first time when the first image was taken is later than the second time when the second image was taken, the third time when the third image was taken may be after the first time, and the fourth time may be before the second time. Alternatively, the third time may be within a predetermined range (for example, 3 days) from the first time, and the fourth time may be within a predetermined range from the second time. The predetermined range is not particularly limited and can be set as appropriate by the administrator or user.

[0096] The captured image acquired in step S21 is image data that allows for the identification of the date and time of capture and the latitude and longitude of each point or area in the captured image. Therefore, using the latitude and longitude identified in the first time, the second time, and in step S3, the server device 2 can identify the third and fourth images.

[0097] As described above, the third and fourth images may be high-resolution captured images. High-resolution captured images may, for example, have a resolution of 1 meter or less. Also, the third and fourth images may be optical images taken during the daytime. The third and fourth images may have the same resolution.

[0098] In step S21, if the server device 2 cooperates with an external system, the server device 2 sends an acquisition request for the third and fourth images to the other computer device. The acquisition request includes information about the date and time the images to be acquired were taken, and information about the area in which the images were taken (for example, the latitude and longitude identified in step S3). The external system that cooperates in step S4 and the external system that cooperates in step S1 may be the same system or may be different systems.

[0099] In addition, the acquisition of the third and fourth images in step S21 may be performed in response to input from the user operating the user terminal 1, similar to step S4.

[0100] In step S21, when the third and fourth images are acquired, the server device 2 identifies the second region where a change occurred within the first region based on the third and fourth images (step S22). The process of identifying the second region in step S22 is performed in the same way as the process of identifying the first region in step S2, so a detailed explanation is omitted.

[0101] Once the second region is identified in step S22, the server device 2 determines whether a predetermined change has occurred in the identified second region (step S23). The predetermined change determined in step S23 can be input in step S1.

[0102] In step S23, the server device 2 may determine whether a predetermined change has occurred in the second region by inputting the third or fourth image into the first prediction model, similar to the process in step S5. For example, if the image data corresponding to the third or fourth image is input into the first prediction model and the region where the predetermined change has occurred matches the second region identified in step S22, the server device 2 can determine that a predetermined change has occurred in the second region.

[0103] Alternatively, in step S23, the server device 2 may determine, based on the third and fourth images, whether a predetermined change has occurred in the identified second region. The method by which the server device 2 identifies the second region in which a predetermined change has occurred based on the third and fourth images is not particularly limited. For example, the server device 2 can use a fourth prediction model to determine whether the second region identified in step S22 is the second region in which a predetermined change has occurred. The fourth prediction model is a prediction model trained using machine learning, with input data being image data (information such as RGB of each pixel constituting the image) in which changes (e.g., demolition, new construction, rebuilding, or repair) are clear for two or more captured images of the same region taken at different times, and output data being information about the position within the captured image and the change in the region corresponding to that position.

[0104] When server device 2 determines whether the change in the second region is demolition, server device 2 uses a fourth prediction model that takes multiple image data of the region before demolition and the region after demolition, taken from above, as input data.

[0105] When server device 2 determines whether the change in the second area is due to new construction, server device 2 uses a fourth prediction model that takes as input data multiple image data of the area before construction began and the area after completion, both of which were photographed from above.

[0106] When server device 2 determines whether the change in the second area is due to rebuilding, server device 2 uses a fourth prediction model that takes as input data multiple image data of the area before and after rebuilding, taken from above.

[0107] When server device 2 determines whether the change in the second region is a repair, server device 2 uses a fourth prediction model that takes multiple image data of the region before and after the repair, taken from above, as input data.

[0108] The machine learning algorithms used are not particularly limited and publicly known algorithms can be used. Since the machine learning algorithms are the same as those described above, their explanation will be omitted.

[0109] If a predetermined change has occurred in the identified second area (YES in step S23), the server device 2 determines whether the identified second area has the attributes of a predetermined real estate (step S24). The attributes of the real estate determined in step S24 may be entered in step S1.

[0110] In step S24, the server device 2 may determine whether the second region has the attributes of a predetermined real estate by inputting the third or fourth image into the second prediction model, similar to the process in step S6. For example, if the server device 2 inputs image data corresponding to the third or fourth image into the second prediction model and the region having the attributes of a predetermined real estate matches the second region where a predetermined change was determined to have occurred in step S23, the server device 2 can determine that the second region has the attributes of a predetermined real estate.

[0111] If the identified second area has the attributes of a predetermined real estate (YES in step S24), the processes in steps S7 to S13 are executed on the identified second area. This completes the identification process according to the second embodiment. On the other hand, if it is determined in step S23 that no predetermined change has occurred in the second area (NO in step S23), or if it is determined in step S24 that the second area does not have the attributes of a predetermined real estate (NO in step S23), the identification process according to the second embodiment is completed.

[0112] Next, a third embodiment of the identification process in the system according to the embodiment of the present invention will be described. Figure 6 is a flowchart of the real estate and owner identification process according to the third embodiment of the present invention. The identification process of the third embodiment is performed by the following steps S31 to S43. The identification process of the third embodiment differs from the identification process of the first embodiment in that it performs the following steps S34 to S36 instead of steps S4 to S6. The processes of steps S31 to S33 and S37 to S43 are the same as the processes of steps S1 to S3 and S7 to S13, so their explanation will be omitted as necessary. In addition, the terms described in the first and second embodiments can be adopted to the extent necessary from the content described in the first and second embodiments.

[0113] In the third embodiment, steps S31 to S33 are performed in the same way as steps S1 to S3. In step S33, once the latitude and longitude of the first region are determined, the server device 2 acquires a third image (step S34). The acquisition of the third image may be performed in the same way as the process in step S4.

[0114] When the third image is acquired in step S34, the server device 2 transmits the third image to the user terminal 1, and the user terminal 1 displays the third image on the display unit 15. The user visually confirms the displayed third image. Then, the user operates the user terminal 1 to select an area on the displayed third image, thereby selecting the second area within the first area. As a result, the user terminal 1 accepts the selection of the second area (step S35).

[0115] The second area selected in step S35 can be arbitrarily selected by the user and may be an area where a predetermined change has occurred, an area having a predetermined property attribute, or both. When the third image is displayed on the user terminal 1, map data may be superimposed on the third image. The map data may show the address of the area shown in the third image, the land number, or the land use zone.

[0116] In the third image displayed in step S35, the outline of the first region identified in step S32 may be displayed, or it may be displayed in a manner that allows the latitude and longitude of the first region identified in step S33 to be understood (for example, as a marker). For example, in the third image, a marker indicating the center position of the first region may be displayed. Also in step S35, the server device 2 may change the display manner of each first region in the third image according to the degree to which a change has occurred in the first region. The degree to which a change has occurred in the first region corresponds, for example, to the amount of change in pixels or the amount of change within the window as described above. For example, changing the display manner means that the hue, intensity, or transparency of the color superimposed on the first region may be changed according to the amount of change within the window, or the display of the outline of the first region may be made to blink.

[0117] The user terminal 1 transmits information about the second area selected in step S35 to the server device 2. The server device 2 identifies the second area upon receiving the information about the second area (step S36).

[0118] When the second region is identified in step S36, the processes in steps S37 to S43 are executed, and the identification process of the third embodiment is completed. In steps S37 to S43, the processes in steps S7 to S13 are executed.

[0119] Note that the processing in step S34 may be omitted. In this case, the captured image displayed on the user terminal 1 when the selection of the second region is accepted in step S35 may be the first image and / or second image used in step S31. The first image and / or second image displayed in step S35 is a captured image of the first region identified in step S32. Alternatively, the user may actually go to the real-world region corresponding to the first region and confirm the second region. The user may operate the user terminal 1 and input information that can identify the second region (for example, an address) in step S35.

[0120] The processes in steps S34 to S36 may be executed in response to an operation on the user terminal 1. Also, the process in step S35 may be executed on the administrator terminal 3. For example, when the first area is identified in the processes in steps S1 to S3, one or more first areas are displayed on the user terminal 1. The user terminal 1 accepts the selection of a first area for identifying the second area and sends the execution request for step S35. When the execution request is received by the server device 2, step S34 is executed and the third image may be identified. Information regarding the identified third image, information regarding the first image, or information regarding the second image, and information regarding the identification of the second area are received by the administrator terminal 3. The administrator terminal 3 displays the first image, the second image, or the third image, and the information regarding the identification of the second area. The information regarding the identification of the second area is, for example, information regarding a predetermined change for identifying the second area, and / or information regarding the attributes of a predetermined property, which the user entered in step S1. The administrator then operates the administrator terminal 3 to select a region on the displayed image, thereby selecting the second region within the first region. This allows the administrator terminal 3 to accept the selection of the second region.

[0121] In addition, the above describes a method of accepting the selection of the second area through an operation on the user terminal 1 or the administrator terminal 3, but the acceptance of the selection of the second area is not limited to this. For example, in step S35, the server device 2 may perform the acceptance of the selection of the second area. In this case, the server device 2 can accept the selection of the second area through the processing in steps S5, S6, or S22.

[0122] [Other Embodiments] The system 10 according to the present invention is not limited to the first, second, and third embodiments described above, but can be modified within the scope of its gist. Furthermore, the configuration of the system 10 described above and the following configurations may be combined arbitrarily.

[0123] Note that the order of the first time and the second time may be reversed. For example, the first time may be before the second time. In this case, in the first embodiment, the third time may be after the second time, before the first time, or between the first and second times. In the second embodiment, the third time may be after the second time, and the fourth time may be before the first time.

[0124] The first region identified in step S2 or S32 may be one or more. If multiple first regions are identified, in steps S4, S21, or S34, multiple third images, or multiple third images and multiple fourth images, each of which is a photograph of a first region, are identified. The second region identified in steps S5, S6, or S22, or the second region selected in step S35 and identified in step S36, may be one or more. If multiple second regions are identified, the processing from step S7 or S37 onwards is performed for each second region. Therefore, in the identification process, the owners of the real estate and their contact information may be multiple.

[0125] Furthermore, the determination in step S23 as to whether a predetermined change has occurred in the second area, and / or the determination in step S24 as to whether a second area has the predetermined property attributes, may be performed in response to input from the user operating the user terminal 1. For example, the second area identified in step S22 is displayed on the user terminal 1. The user visually determines whether a predetermined change has occurred in the second area, or whether the second area has the predetermined property attributes. Then, in response to input to the user terminal 1, the user may input the determination result to execute the process in step S23 or S24. This process may also be performed on the administrator terminal 3.

[0126] Step S5 identifies a second region where a predetermined change has occurred from the third image, and step S23 determines whether a predetermined change has occurred in the second region. However, in step S1, the user may operate the input unit 14 of the user terminal 1 to select one of the above predetermined changes from options such as demolition, new construction, rebuilding, and repair. The user selects one of these changes depending on what kind of change they want to identify the owner of the property and their contact information.

[0127] Step S6 identifies an area corresponding to real estate having predetermined attributes from the third image, and step S24 determines whether the second area has the predetermined real estate attributes. However, in step S1, the user may operate the input unit 14 of the user terminal 1 to select the predetermined attributes from options such as vacant house, idle land, parking lot, or agricultural land. The user selects one attribute from these options depending on what kind of real estate owner and their contact information they wish to identify. Furthermore, in addition to selecting the predetermined attributes, in step S1, the user may operate the input unit 14 of the user terminal 1 to select, for example, the time when the area to be searched has the predetermined real estate attributes from options such as before the change occurred or after the change occurred. Depending on the selection, the server device 2 can identify when the third image acquired in step S4 was taken. Also, depending on the selection, the server device 2 can select the image to execute step S24 from the third image or the fourth image.

[0128] If the time when the property has the specified attributes is not selected, it is preferable that a third image is used in S24. In this case, it is preferable that the third image used in step S6 or S24 is an image taken after the first time or within a predetermined range from the first time. The third image used in step S6 or S24 may also be the one with the most recent date and time of capture.

[0129] Note that the processing in step S3 or S33 may be omitted. In this case, instead of latitude and longitude, information that can identify the first region, such as an address, place name, or area, may be specified. In steps S4, S21, or S34, the third image, or the third and fourth images, are identified based on the information that can identify the first region.

[0130] Note that the processing in step S4 may be omitted. In this case, in steps S5 and S6, the first image and / or second image used in step S1 can be used instead of the third image. The first image and / or second image used in steps S5 and S6 are images taken of the first region identified in step S2. In other words, the system 10 can identify the second region within the first region that satisfies predetermined conditions based on the third image, the first image, or the second image which has captured at least a part of the first region.

[0131] Note that the processing in step S21 may be omitted. In this case, in steps S22, S34, and S24, the first and second images used in step S1 can be used instead of the third and fourth images. The first and second images used in steps S22, S34, and S24 are images taken of the first region identified in step S2.

[0132] Steps S4 to S7, steps S21 to S24 and S7, or steps S34 to S37 may be omitted. In this case, step S8 or S38 uses the latitude and longitude identified in step S3 or S33 to identify the address of the real estate corresponding to the first area. The address corresponding to the first area only needs to be an address corresponding to at least a part of the area within the first area. Also, the address corresponding to the first area may be one or more addresses. Then, the server device 2 executes the processes in steps S9 to S11 or S39 to S41 in the same manner as above, and can identify the owner of the real estate corresponding to an address based on the correspondence between the address corresponding to the first area and the owner of the real estate corresponding to that address.

[0133] Furthermore, when a predetermined change occurs in the first area, and / or when the first area has predetermined property attributes, the server device 2 may identify the address of the property corresponding to the first area, and may also identify the owner of the property corresponding to the identified address. In this embodiment, the system 10 omits steps S21 and S22 for the first area identified in steps S1 to S3, and executes steps S23 and / or S24. Then, the processing from step S7 onward is executed.

[0134] The above describes an embodiment in which the system 10 identifies a second region where a predetermined change has occurred within the first region, and a second region having predetermined real estate attributes within the first region, based on the third image, or the third and fourth images. However, the system is not limited to this embodiment. For example, the processing in step S5 or step S23 may be omitted. Also, for example, the processing in step S6 or step S24 may be omitted. In other words, the system 10 may identify a second region where a predetermined change has occurred within the first region, or a second region having predetermined real estate attributes within the first region, based on the third image, or the third and fourth images.

[0135] In the second embodiment, steps S23 and S24 may be omitted. Alternatively, the first, second, third, or fourth images of the second region captured in step S22 may be used to perform the processing from step S35 onward in the third embodiment.

[0136] Note that the processing in step S10 or S40 may be performed after step S7 or S37. Alternatively, after the processing up to step S7 or S37 and the processing in step S10 or S40 have been performed, the processing in steps S8, S9, S11, and S13, or steps S38, S39, S41, and S43 may be performed in response to the operation input to the user terminal 1 or for the second area selected by the user terminal 1. Or, after the processing up to step S8 or S38 and the processing in step S10 or S40 have been performed, the processing in steps S9, S11, and S13, or steps S39, S41, and S43 may be performed in response to the operation input to the user terminal 1 or for the second area selected by the user terminal 1.

[0137] Furthermore, the server device 2 can perform a process to extract contours using a known method based on the third image acquired in step S4, and divide the third image into multiple regions demarcated by contours. Then, for each of these multiple regions, the server device 2 can use the first prediction model and / or the second prediction model to determine whether or not it corresponds to a real estate where a predetermined change has occurred, and / or a real estate with predetermined attributes.

[0138] Furthermore, the processing in steps S4, S21, or S34 may be a process for acquiring an image with different properties from the captured image (first image and second image) used to identify the first region. An image with different properties from the first and second images may, for example, have a different resolution, be captured using a different wavelength, or be captured at a different time of day. For example, if the first and second images are visible light images, an image captured using a different wavelength may be a thermal infrared image or a SAR image. The system 10 can identify the first region where a change has occurred by processing steps S1 to S4, steps S1 to S3 and S21, or steps S1 to S3 and S34, and further identify an image with different properties that captures that first region.

[0139] In the above-described embodiment, a communication connection was established between the user terminal 1 and / or the administrator terminal 3 and the server device 2, and a specific process was executed. However, for example, the specific process may be executed on the user terminal 1. In this case, the process executed by the server device 2 in the above-described embodiment is executed on the control unit 11 of the user terminal 1. Information necessary for the process on the user terminal 1 may be pre-stored in the storage unit 13 or read from an external storage device.

[0140] The user can operate the user terminal 1 to request the execution of steps S8, S11, S13, S38, S41, or S43. The system 10 may also charge the user when the execution of steps S8, S11, S13, S38, S41, or S43 is performed. For example, after the execution of step S8 or S38, the system 10 may control the user terminal 1 to display the address of the real estate corresponding to the identified second area, as well as the identified changes, the attributes of the identified real estate, and / or map information indicating the second area. If the user selects the request button to execute the process of step S11 or S41 displayed on the display screen of the user terminal 1, the processes of steps S9 to S11 or S39 to S41 may be executed, and the user may be charged.

[0141] Thus, a system comprising at least one computer device includes: a first region identification means for identifying a first region where a change has occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; a selection receiving means for accepting the selection of a second region within the first region based on a third image capturing at least a portion of the first region, the first image, or the second image; and an address identification means for identifying an address corresponding to the second region. Since the first image, the second image, and / or the third image are images taken of the ground from above, the address corresponding to the second region within the first region where a change has occurred can be identified. Furthermore, the address corresponding to the region where a change has occurred can be discovered quickly.

[0142] Thus, a system comprising at least one computer device includes a first region identification means for identifying a first region where a change has occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image, and a second region identification means for identifying a second region within the first region that satisfies predetermined conditions based on a third image that captures at least a portion of the first region. Since the first image, the second image, and the third image are images taken of the ground from above, the second region within the first region that satisfies the predetermined conditions can be identified. Furthermore, regions where changes have occurred can be detected as quickly as possible.

[0143] Furthermore, because the first and second images are lower-resolution images than the third image, the burden of identifying a second region that satisfies predetermined conditions within the first region is reduced. For example, processing speed can be improved and processing costs can be reduced. Also, because the third image is an optical image taken during the day, and the first and second images are optical, infrared, or SAR images taken at night, when identifying a second region that satisfies predetermined conditions from the first region, images of different properties are used, allowing the second region to be identified from different perspectives. For example, by identifying areas with increased population or areas that are growing or developing based on changes in nighttime light images or infrared images, specific changes can be identified using optical images taken during the day. Also, for example, by identifying areas where changes in topography have occurred based on changes in SAR images, specific changes can be identified using optical images taken during the day. Furthermore, by using images of different properties, all second regions that have changed can be detected without omission.

[0144] Furthermore, since the first time period belongs to a different day than the second time period and is later than the second time period, and the first and second images are images taken during a predetermined time period, the first region can be identified based on the first and second images, excluding time-dependent changes.

[0145] Furthermore, the second area identification means can identify a second area in the first area where a predetermined change has occurred, and / or a second area having predetermined real estate attributes, based on the third image. Furthermore, the second domain identification means uses a machine learning-trained predictive model, which takes image data relating to a photograph taken of the ground from above as input data and information regarding the position within the photograph and changes or property attributes in the area corresponding to that position as output data, to identify a second domain having predetermined property attributes. Thus, the second domain identification means can identify a second domain having predetermined property attributes within the first domain using a machine learning-trained predictive model.

[0146] Furthermore, the second region identification means can accurately identify the second region where a change occurred within the first region by identifying the second region based on the third image taken at the third time and the fourth image taken at the fourth time, which captures at least a part of the first region. In addition, for the purpose of accurately identifying the second region, it is preferable that the first and second images are lower-resolution images than the third and fourth images, or that the third and fourth images are optical images taken during the day, and the first and second images are optical images, infrared images, or SAR images taken at night. Similarly, for the purpose of accurately identifying the second region, it is preferable that the first time belongs to a different day than the second time and is later than the second time, the third time is after the first time, and the fourth time is before the second time.

[0147] Furthermore, by providing address identification means for identifying an address corresponding to the second area, the system can identify an address corresponding to the second area. Furthermore, by providing address identification means for identifying latitude and longitude corresponding to at least one location within the second area and identifying an address corresponding to the identified latitude and longitude, the system can identify the address of real estate corresponding to the latitude and longitude corresponding to at least one location within the second area. Furthermore, by providing owner identification means for identifying the owner of real estate corresponding to the address identified by the address identification means, based on the correspondence between an address and the owner of the real estate corresponding to the address, the system can identify the owner of real estate corresponding to an address in the second area that satisfies predetermined conditions.

[0148] Thus, a system comprising at least one computer device includes: a first area identification means for identifying a first area where a change has occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; an address identification means for identifying an address corresponding to the first area; and an owner identification means for identifying the owner of real estate corresponding to the address identified by the address identification means based on the correspondence between the address and the owner of the real estate corresponding to the address. Since the first and second images are images taken from above the ground, the owner of real estate at the address corresponding to the first area where a change has occurred can be identified. Furthermore, the owner identification means can identify the owner of real estate at the address corresponding to the first area where a predetermined change has occurred and / or the first area has predetermined real estate attributes by identifying the owner of real estate corresponding to the address identified by the address identification means when a predetermined change has occurred in the first area and / or when the first area has predetermined real estate attributes.

[0149] Furthermore, the owner identification means can identify the owner and contact information of the real estate corresponding to the address by identifying the owner and contact information of the real estate corresponding to the address identified by the address identification means, based on the correspondence between the address and the owner and contact information of the real estate corresponding to that address. Also, if the address identified by the address identification means is a land lot number, the owner identification means can identify the owner of the real estate corresponding to the identified land lot number by identifying the owner of the real estate corresponding to the identified land lot number, based on the correspondence between the land lot number and the owner of the real estate corresponding to the land lot number.

[0150] 1 User terminal 2 Server device 3 Administrator terminal 4 Communication network 10 System 11 Control unit 12 RAM 13 Storage unit 14 Input unit 15 Display unit 16 Communication interface 21 Control unit 22 RAM 23 Storage unit 24 Communication interface 31 Map data 32 Captured image 33 Area

Claims

1. A system comprising at least one computer device, comprising: a first region identification means for identifying a first region in which a change has occurred, based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; a selection acceptance means for accepting a selection of a second region within the first region, based on a third image capturing at least a portion of the first region, the first image, or the second image; and an address identification means for identifying an address corresponding to the second region, wherein the first image, the second image, and / or the third image are images taken of the ground from above.

2. A system comprising at least one computer device, comprising: a first region identification means for identifying a first region in which a change has occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; and a second region identification means for identifying a second region within the first region that satisfies predetermined conditions based on a third image capturing at least a portion of the first region, wherein the first image, the second image, and the third image are images taken of the ground from above.

3. The system according to claim 1 or 2, wherein the first image and the second image are captured images with a lower resolution than the third image.

4. The system according to claim 1 or 2, wherein the third image is an optical image taken during the daytime, and the first and second images are optical images, infrared images, or SAR images taken at night.

5. The system according to any one of claims 1 to 4, wherein the first time is on a different day than the second time and is later than the second time, and the first image and the second image are images taken during a predetermined time period.

6. The system according to any one of claims 2 to 5, wherein the second area identification means identifies a second area in the first area where a predetermined change has occurred, and / or a second area having predetermined real estate attributes, based on the third image.

7. The system according to claim 6, wherein the second region identification means uses a machine learning-trained prediction model to identify a second region where a predetermined change has occurred, with input data relating to an aerial photograph of the ground, and output data relating to a position within the photograph and a change in a region corresponding to that position.

8. The system according to claim 6 or 7, wherein the second area identification means uses image data relating to a photograph taken of the ground from above as input data, and uses a machine learning-trained predictive model to identify a second area having predetermined real estate attributes, using information relating to the location within the photograph and the attributes of real estate in the area corresponding to that location as output data.

9. The system according to any one of claims 2 to 8, wherein the second region identification means identifies a second region in which a change occurred within the first region based on the third image taken at the third time and the fourth image taken at the fourth time, which captures at least a part of the first region, and the first and second images are lower-resolution captured images than the third and fourth images, or the third and fourth images are optical images taken during the day, and the first and second images are optical images, infrared images, or SAR images taken at night.

10. The system according to claim 9, wherein the first time is on a different day from the second time and is later than the second time, the third time is after the first time, and the fourth time is before the second time.

11. The system according to any one of claims 2 to 10, comprising address identification means for identifying an address corresponding to the second area.

12. The system according to any one of claims 1 to 11, wherein the address identification means identifies latitude and longitude corresponding to at least one location within the second area, and identifies an address corresponding to the identified latitude and longitude.

13. The system according to any one of claims 1 to 12, comprising: an owner identification means for identifying the owner of real estate corresponding to an address identified by an address identification means, based on the correspondence between an address and the owner of real estate corresponding to said address.

14. A system comprising at least one computer device, comprising: a first region identification means for identifying a first region in which a change has occurred, based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; an address identification means for identifying an address corresponding to the first region; and an owner identification means for identifying the owner of real estate corresponding to an address identified by the address identification means, based on the correspondence between an address and the owner of real estate corresponding to the address, wherein the first image and the second image are images taken of the ground from above.

15. The system according to claim 13 or 14, wherein the owner identification means identifies the owner of real estate corresponding to an address identified by the address identification means when a predetermined change occurs in the first area and / or when the first area has predetermined real estate attributes.

16. The system according to any one of claims 13 to 15, wherein the owner identification means identifies the owner of the real estate corresponding to the address identified by the address identification means, based on the correspondence between an address and the owner of the real estate corresponding to that address and the owner's contact information.

17. The system according to any one of claims 13 to 16, wherein the address identified by the address identification means is a land lot number, and the owner identification means identifies the owner of the real estate corresponding to the identified land lot number based on the correspondence between the land lot number and the owner of the real estate corresponding to the land lot number.

18. A program comprising: a computer device functioning as a first region identification means for identifying a first region where a change has occurred, based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; a selection receiving means for accepting the selection of a second region of the first region based on a third image capturing at least a portion of the first region, the first image, or the second image; and an address identification means for identifying an address corresponding to the second region, wherein the first image, the second image, and / or the third image are images taken of the ground from above.

19. A program comprising a computer device functioning as a first region identification means for identifying a first region where a change has occurred, based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image, and a second region identification means for identifying a second region within the first region that satisfies predetermined conditions, based on a third image which captures at least a portion of the first region, wherein the first image, the second image, and the third image are images taken of the ground from above.

20. A program comprising: a computer device that functions as a first region identification means for identifying a first region where a change has occurred, based on a first image taken at a first time and a second image taken at a second time which captures at least a portion of the first image; an address identification means for identifying an address corresponding to the first region; and an owner identification means for identifying an owner of real estate corresponding to an address identified by the address identification means, based on the correspondence between an address and the owner of real estate corresponding to the address, wherein the first image and the second image are images taken of the ground from above.

21. A method to be performed in a system comprising at least one computer device, comprising: a first region identification step of identifying a first region in which a change has occurred, based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; a selection acceptance step of accepting the selection of a second region of the first region based on a third image capturing at least a portion of the first region, the first image, or the second image; and an address identification step of identifying an address corresponding to the second region, wherein the first image, the second image, and / or the third image are images taken of the ground from above.

22. A method to be performed in a system comprising at least one computer device, comprising: a first region identification step of identifying a first region in which a change has occurred based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; and a second region identification step of identifying a second region in the first region that satisfies predetermined conditions based on a third image capturing at least a portion of the first region, wherein the first image, the second image, and the third image are images taken of the ground from above.

23. A method to be performed in a system comprising at least one computer device, comprising: a first region identification step of identifying a first region in which a change has occurred, based on a first image taken at a first time and a second image taken at a second time, which captures at least a portion of the first image; an address identification step of identifying an address corresponding to the first region; and an owner identification step of identifying an owner of real estate corresponding to an address identified by the address identification step, based on the correspondence between an address and the owner of real estate corresponding to the address, wherein the first image and the second image are images taken of the ground from above.

Images