Homestead use state analysis method and system

Abstract

The invention belongs to the technical field of homestead management. The invention provides a homestead use state analysis method and system. The method comprises the following steps: shooting a first high-definition image of a first target homestead and a second high-definition image of a similar second target homestead in an analysis area; extracting a first building contour feature of the first target homestead based on each first high-definition image, and constructing a first three-dimensional structure of the first target homestead according to the first building contour feature; extracting a second building contour feature of the second target homestead based on each second high-definition image, and inputting the first three-dimensional structure and the second building contour feature into the three-dimensional structure restoration model to obtain a predicted second three-dimensional structure; and calculating a structural deviation value between the second three-dimensional structure and the first three-dimensional structure, and when the structural deviation value is lower than a deviation threshold value, judging that the first target homestead is in a use state. Through the cooperation of the unmanned aerial vehicle and the ground terminal, the accurate judgment of the use state of the homestead is realized, and a large amount of visiting manpower does not need to be configured.

Description

Technical Field

[0001] The present invention relates to the technical field of homestead management, and in particular to a method and system for analyzing the use status of a homestead. Background Art

[0002] Analyzing and monitoring the use status of homesteads is the key to achieving effective management and use of homesteads. The existing determination of the use status of homesteads is basically done by manpower, that is, relevant personnel determine whether the homestead is in use or idle through visits and other methods. However, this method is very inefficient and requires the deployment of a large number of personnel, which is not economical. The solution of the present invention is to improve this technical problem. Summary of the invention

[0003] In this regard, the present invention provides a method, system, electronic device, computer storage medium and computer program product for analyzing the usage status of a homestead to solve the above-mentioned technical problems.

[0004] The present invention discloses a method for analyzing the use status of a homestead, and the method comprises the following steps:

[0005] A plurality of first high-definition images of a first target homestead in the analysis area and a plurality of second high-definition images of a plurality of second target homesteads similar to the first target homestead are photographed by a drone; wherein the first high-definition images are photographed at different angles from each other, and the second high-definition images are photographed at different angles from each other;

[0006] The ground terminal extracts the first building outline features of the first target homestead based on each of the first high-definition images, and constructs a first three-dimensional structure of the first target homestead based on the first building outline features;

[0007] The ground terminal extracts the second building outline features of each second target homestead based on each second high-definition image, inputs the first three-dimensional structure and the second building outline features into a three-dimensional structure restoration model based on artificial intelligence, and obtains a predicted second three-dimensional structure;

[0008] The structural deviation value between the second three-dimensional structure and the first three-dimensional structure is calculated. If the structural deviation value is lower than the deviation threshold, the first target homestead is determined to be in use; otherwise, the first target homestead is determined to be idle.

[0009] In some embodiments, before taking a plurality of first high-definition images of a first target homestead within the analysis area by using a drone, the method further includes:

[0010] The drone takes a third high-definition image of the analysis area, and the ground terminal determines each homestead area from the third high-definition image, and determines and obtains a regional high-definition image corresponding to each homestead area in the third high-definition image;

[0011] Furthermore, the ground terminal performs color quantity analysis on the regional high-definition images of each of the homestead areas, and determines each of the first target homesteads based on the obtained color quantities.

[0012] In some embodiments, the plurality of first high-definition images of a first target homestead in the analysis area and the plurality of second high-definition images of a plurality of second target homesteads adjacent to the first target homestead taken by the drone include:

[0013] deriving the type of buildings in the analysis area based on the third high-definition image, determining the building height according to the type, and determining a group of shooting angles according to the building height, specifically, the angle span range corresponding to the group of shooting angles is inversely proportional to the building height;

[0014] The drone is controlled to shoot several first high-definition images of a first target homestead within the analysis area and several second high-definition images of several second target homesteads adjacent to the first target homestead according to the group of shooting angles.

[0015] In some embodiments, a plurality of second high-definition images of a plurality of second target homesteads similar to the first target homestead in the analysis area are taken by a drone, including:

[0016] deriving a first number of other homesteads with similar building types to the first target homestead within the analysis area based on the third high-definition image analysis, and determining a second number based on the first number;

[0017] Determine the second number of the second target homesteads adjacent to the first target homestead within the analysis area.

[0018] In some embodiments, the three-dimensional structure restoration model is constructed based on a large model, and the large model is fine-tuned using small sample training data to obtain the three-dimensional structure restoration model.

[0019] In some embodiments, calculating the structural deviation value between the second three-dimensional structure and the first three-dimensional structure includes:

[0020] Decomposing the second three-dimensional structure and the first three-dimensional structure into a plurality of second three-dimensional substructures and a plurality of first three-dimensional substructures according to building units;

[0021] Determine the corresponding second three-dimensional substructure and the first three-dimensional substructure based on the same position principle, and calculate the first structural deviation value of the second three-dimensional substructure and the first three-dimensional substructure;

[0022] The first structural deviation values ​​are fused and calculated to obtain a second structural deviation value.

[0023] The present invention also discloses a homestead use status analysis system, the system comprising a processing device and a storage device, the processing device retrieves and executes computer codes in the storage device to implement the following method steps:

[0024] A plurality of first high-definition images of a first target homestead in the analysis area and a plurality of second high-definition images of a plurality of second target homesteads similar to the first target homestead are photographed by a drone; wherein the first high-definition images are photographed at different angles from each other, and the second high-definition images are photographed at different angles from each other;

[0025] The ground terminal extracts the first building outline features of the first target homestead based on each of the first high-definition images, and constructs a first three-dimensional structure of the first target homestead based on the first building outline features;

[0026] The ground terminal extracts the second building outline features of each second target homestead based on each second high-definition image, inputs the first three-dimensional structure and the second building outline features into a three-dimensional structure restoration model based on artificial intelligence, and obtains a predicted second three-dimensional structure;

[0027] The structural deviation value between the second three-dimensional structure and the first three-dimensional structure is calculated. If the structural deviation value is lower than the deviation threshold, the first target homestead is determined to be in use; otherwise, the first target homestead is determined to be idle.

[0028] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in any of the preceding items.

[0029] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0030] The present invention also discloses a computer program product. When the computer program product is run on a terminal, the terminal implements any of the above methods when executing the computer program product.

[0031] The solution of the present invention uses the cooperation of the drone and the ground terminal to achieve accurate judgment on the usage status of the homestead, without the need to configure a large number of visiting manpower, and can significantly improve the analysis efficiency of the usage status of the homestead. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 is a schematic diagram of a scenario in which a drone is used to detect the use status of a homestead, as disclosed in an embodiment of the present invention;

[0034] Figure 2 It is a flow chart of a method for analyzing the use status of a homestead disclosed in an embodiment of the present invention;

[0035] Figure 3 It is a structural schematic diagram of a homestead usage status analysis system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0037] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0038] like Figure 1 , Figure 2 As shown, an embodiment of the present invention discloses a method for analyzing the use status of a homestead, and the method comprises the following steps:

[0039] A plurality of first high-definition images of a first target homestead in the analysis area and a plurality of second high-definition images of a plurality of second target homesteads similar to the first target homestead are photographed by a drone; wherein the first high-definition images are photographed at different angles from each other, and the second high-definition images are photographed at different angles from each other;

[0040] The ground terminal extracts the first building outline features of the first target homestead based on each of the first high-definition images, and constructs a first three-dimensional structure of the first target homestead based on the first building outline features;

[0041] The ground terminal extracts the second building outline features of each second target homestead based on each second high-definition image, inputs the first three-dimensional structure and the second building outline features into a three-dimensional structure restoration model based on artificial intelligence, and obtains a predicted second three-dimensional structure;

[0042] The structural deviation value between the second three-dimensional structure and the first three-dimensional structure is calculated. If the structural deviation value is lower than the deviation threshold, the first target homestead is determined to be in use; otherwise, the first target homestead is determined to be idle.

[0043] Compared with the traditional method of determining by human visits, the present invention uses a drone to shoot high-definition images of the target homestead that needs to be analyzed for usage status, and analyzes the usage status of the homestead buildings extracted from the high-definition images. Specifically, the drone shoots several first high-definition images of the first target homestead in the analysis area, and several second high-definition images of several second target homesteads similar to the first target homestead. The first high-definition image and the second high-definition image are multiple images taken from different shooting angles, which is conducive to the subsequent generation of accurate three-dimensional structures of the homestead. The ground terminal located on the ground and operated by relevant personnel receives the first high-definition image and the second high-definition image, and extracts the first building outline features of the buildings (houses, walls, etc.) in the first target homestead from each first high-definition image, and the first three-dimensional structure of the first target homestead can be constructed based on this. The first three-dimensional structure reflects the real three-dimensional structural state of each building in the first target homestead. At the same time, the contour features of the buildings of each second target homestead are extracted from each second high-definition image, and all the contour features are integrated into the second building contour features; the first three-dimensional structure and the second building contour features are input into the three-dimensional structure restoration model based on artificial intelligence, and the three-dimensional structure restoration model predicts the second three-dimensional structure of each building of the first target homestead under the guidance of the second building contour features. The second three-dimensional structure reflects the three-dimensional structural state that the first target homestead should have under normal use and maintenance. Finally, by comparing the structural deviation value between the real first three-dimensional structure and the predicted second three-dimensional structure, it is possible to determine whether the first target homestead is in use or idle.

[0044] Therefore, the solution of the present invention uses the cooperation between the drone and the ground terminal to achieve accurate judgment of the usage status of the homestead, without the need to configure a large number of visiting manpower, which can significantly improve the analysis efficiency of the usage status of the homestead.

[0045] It should be noted that the present invention does not specifically limit the selection of the drone, the configuration of the camera, and the communication and control method between the drone and the ground terminal.

[0046] In some embodiments, before taking a plurality of first high-definition images of a first target homestead within the analysis area by using a drone, the method further includes:

[0047] The third high-definition image of the analysis area is taken by the drone, and the ground terminal determines each homestead area from the third high-definition image, and determines and obtains the regional high-definition image corresponding to each homestead area in the third high-definition image;

[0048] Furthermore, the ground terminal performs color quantity analysis on the regional high-definition images of each of the homestead areas, and determines each of the first target homesteads based on the obtained color quantities.

[0049] In an embodiment of the present invention, when the analyst arrives at the analysis area, the drone is released, and the drone first takes a third high-definition image (such as a panoramic image) of the entire analysis area and transmits it to the ground terminal. The ground terminal first determines each homestead area from it, and determines the regional high-definition image corresponding to each homestead area in the third high-definition image. Then, since when the homestead is in use, there will be objects such as clothes, food, and parked cars, and the colors of these objects are usually different and relatively bright compared to the building itself. Therefore, the number of colors of the high-definition images of each area is analyzed, and the first target homestead is determined from each homestead area based on the number of colors obtained by the analysis. Specifically, when the number of colors is lower than the color number threshold, it can be preliminarily determined that the homestead is in an idle state, and it is used as the first target homestead for subsequent targeted analysis; otherwise, it can be preliminarily determined that the homestead is in use and is not used as the first target homestead.

[0050] In some embodiments, the plurality of first high-definition images of a first target homestead in the analysis area and the plurality of second high-definition images of a plurality of second target homesteads adjacent to the first target homestead taken by the drone include:

[0051] deriving the type of buildings in the analysis area based on the third high-definition image, determining the building height according to the type, and determining a group of shooting angles according to the building height, specifically, the angle span range corresponding to the group of shooting angles is inversely proportional to the building height;

[0052] The drone is controlled to shoot several first high-definition images of a first target homestead within the analysis area and several second high-definition images of several second target homesteads adjacent to the first target homestead according to the group of shooting angles.

[0053] In the embodiment of the present invention, by shooting the image of the target homestead at different angles, it is helpful to accurately analyze and obtain the three-dimensional structure data of the buildings in the target homestead, and then it is helpful to accurately construct the first three-dimensional structure of each building in the first target homestead. At the same time, the determination of the shooting angle should also be appropriate, not too much or too little.

[0054] In view of the above requirements, the present invention first analyzes the type of building in the analysis area based on the third high-definition image obtained by the aforementioned shooting, and then determines the building height according to the building type. For example, if the type of building analyzed is a bungalow, the building height is determined to be 5 meters, and if the type of building analyzed is a building, the building height is determined to be 10 meters, etc., which can be determined by the building type-height comparison table. Furthermore, according to the aforementioned determined building height, a group of shooting angles are determined, and specifically, the angle span range corresponding to the group of shooting angles is inversely proportional to the building height, that is, the higher the height of the building in the analysis area, the easier it is to capture the three-dimensional structure data of the building, and the smaller the difference between the maximum angle value and the minimum angle value of the group of shooting angles is set at this time; and the lower the height of the building in the analysis area, due to the insufficient building height, it is more difficult to capture the clear three-dimensional structure data of the building, and the larger the difference between the maximum angle value and the minimum angle value of the group of shooting angles is set at this time, so that the calculation deviation caused by the visual error can be overcome (generally lower than the actual height of the building).

[0055] It should be noted that the number of angles in the group of shooting angles can also be adjusted accordingly, that is, the number of angles corresponding to the group of shooting angles is inversely proportional to the height of the building. Such a setting is also conducive to extracting a more accurate three-dimensional structure of the building.

[0056] In some embodiments, a plurality of second high-definition images of a plurality of second target homesteads similar to the first target homestead in the analysis area are taken by a drone, including:

[0057] deriving a first number of other homesteads with similar building types to the first target homestead within the analysis area based on the third high-definition image analysis, and determining a second number based on the first number;

[0058] Determine the second number of the second target homesteads adjacent to the first target homestead within the analysis area.

[0059] In an embodiment of the present invention, the second building outline feature extracted from the second target homestead can be used to assist the three-dimensional structure restoration model in "restoring" the first three-dimensional structure to the three-dimensional structure state that the first target homestead should have under normal use and maintenance. In order to ensure the accuracy of the second three-dimensional structure predicted by the three-dimensional structure restoration model, it is necessary that the second building outline feature contains an appropriate number of outline features of the second target homestead. In this regard, the present invention adopts the following scheme:

[0060] The third high-definition image is continuously used to analyze and obtain the first number of other homesteads with similar building types to the first target homestead. For example, if the building of the first target homestead is a bungalow, other homesteads with the same bungalow type are determined from the third high-definition image, and then the second number is determined based on the first number of these other homesteads. Then, the second number of second target homesteads with similar characteristics to the first target homestead is screened around the first target homestead.

[0061] Therefore, by analyzing the number of other homesteads with the same type of buildings in the analysis area, the number of second target homesteads that should be screened for generating the second building outline features is determined, thereby ensuring that the second building outline features contain outline features of an appropriate number of second target homesteads, which can not only ensure the accuracy of the prediction results of the three-dimensional structure restoration model, but also reduce the analysis and calculation load of the three-dimensional structure restoration model and improve the prediction efficiency.

[0062] It should be noted that the second number may be a value obtained by multiplying the first number by a conversion coefficient, and the conversion coefficient should be a value less than 1.

[0063] In some embodiments, the three-dimensional structure restoration model is constructed based on a large model, and the large model is fine-tuned using small sample training data to obtain the three-dimensional structure restoration model.

[0064] In the embodiment of the present invention, with the advancement of science and technology, large models such as ChatGPT, KIMI, and Tongyi Qianwen have developed rapidly. These large models have more powerful "intelligent" analysis capabilities and have achieved significant progress in text understanding, translation, writing, and other aspects. The present invention constructs the above-mentioned three-dimensional structure restoration model based on these large models. Specifically, small sample training data is obtained in advance. The small sample training data contains a certain amount of training data. These training data include various structural form data of various types of buildings. These small sample training data are used to fine-tune the existing large models, and a three-dimensional structure restoration model suitable for restoring the three-dimensional structure of the building in the present invention can be obtained.

[0065] Among them, the small sample in the present invention is relative to the training sample of the vertical model. The vertical model needs to be built using a specific algorithm and trained using a large amount of training data. The present invention adopts a general large model. The large model does not need to be built, and it has been fully trained during use. At this time, only less training data, that is, a small sample, is needed to train its prediction and analysis capabilities in certain aspects.

[0066] In some embodiments, calculating the structural deviation value between the second three-dimensional structure and the first three-dimensional structure includes:

[0067] Decomposing the second three-dimensional structure and the first three-dimensional structure into a plurality of second three-dimensional substructures and a plurality of first three-dimensional substructures according to building units;

[0068] Determine the corresponding second three-dimensional substructure and the first three-dimensional substructure based on the same position principle, and calculate the first structural deviation value of the second three-dimensional substructure and the first three-dimensional substructure;

[0069] The first structural deviation values ​​are fused and calculated to obtain a second structural deviation value.

[0070] In the embodiment of the present invention, the second three-dimensional structure and the first three-dimensional structure obtained above contain multiple single buildings, such as the main house, the wing house, etc., so the present invention first splits the single building, that is, obtains multiple second three-dimensional substructures and first three-dimensional substructures, and the second three-dimensional substructures and the first three-dimensional substructures in the same position constitute a group of comparison data. The first structural deviation values ​​between the second three-dimensional substructures and the first three-dimensional substructures in each group of comparison data are calculated respectively, and then the first structural deviation values ​​corresponding to all the single buildings are fused and calculated, that is, the second structural deviation value that can characterize the structural deviation value between the second three-dimensional structure and the first three-dimensional structure is obtained.

[0071] The fusion calculation may be a weighted average, wherein the weight of the main house is higher than that of the wing room, and the weight of the wing room is higher than that of the roofless house, etc. The above weight relationship is only an example, and may be determined according to the number of building types included in the homestead, and the weight of each type of building may be pre-specified.

[0072] like Figure 3 As shown, the embodiment of the present invention further discloses a homestead use status analysis system, the system comprising a processing device and a storage device, the processing device retrieves and executes the computer code in the storage device to implement the following method steps:

[0073] A plurality of first high-definition images of a first target homestead in the analysis area and a plurality of second high-definition images of a plurality of second target homesteads similar to the first target homestead are photographed by a drone; wherein the first high-definition images are photographed at different angles from each other, and the second high-definition images are photographed at different angles from each other;

[0074] The ground terminal extracts the first building outline features of the first target homestead based on each of the first high-definition images, and constructs a first three-dimensional structure of the first target homestead based on the first building outline features;

[0075] The ground terminal extracts the second building outline features of each second target homestead based on each second high-definition image, inputs the first three-dimensional structure and the second building outline features into a three-dimensional structure restoration model based on artificial intelligence, and obtains a predicted second three-dimensional structure;

[0076] The structural deviation value between the second three-dimensional structure and the first three-dimensional structure is calculated. If the structural deviation value is lower than the deviation threshold, the first target homestead is determined to be in use; otherwise, the first target homestead is determined to be idle.

[0077] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the above embodiment.

[0078] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0079] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the terminal implements the method described in the above embodiment.

[0080] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0081] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0083] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A method for analyzing the use status of homestead, characterized in that , the method comprises the following steps: A plurality of first high-definition images of a first target homestead in the analysis area and a plurality of second high-definition images of a plurality of second target homesteads similar to the first target homestead are photographed by a drone; wherein the first high-definition images are photographed at different angles from each other, and the second high-definition images are photographed at different angles from each other; The ground terminal extracts a first building outline feature of the first target homestead based on each of the first high-definition images, and constructs a first three-dimensional structure of the first target homestead based on the first building outline feature; The ground terminal extracts the second building outline features of each second target homestead based on each second high-definition image, inputs the first three-dimensional structure and the second building outline features into a three-dimensional structure restoration model based on artificial intelligence, and obtains a predicted second three-dimensional structure; The structural deviation value between the second three-dimensional structure and the first three-dimensional structure is calculated. If the structural deviation value is lower than the deviation threshold, the first target homestead is determined to be in use; otherwise, the first target homestead is determined to be idle.

2. A method for analyzing the use status of a homestead according to claim 1, characterized in that: Before taking a plurality of first high-definition images of the first target homestead within the analysis area by the drone, the method further includes: The third high-definition image of the analysis area is taken by the drone, and the ground terminal determines each homestead area from the third high-definition image, and determines and obtains the regional high-definition image corresponding to each homestead area in the third high-definition image; Furthermore, the ground terminal performs color quantity analysis on the regional high-definition images of each of the homestead areas, and determines each of the first target homesteads based on the obtained color quantities.

3. A method for analyzing the use status of a homestead according to claim 2, characterized in that: A plurality of first high-definition images of a first target homestead in an analysis area and a plurality of second high-definition images of a plurality of second target homesteads adjacent to the first target homestead are taken by a drone, including: deriving the type of buildings in the analysis area based on the third high-definition image, determining the building height according to the type, and determining a group of shooting angles according to the building height, specifically, the angle span range corresponding to the group of shooting angles is inversely proportional to the building height; The drone is controlled to shoot several first high-definition images of a first target homestead in the analysis area and several second high-definition images of several second target homesteads adjacent to the first target homestead according to the group of shooting angles.

4. A method for analyzing the use status of a homestead according to claim 3, characterized in that: A plurality of second high-definition images of a plurality of second target homesteads similar to the first target homestead in the analysis area are photographed by a drone, including: deriving a first number of other homesteads with similar building types to the first target homestead in the analysis area based on the third high-definition image analysis, and determining a second number based on the first number; Determine the second number of the second target homesteads adjacent to the first target homestead within the analysis area.

5. A method for analyzing the use status of a homestead according to claim 4, characterized in that: The three-dimensional structure restoration model is constructed based on a large model, and the large model is fine-tuned using small sample training data to obtain the three-dimensional structure restoration model.

6. A method for analyzing the use status of a homestead according to claim 4, characterized in that: The calculating the structural deviation value between the second three-dimensional structure and the first three-dimensional structure includes: Decomposing the second three-dimensional structure and the first three-dimensional structure into a plurality of second three-dimensional substructures and a plurality of first three-dimensional substructures according to building units; Determine the corresponding second three-dimensional substructure and the first three-dimensional substructure based on the same position principle, and calculate the first structural deviation value of the second three-dimensional substructure and the first three-dimensional substructure; The first structural deviation values ​​are fused and calculated to obtain a second structural deviation value.

7. A system for analyzing the status of homestead use, characterized in that: The system includes a processing device and a storage device, wherein the processing device retrieves and executes computer codes in the storage device to implement the following method steps: A plurality of first high-definition images of a first target homestead in the analysis area and a plurality of second high-definition images of a plurality of second target homesteads similar to the first target homestead are photographed by a drone; wherein the first high-definition images are photographed at different angles from each other, and the second high-definition images are photographed at different angles from each other; The ground terminal extracts a first building outline feature of the first target homestead based on each of the first high-definition images, and constructs a first three-dimensional structure of the first target homestead based on the first building outline feature; The ground terminal extracts the second building outline features of each second target homestead based on each second high-definition image, inputs the first three-dimensional structure and the second building outline features into a three-dimensional structure restoration model based on artificial intelligence, and obtains a predicted second three-dimensional structure; The structural deviation value between the second three-dimensional structure and the first three-dimensional structure is calculated. If the structural deviation value is lower than the deviation threshold, the first target homestead is determined to be in use; otherwise, the first target homestead is determined to be idle.

8. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 6.

9. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program stored on a non-transitory computer readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images