Building patrol method and device based on virtual personal assistant

Abstract

The invention discloses a building inspection method and device based on a virtual personal assistant, and the method comprises the steps: judging whether a video camera visual cone can completely cover a target building or not based on the obtained coordinate range of the target building and the range of the video camera visual cone; enabling the camera to bypass a circle in the horizontal direction from the current position, and enabling a virtual personal assistant to be located below an anchor point connecting line of the camera and the target building in the horizontal bypassing process of the camera, and bypassing the target building; if not, determining a plurality of camera visual angles or a plurality of camera reference positions according to the camera visual cone body range and the target building coordinate range, and enabling the camera to detour a circle in the horizontal direction at each visual angle or each reference position from the lowest visual angle or the lowest reference position, and in the horizontal bypassing process of the camera, the virtual personal assistant starts to bypass the target building from the entering position.

Description

Technical Field

[0001] The present invention relates to the field of geographic information technology, and in particular to a building inspection method and device based on a virtual personal assistant. Background Art

[0002] It has become a trend to present electronic maps in 3D. Compared with 2D maps, 3D maps have richer geographical information. After adding height information to electronic maps, the contents in the electronic maps can be depicted in vivid 3D images according to their contour information. For example, Shanghai Oriental Pearl Radio and Television Station can be redesigned and recreated into a 3D building model according to its actual shape, and its 3D shape can be depicted in the map.

[0003] Virtual Personal Assistant (VPA) has evolved into a virtual 3D image today. Through real-time 3D rendering technology, it is built on the development of AI and voice recognition, leaving developers with more scalability and flexibility in the expression of emotional interaction.

[0004] In the existing technology, virtual personal assistants can be seen in the central control interface of the navigation. Through the user's questions, the virtual personal assistant can quickly and accurately solve the problem and provide convenient information services for the driver. It improves the driving experience and also demonstrates the potential of virtual personal assistants in the field of smart cars. Summary of the invention

[0005] In order to better enhance the viewing experience of users, an embodiment of the present invention provides a building inspection method and device based on a virtual personal assistant.

[0006] In a first aspect, an embodiment of the present invention provides a building inspection method based on a virtual personal assistant, the method comprising:

[0007] Based on the acquired target building coordinate range and camera viewing frustum range, determine whether the camera viewing frustum can completely cover the target building:

[0008] If yes, the camera is moved horizontally from the current position to make a circle, and during the horizontal circle of the camera, the virtual personal assistant is placed below the line connecting the anchor points of the camera and the target building, and circles the target building;

[0009] If not, multiple camera viewing angles or multiple camera reference positions are determined according to the camera viewing frustum range and the target building coordinate range, so that the camera starts from the lowest viewing angle or the lowest reference position and moves around horizontally at each viewing angle or each reference position, and during the horizontal movement of the camera, the virtual personal assistant moves around the target building from an entry position.

[0010] In one or some optional implementations of the embodiments of the present application, the determining of multiple camera viewing angles or multiple camera reference positions according to the camera viewing frustum range and the target building coordinate range, causing the camera to start from the lowest viewing angle or the lowest reference position and to horizontally circle around each viewing angle or each reference position, and causing the virtual personal assistant to circle around the target building from an entry position during the horizontal circle of the camera, includes:

[0011] Determine whether the total range covered by the camera's visual frustum can completely cover the target building after the camera at the current position adjusts its viewing angle:

[0012] If so, the camera browsing coverage ratio under the first scheme and the camera browsing coverage ratio under the second scheme are determined in the following manner. If the camera browsing coverage ratio under the first scheme is greater than the camera browsing coverage ratio under the second scheme, the first scheme is executed, otherwise the second scheme is executed:

[0013] The first scheme is: determining a plurality of camera viewing angles according to the camera viewing cone range and the target building coordinate range, making the camera circle around the target building in a horizontal direction in each camera viewing angle in a bottom-to-top order, and making the virtual personal assistant circle around the target building from an entry position during the horizontal circle of the camera;

[0014] The second solution is: determining a plurality of camera reference positions according to the camera viewing frustum range and the target building coordinate range, and making the camera orbit in the horizontal direction at each camera reference position in order from bottom to top, and making the virtual personal assistant orbit the target building from the entry position during the horizontal orbit of the camera;

[0015] If not, the second solution is executed.

[0016] In one or some optional implementations of the embodiments of the present application, the determining of a plurality of camera viewing angles according to the camera viewing frustum range and the target building coordinate range, making the camera orbit in a horizontal direction at each camera viewing angle in order from bottom to top, and making the virtual personal assistant orbit the target building from an entry position during the horizontal orbit of the camera, including:

[0017] Determine the total coverage angle required for the target building under the horizontal viewing angle according to the camera viewing frustum range and the target building coordinate range;

[0018] Determining the viewing angles of the multiple cameras according to the vertical field of view angles of the cameras and the total coverage angle;

[0019] From bottom to top, make the camera move around in the horizontal direction in each camera angle;

[0020] During the horizontal movement of the camera, the virtual personal assistant is caused to move around the target building from an entry position, and the virtual personal assistant is always within the range of the camera's visual cone.

[0021] In one or some optional implementations of the embodiment of the present application, determining the multiple camera viewing angles according to the vertical field of view angle of the camera and the total coverage angle includes:

[0022] Taking the vertical field of view angle of the camera as the rotation angle, under the current orientation of the camera, the camera is rotated upward and / or downward so that the total rotation angle of the camera is not less than the total coverage angle, and the viewing angles of the multiple cameras are determined;

[0023] or,

[0024] Under the current orientation of the camera, the camera is rotated upward and / or downward so that the total rotation angle of the camera is equal to the total coverage angle, and the multiple camera viewing angles are determined.

[0025] In one or some optional implementations of the embodiment of the present application, under the current orientation of the camera, the camera is rotated upward and / or downward so that the total rotation angle of the camera is equal to the total coverage angle, and the multiple camera viewing angles are determined, including:

[0026] According to the vertical field of view angle of the camera and the total coverage angle, determine whether the angle of rotating the camera upward and / or downward is greater than the vertical field of view angle of the camera under the current orientation of the camera. If so, during the process of rotating the camera upward and / or downward, first use the vertical field of view angle of the camera as the rotation angle to determine the final rotation angle of the camera upward and / or downward.

[0027] In one or some optional implementations of the embodiments of the present application, the determining of a plurality of camera reference positions according to the camera viewing frustum range and the target building coordinate range, making the camera orbit horizontally at each camera reference position in order from bottom to top, and making the virtual personal assistant orbit the target building from an entry position during the horizontal orbit of the camera, includes:

[0028] Determine the viewing frustum coverage distance under the horizontal viewing angle according to the camera viewing frustum range and the target building coordinate range;

[0029] Determine the total coverage distance required for the target building under the horizontal viewing angle according to the target building coordinate range;

[0030] Determining a plurality of camera reference positions according to the viewing frustum coverage distance, the total coverage distance and the initial position of the camera;

[0031] From bottom to top, make the camera move around horizontally at each camera reference position;

[0032] During the horizontal movement of the camera, the virtual personal assistant is caused to move around the target building from an entry position, and the virtual personal assistant is always within the range of the camera's visual cone.

[0033] In one or some optional implementations of the embodiment of the present application, the camera browsing coverage ratio is calculated in the following manner:

[0034] Determine the horizontal coverage angle of the viewing cone according to the viewing cone range of the camera, and determine the horizontal coverage ratio;

[0035] Determine the vertical coverage ratio according to the vertical field of view angle and the total coverage angle of the camera or the frustum coverage distance and the total coverage distance of the camera;

[0036] The browsing coverage ratio is determined according to the horizontal coverage ratio and the vertical coverage ratio.

[0037] In one or some optional implementations of the embodiment of the present application, the virtual personal assistant is enabled to detour the target building from the entry position by:

[0038] Determine whether the anchor point of the target building is within the range of the camera's viewing frustum:

[0039] If yes, causing the virtual personal assistant to go around the target building from below the line connecting the camera and the anchor point of the target building;

[0040] If not, the virtual personal assistant is caused to circle the target building starting from below the angular bisector of the vertical field of view of the camera.

[0041] In a second aspect, an embodiment of the present invention provides a building inspection device based on a virtual personal assistant, the device comprising:

[0042] The first judgment module is used to judge whether the camera visual frustum can completely cover the target building based on the acquired target building coordinate range and camera visual frustum range:

[0043] A first acquisition module is used for making the camera horizontally circle around the target building if the camera viewing cone can completely cover the target building, and making the virtual personal assistant be below the line connecting the anchor points of the camera and the target building during the horizontal circle of the camera, and circle around the target building;

[0044] The second acquisition module is used to determine multiple camera viewing angles or multiple camera reference positions according to the camera viewing angle range and the target building coordinate range if the camera viewing frustum cannot completely cover the target building, so that the camera starts from the lowest viewing angle or the lowest reference position and horizontally circles around each viewing angle or each reference position, and during the horizontal circle of the camera, the virtual personal assistant rises from an entry position and circles around the target building.

[0045] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the building inspection method based on a virtual personal assistant as described above.

[0046] In a fourth aspect, an embodiment of the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the building inspection method based on a virtual personal assistant as described above is implemented.

[0047] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0048] The building patrol method based on a virtual personal assistant provided in an embodiment of the present invention determines whether the camera's visual cone can completely cover the target building by obtaining the target building coordinate range and the camera's visual cone range: if so, the camera is made to orbit in the horizontal direction, and the virtual personal assistant is placed below the line connecting the anchor points of the camera and the target building and then orbits; if not, multiple camera viewing angles or multiple camera reference positions are determined according to the camera's visual cone range and the target building's coordinate range, so that the camera starts from the lowest viewing angle or the lowest reference position, and orbits in the horizontal direction at each viewing angle or each reference position, and in the process of the camera's horizontal orbit, the virtual personal assistant is made to orbit the target building from the entry position. The method uses different methods to design camera patrol trajectories according to different situations to display buildings, and is combined with the method of displaying the target building with the assistance of a virtual personal assistant, which can effectively enhance interactivity and realize a personalized user experience. Through the intelligent analysis of the virtual personal assistant, the system can provide personalized building displays according to user interests, display the detailed construction of the building, and enhance the interaction between users and buildings through a variety of display methods, thereby improving the quality of viewing experience.

[0049] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0050] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0052] Figure 1 A schematic diagram of the steps of a building inspection method based on a virtual personal assistant provided by an embodiment of the present invention;

[0053] Figure 2 A schematic diagram of mesh vertices of a 3D sphere provided by an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of a 3D ball rendering effect provided by an embodiment of the present invention;

[0055] Figure 4 A schematic diagram of 3D spherical mesh vertices and rendering effects provided by an embodiment of the present invention;

[0056] Figure 5A schematic diagram of a camera viewing frustum completely covering a target building provided by an embodiment of the present invention;

[0057] Figure 6 A schematic diagram showing that the visual frustum of a camera provided in an embodiment of the present invention cannot completely cover a target building;

[0058] Figure 7 A schematic diagram of different viewing angles when the visual frustum of a camera provided by an embodiment of the present invention can completely cover a target building;

[0059] Figure 8 A schematic diagram of a patrol scheme when the visual cone of a camera provided in an embodiment of the present invention can completely cover a target building;

[0060] Fig. 9 A schematic diagram of different viewing angles when the camera viewing frustum provided by an embodiment of the present invention cannot completely cover the target building;

[0061] Fig.10 A schematic diagram of the intersection of a camera viewing frustum and a target building under a vertical viewing angle provided by an embodiment of the present invention;

[0062] Fig.11 A schematic diagram of a first implementation method in the first solution provided in an embodiment of the present invention;

[0063] Fig.12 A schematic diagram of a second implementation method in the first solution provided in an embodiment of the present invention;

[0064] Fig.13 A schematic diagram of an example of horizontal detour at different viewing angles of the first solution provided in an embodiment of the present invention;

[0065] Fig.14 A schematic diagram of multiple camera viewing angles of a first solution provided by an embodiment of the present invention;

[0066] Fig.15 A schematic diagram of multiple camera reference positions of the second solution provided in an embodiment of the present invention;

[0067] Fig.16 A schematic diagram of a detour solution of the second solution provided in an embodiment of the present invention;

[0068] Fig.17 A schematic diagram showing that the visual frustum of a camera provided in an embodiment of the present invention cannot cover a target building;

[0069] Fig.18 A schematic diagram of the structure of a building patrol device based on a virtual personal assistant provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0071] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0072] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0073] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0074] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0075] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0076] It should be understood that the size of the serial numbers of the steps in the following embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0077] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0078] The inventors found that in the prior art, a virtual personal assistant can be seen appearing in the central control interface of the navigation system, helping users solve some problems by asking questions by the users. In addition, the present invention envisions a scenario where a virtual personal assistant is allowed to enter a 3D map, and can it also help users solve some problems in the same way, for example: guiding the user's perspective, quickly understanding the structure of a building, and displaying points of interest that may arouse the user's interest.

[0079] Among them, the 3D building model needs to be rendered, which usually includes a color part for rendering and a part of mesh vertices for representing the model outline. Because the content of the present invention does not involve the part of rendering color, this part will not be expanded, and only the relationship between the part of mesh vertices of the model outline and the present invention is explained.

[0080] A 3D building model is actually composed of a group of mesh vertices, which form a number of small planes. The outline is formed by these small planes, and the interior of the model is empty. Figure 2 and Figure 3 It shows the mesh vertices of the 3D ball and the 3D ball rendering effect. Figure 4 The mesh vertices and rendering effects of the 3D ball are displayed at the same time. The 3D ball rendering effect refers to the part with added colors, and the colors have corresponding processing and reflection of the lighting. The model itself needs to specify the coordinate system. The optional coordinate systems are the left-handed coordinate system and the right-handed coordinate system. The left-handed coordinate system and the right-handed coordinate system will affect the positive direction of the x and z axes of the coordinate axis, and the y axis is the vertical direction. Therefore, on the same 3D building model, if the left-handed coordinate system and the right-handed coordinate system are applied respectively, the coordinate values ​​of the grid points obtained are different, but it does not prevent the use of grid vertices to represent the mesh information of the model or perform subsequent calculations.

[0081] These mesh vertices of the 3D building model have local coordinate values ​​based on the coordinate axes of the 3D building model. The space represented by the coordinate axes inside the 3D building model is called the local space, and the coordinates in the local space are called local coordinates. The 3D building model also needs to be placed in a map, and the map also has its own coordinate system, which is also a three-dimensional coordinate system. The space in the map is called the world space. The 3D building model will also have coordinates relative to the world space, called world coordinates. According to the world coordinates of the target building model and the rotation angle in the world space, the position of the target building model in the world can be determined, and the world coordinates of any grid point on the model can be obtained. The present invention will be mainly based on world coordinates unless otherwise specified.

[0082] Based on this, the inventors have made the present invention after further research and development, providing a building inspection method and device based on a virtual personal assistant.

[0083] Embodiment 1

[0084] The embodiment of the present invention provides a building inspection method based on a virtual personal assistant, referring to Figure 1 As shown, the method includes:

[0085] S101: Based on the acquired coordinate range of the target building and the range of the camera viewing frustum, it is determined whether the camera viewing frustum can completely cover the target building.

[0086] In the embodiment of the present application, it is necessary to obtain the coordinate range of the target building and the camera frustum range. The target building can be a real building in the simulated real world. It is necessary to convert the world coordinates of the target building into a 3D building model and establish the local coordinates of the 3D building model. The schematic diagram of the camera frustum range and the target building coordinate range in the 3D modeling system is as follows: Figure 5 , Figure 6 As shown in the figure, the observed object in the figure is the target building, and the quadrangular pyramid with the camera as the vertex is the camera viewing frustum. Figure 5 The situation in the middle indicates that the camera's viewing frustum completely covers the target building. Figure 6 The situation in represents the case where the camera viewing frustum cannot fully cover the target building.

[0087] S102: If the camera viewing frustum can completely cover the target building, the camera is caused to orbit horizontally from the current position, and during the horizontal orbit of the camera, the virtual personal assistant is placed below the line connecting the anchor points of the camera and the target building, and the virtual personal assistant orbits the target building.

[0088] In the embodiment of the present application, when the camera viewing cone and the target building are Figure 5When the camera's viewing frustum can completely cover the target building, the schematic diagrams under different viewing angles are as follows Figure 7 As shown, the gray parts under the vertical viewing angle and the horizontal viewing angle in the figure are the horizontal coverage surface and the vertical coverage surface respectively.

[0089] In this case, the patrol plan diagram is as follows Figure 8 As shown in the figure, the camera only needs to circle horizontally from the current position, either clockwise or counterclockwise, to complete the inspection of the target building.

[0090] In the embodiment of the present application, the virtual personal assistant has its own 3D virtual image, which is also composed of mesh vertices. The special thing is that the 3D virtual image is dominated by the image skeleton, and will automatically calculate and generate the displacement transformation of the mesh vertices according to the actions made by the virtual image. Displacement transformation means that the mesh vertex is transformed from the original position to the new position based on the local coordinate system. The process of displacement transformation is automatic calculation. Those skilled in the art can realize the automatic calculation of displacement transformation based on the detailed description of the prior art, and it is not specifically limited in the embodiment of the present invention.

[0091] When the virtual image of the virtual personal assistant makes a new action, the mesh vertices of this image will also change. In order to simplify the impact of the virtual personal assistant's action transformation, the image of the virtual personal assistant is simplified into a cube in the present invention. This cube needs to be able to just cover the actual virtual personal assistant, that is, the actual virtual personal assistant's external cube, to ensure that all actions of the virtual personal assistant are within the cube.

[0092] Reference Figure 8 As shown, during the horizontal orbit of the camera, the cube of the virtual personal assistant is placed below the line connecting the anchor points of the camera and the target building, and the cube of the virtual personal assistant is always completely within the camera's visual cone as the camera orbits the target building. Among them, the anchor point of the target building is directly obtained, and is generally the local center point that the model should emphasize the most. It needs to be specifically considered according to the shape of the model. For example, for the Oriental Pearl Radio and Television Tower, whether it is set at the top of the tower, the spherical part, or the bottom of the tower is considered when the model is established. The specific method of obtaining the anchor point can be implemented by those skilled in the art based on the detailed description of the prior art, and no specific limitation is made here.

[0093] In the embodiment of the present application, when the camera can completely cover the target building, the camera is moved horizontally around to ensure that the camera can smoothly and completely display all parts of the building, and the virtual personal assistant is placed below the line connecting the camera and the anchor point of the target building to attract the user's attention, making it easier for the user to focus on the local center point of the building, guiding the user's perspective, quickly understanding the structure of the target building, and displaying points of interest that may arouse the user's interest.

[0094] S103: If the camera viewing frustum cannot completely cover the target building, multiple camera viewing angles or multiple camera reference positions are determined according to the camera viewing frustum range and the target building coordinate range, so that the camera starts from the lowest viewing angle or the lowest reference position and moves around in the horizontal direction at each viewing angle or each reference position. During the horizontal movement of the camera, the virtual personal assistant moves around the target building from the entry position.

[0095] In the embodiment of the present application, in the above step S103, multiple camera viewing angles or multiple camera reference positions are determined according to the camera viewing cone range and the target building coordinate range, so that the camera starts from the lowest viewing angle or the lowest reference position and circles around in the horizontal direction at each viewing angle or each reference position, and in the process of the camera circling horizontally, the virtual personal assistant starts to circle around the target building from the entry position, specifically including:

[0096] Determine whether the total range of the camera's frustum can completely cover the target building after the camera at the current position adjusts its viewing angle:

[0097] If so, the camera browsing coverage ratio under the first scheme and the camera browsing coverage ratio under the second scheme are determined in the following manner. If the camera browsing coverage ratio under the first scheme is greater than the camera browsing coverage ratio under the second scheme, the first scheme is executed. If the camera browsing coverage ratio under the first scheme is not greater than the camera browsing coverage ratio under the second scheme, the second scheme is executed:

[0098] The first scheme is: determining multiple camera angles according to the camera frustum range and the target building coordinate range, making the camera circle around the target building in the horizontal direction in each camera angle in order from bottom to top, and making the virtual personal assistant circle around the target building from the entry position during the horizontal circle of the camera;

[0099] The second solution is: determine multiple camera reference positions according to the camera's frustum range and the target building's coordinate range, and make the camera orbit horizontally at each camera reference position in order from bottom to top, and make the virtual personal assistant orbit the target building from the entry position during the horizontal orbit of the camera;

[0100] If not, execute the second solution.

[0101] The camera browsing coverage ratio is calculated in the following way:

[0102] Determine the horizontal coverage angle of the viewing cone according to the range of the viewing cone of the camera, and determine the horizontal coverage ratio;

[0103] Determine the vertical coverage ratio according to the vertical field angle and the total coverage angle of the camera or the frustum coverage distance and the total coverage distance of the camera;

[0104] Determine the browsing reach ratio based on the horizontal reach ratio and the vertical reach ratio.

[0105] The virtual personal assistant is enabled to go around the target building from the entry position by:

[0106] Determine whether the anchor point of the target building is within the camera's viewing frustum:

[0107] If yes, the virtual personal assistant is caused to circle the target building from below the line connecting the camera and the anchor point of the target building;

[0108] If not, the virtual personal assistant is made to circle the target building starting from below the bisector of the vertical field of view of the camera.

[0109] In the embodiment of the present application, when the camera viewing cone and the target building are Figure 6 When the camera's viewing cone can completely cover the target building, the schematic diagrams under different viewing angles are as follows: Fig. 9 As shown in the figure, it can be seen that no matter the vertical or horizontal perspective, there may be a situation where the coverage is not complete. The schematic diagram of the intersection of the camera frustum and the target building under the vertical perspective is as follows: Fig.10 As shown, points A and B are the intersection points of the viewing frustum and the target building, point O is the center point of the target building, the angle of AOB, that is, the horizontal coverage angle is α, and the angle required for the camera to cover the model horizontally is 360°, so the camera needs to be moved around in the horizontal direction.

[0110] In the embodiment of the present application, two solutions are proposed for the situation where the horizontal viewing angle cannot be fully covered. It is necessary to determine whether the total range covered by the camera's visual cone after the horizontal viewing angle of the camera at the current position is adjusted can completely cover the target building. If it can be covered, the camera browsing coverage ratio under the first solution and the camera browsing coverage ratio under the second solution are calculated respectively, and the solution with a larger browsing coverage ratio is executed. If it cannot be fully covered, the second solution is directly executed.

[0111] In one embodiment, without moving the vertical position of the camera, the specific implementation steps of the first solution may include:

[0112] Determine the total coverage angle required for the target building under the horizontal viewing angle according to the camera viewing cone range and the target building coordinate range;

[0113] Determine multiple camera viewing angles based on the vertical field of view and total coverage angle of the camera;

[0114] From bottom to top, make the camera move around in the horizontal direction in each camera angle;

[0115] During the horizontal movement of the camera, the virtual personal assistant is caused to move around the target building from the entry position, and the virtual personal assistant is always completely within the range of the camera's visual cone.

[0116] The above-mentioned determination of multiple camera viewing angles according to the vertical field of view angle and the total coverage angle of the camera may specifically include the following two different implementation methods:

[0117] First implementation method: using the vertical field of view angle of the camera as the rotation angle, under the current orientation of the camera, the camera is rotated upward and / or downward so that the total rotation angle of the camera is not less than the total coverage angle, and multiple camera viewing angles are determined;

[0118] or,

[0119] The second implementation manner: under the current orientation of the camera, the camera is rotated upward and / or downward so that the total rotation angle of the camera is equal to the total coverage angle, and multiple camera viewing angles are determined.

[0120] In the second implementation, the camera is rotated upward and / or downward under the current orientation of the camera so that the total rotation angle of the camera is equal to the total coverage angle, and multiple camera viewing angles are determined, specifically including:

[0121] According to the vertical field of view and total coverage angle of the camera, determine whether the angle of rotating the camera upward and / or downward is greater than the vertical field of view of the camera under the current orientation of the camera. If so, during the process of rotating the camera upward and / or downward, first use the vertical field of view of the camera as the rotation angle to determine the final rotation angle of the camera upward and / or downward.

[0122] Since the angle of each rotation in the first implementation is a fixed rotation angle, that is, the vertical field of view of the camera, when the camera rotates upward to completely cover the target building, the frustum range of the camera will exceed the top of the target building. Similarly, when the camera rotates downward to completely cover the target building, the frustum range of the camera will exceed the bottom of the target building. Therefore, the total rotation angle of the camera is generally greater than the total coverage angle required for the target building. Of course, in some extreme cases, if the camera rotates upward to completely cover the target building, the last frustum of the camera rotated upward is tangent to the target building, and when the camera rotates downward to completely cover the target building, the last frustum of the camera rotated downward is tangent to the target building, then the total rotation angle of the camera is exactly equal to the total coverage angle required for the target building.

[0123] In the embodiment of the present application, in the first solution, a schematic diagram of multiple camera viewing angles in the first implementation is as follows Fig.11 As shown, the schematic diagram of multiple camera viewing angles in the second implementation is as follows Fig.12 shown. Fig.11 and Fig.12 The solid triangle 1 is the camera viewing cone at the current horizontal viewing angle, β is the vertical field angle of the camera, and triangles 2 and 3 are the camera viewing cone at the current horizontal viewing angle after the camera adjusts the viewing angle upward and downward, respectively.

[0124] Fig.11 Indicates that the vertical field of view of the camera is used as the rotation angle. Under the current orientation of the camera, the camera is rotated upward and / or downward so that the total rotation angle of the camera is not less than the total coverage angle required by the target building. Fig.11 It can be seen that the angle required to rotate when parts 1, 2, and 3 are not repeated is equal to m×β+n×β, where m×β is the angle of upward rotation and n×β is the angle of downward rotation. The angle covered by the camera's up and down rotation is m×β+n×β+β=(m+n+1)×β, where m>0 and / or n>0.

[0125] Fig.12 It means that under the current orientation of the camera, the camera is rotated upward m times and / or downward n times, so that the total rotation angle of the camera is equal to the total coverage angle required by the target building. To make the total rotation angle of the camera equal to the total coverage angle required by the target building, it is necessary to determine whether the angle of the camera rotated upward and / or downward under the current orientation of the camera is greater than the vertical field of view of the camera. If so, in the process of rotating the camera upward and / or downward, the vertical field of view of the camera is first used as the rotation angle, and the camera is rotated upward m times and downward n times. Finally, the final rotation angle of the camera rotated upward and / or downward is determined, so that the final viewing cone of the camera rotated upward / downward is tangent to the target building. Fig.12 The θ1 and θ2 in are the final rotation angles upward and / or downward. Fig.12 It can be seen that the angle covered by the up and down rotation of the camera is m×β+θ1+n×β+θ2+β=(m+n+1)×β+θ1+θ2, among which at least one of m, n, θ1, θ2 is not 0.

[0126] On the basis of the first implementation method, the inventors considered that since the horizontal and vertical field angles of the camera cannot be adjusted arbitrarily during the rotation and displacement process, the rotation angle is not an integer multiple of β. Based on this, the inventors proposed the above-mentioned second implementation method, so that the final viewing cone of the camera rotating upward and downward is tangent to the target building.

[0127] The schematic diagram of the inspection plan under the first plan is as follows Fig.13 and Fig.14 See Fig.13 , the camera is at position 1, and it can completely cover the horizontal part of the coverage distance a by rotating 180° along the horizontal direction. Similarly, for the camera at position 2, it can completely cover the part of the coverage distance b by rotating 180° along the horizontal direction. According to the above scheme, if Fig.14 As shown, the virtual personal assistant needs to complete four rounds of detours within the coverage of the four camera positions under the four camera perspectives 1, 2, 3, and 4. The detour process starts from the lowest position, 2→1→3→4, and the corresponding parts of the model are b, a, c, and d. After each detour, the virtual personal assistant needs to enter the next part until all parts are traversed.

[0128] In one embodiment, the specific implementation steps of the second solution may include:

[0129] Determine the viewing frustum coverage distance under the horizontal viewing angle according to the camera viewing frustum range and the target building coordinate range;

[0130] Determine the total coverage distance required for the target building under the horizontal viewing angle according to the coordinate range of the target building;

[0131] Determine multiple camera reference positions according to the viewing frustum coverage distance, the total coverage distance and the initial position of the camera;

[0132] From bottom to top, make the camera move around horizontally at each camera reference position;

[0133] During the horizontal orbiting of the camera, the virtual personal assistant is made to orbit the target building from the entry position, and the virtual personal assistant is always within the camera's visual frustum.

[0134] The second scheme diagram is as follows Fig.15As shown in the figure, the solid triangle is the camera frustum at the horizontal viewing angle of the current position, a is the frustum coverage distance of the camera at the horizontal viewing angle, and the dotted triangle is the camera frustum at the horizontal viewing angle after the camera at the current position is adjusted upward and downward. The second scheme specifically includes: determining the frustum coverage distance at the horizontal viewing angle according to the camera frustum range and the target building coordinate range; determining the total coverage distance required for the target building at the horizontal viewing angle according to the target building coordinate range; determining multiple camera reference positions according to the frustum coverage distance, the total coverage distance and the initial position of the camera, so that the camera at the current position moves upward j times and downward k times, and the distance of each vertical movement is equal to the frustum coverage distance a. Among them, the frustum coverage distance a can be converted into the distance between the extension line of the vertical field of view angle of the camera and the focus of the surface contour of the model when it is specifically calculated. By Fig.15 It can be seen that the distance required to move without repetition is equal to j×a+k×a, j×a is the distance moved upward, and k×a is the distance moved downward. The distance covered by the camera moving up and down is j×a+k×a+a=(j+k+1)×a, where j>0 and / or k>0.

[0135] The schematic diagram of the inspection plan of the second plan is as follows Fig.16 As shown, in order from bottom to top, the camera is made to orbit horizontally at each camera reference position; during the horizontal orbit of the camera, the virtual personal assistant is made to orbit the target building from the entry position, and the virtual personal assistant is always within the camera frustum. Fig.16 , the camera needs to descend first, descend k×a, and the virtual personal assistant needs to be below the angular bisector OC of the camera's vertical field of view to determine the entry position of the virtual personal assistant. The virtual personal assistant needs to detour along the outer contour of the model in the horizontal direction and gradually rise in the vertical direction. The number of detours is related to the position of the camera. Fig.16 In the example, there are 4 reference positions for the camera, through which the target building can be fully viewed. Therefore, the number of detours of the camera and the virtual personal assistant is also 4. The virtual personal assistant moves upward from the entry position to the top to exit the detour.

[0136] In the embodiment of the present application, if the total range covered by the camera's visual frustum can completely cover the target building after the camera at the current position adjusts its viewing angle, the browsing coverage ratios of the first scheme and the second scheme are calculated respectively, and the browsing coverage ratios of the two schemes are compared, and the scheme with a larger browsing coverage ratio is executed.

[0137] In the case of the first scheme, the horizontal coverage ratio = α / 360°. In the first implementation, the vertical coverage ratio = the vertical field of view of the camera β / the total coverage angle of the camera = β / ((m+n+1)×β), the browsing coverage ratio = the horizontal coverage ratio × the vertical coverage ratio = (α / 360°)×(β / ((m+n+1)×β)), where at least one of m and n is not equal to 0; in the second implementation, the vertical coverage ratio = the vertical field of view of the camera β / the total coverage angle of the camera = β / ((m+n+1)×β+θ1+θ2), the browsing coverage ratio = the horizontal coverage ratio × the vertical coverage ratio = (α / 360°)×(β / ((m+n+1)×β+θ1+θ2)), where at least one of m, n, θ1 and θ2 is not equal to 0. α is the horizontal coverage angle, β is the vertical field of view of the camera, m and n represent the number of times the camera rotates upward and downward, respectively, and θ 1 and β 2 That is, the final upward and / or downward rotation angle of the camera in the second implementation manner.

[0138] In the case of the second solution, the horizontal coverage ratio = horizontal coverage angle α / 360°, the vertical coverage ratio = camera's frustum coverage distance a / camera's total coverage distance = a / (j+k+1)×a, and the browsing coverage ratio is equal to the horizontal coverage ratio×vertical coverage ratio=(α / 360°)×(1 / (j+k+1)), where at least one of j and k is not equal to 0. Where a is the camera's frustum coverage distance, and j and k represent the number of times the camera moves up and down, respectively.

[0139] In one embodiment, the target building is Figure 6 As shown, the schematic diagrams of the target building from vertical and horizontal perspectives are shown in Fig.10 and Fig.11 As shown, the horizontal coverage angle is α=30°, and the vertical field of view angle of the camera is β=30°. In the first scheme, the browsing coverage ratios of the two viewing angle selection situations in the first scheme are calculated as follows: Fig.11 As shown, the horizontal coverage ratio = α / 360° = 30° / 360° = 8.33%, the vertical coverage ratio = β / ((m+n+1)×β) = 33.33%, at this time m=1, n=1, the browsing coverage ratio = 33.33%×8.33%=2.78%; the second implementation method in the first solution is as follows Fig.12As shown, the horizontal coverage ratio = α / 360° = 8.33%, the vertical coverage ratio = β / ((m+n+1)×β+θ1+θ2) = 30 / ((0+0+1)×30+15+20) = 30 / 65 = 46.15%, at this time m=0, n=0, θ1=15°, θ2=20°, the browsing coverage ratio = 46.15%×8.33%=3.87%.

[0140] In a specific embodiment, assuming that the horizontal coverage angle is α=30° and the vertical field of view angle of the camera is β=30°, then in the second scheme, the horizontal coverage ratio = α / 360° = 30° / 360° = 8.33%, the vertical coverage ratio = a / (j+k+1)×a=a / 4a=1 / 4=25%, where j=2, k=1, and the browsing coverage ratio = 25%×8.33%=2.08%.

[0141] Since there are differences in the viewing angle adjustment methods between the first implementation method and the second implementation method of the first scheme, a unified measurement method is needed to ensure the consistency of comparison. Therefore, it is necessary to convert the browsing coverage ratio result of the second implementation method to the measurement method of the first implementation method, and the formula is: browsing coverage ratio of the second implementation method after conversion = browsing coverage ratio of the second implementation method × (vertical coverage ratio of the first implementation method / vertical coverage ratio of the second implementation method). Fig.12 As shown in the example, the browsing coverage ratio after conversion of the second implementation method = 3.87% × 33.33% / 46.15% = 2.79%, 2.79% is greater than 2.78%, so the second implementation method in the first solution is better.

[0142] Similarly, since the first solution is to adjust the vertical coverage ratio according to the viewing angle, and the second solution is to adjust the vertical coverage ratio according to the distance, a unified measurement method is needed to ensure the consistency of the comparison. Therefore, the specific calculation expression for converting the result of the second solution to the measurement method of the first solution is: the browsing coverage ratio of the second solution = the browsing coverage ratio of the second solution × (the vertical coverage ratio of the first solution / the vertical coverage ratio of the second solution). Fig.15 Taking the result of the browsing coverage ratio of the second scheme shown as an example, the browsing coverage ratio of the second scheme after conversion is converted into the measurement method of the second implementation method of the first scheme = 2.08% × 46.15% / 25% = 3.83%, 3.83% is less than 3.87%, so the second implementation method in the first scheme is better.

[0143] In the embodiment of the present application, if the camera at the current position adjusts the viewing angle, the total range covered by the camera's visual frustum cannot completely cover the target building, as shown in the schematic diagram Fig.17As shown, in this case, the purpose of completely patrolling the target building can only be achieved by changing the vertical position of the camera. The second solution mentioned above will be directly executed, and a circle will be made horizontally at each camera reference position from bottom to top at multiple camera reference positions. At the same time, the virtual personal assistant will circle the target building and always be within the camera's field of view.

[0144] In the embodiment of the present application, when the virtual personal assistant is circling, it is necessary to obtain the circling radius and circling period of the virtual personal assistant; determine the circling rate of the virtual personal assistant in the horizontal direction according to the circling radius and circling period; determine the moving rate of the virtual personal assistant in the vertical direction according to the visual cone coverage distance and the circling period, so as to smooth the operating frequency of the entire moving distance. To make the moving trajectory of the virtual personal assistant as natural as possible, for example, it is possible to consider using a Bezier curve to make the circling path smooth.

[0145] In the embodiment of the present application, it can be found from the comparison between the first solution and the second solution that the two implementation methods of the first solution are similar to a person looking up, looking straight, and looking down, and the distance in each stage is different. Fig.14 , the distances a, b, c, and d of the target building covered under different viewing angles are inconsistent, which is closer to people's viewing habits. This method is more in line with people's natural observation habits, making the presentation of the target building more intuitive and comfortable. The second option is similar to the feeling of browsing in an elevator. The entire browsing process is carried out along a spiral curve. The height of each rise can be of equal amplitude and frequency, providing a novel and smooth experience, making it easier for users to grasp the overall layout of the target building. When actually selecting a detour plan, technical personnel in this field can refer to the above-mentioned browsing coverage ratio to select a suitable plan, or they can consider the actual usage experience and select a suitable detour plan.

[0146] In the embodiments of the present application, from the usage level, the situations that trigger the building patrol and virtual personal assistant detour method include: the user is interested in a landmark building in the map, and then clicks on the building to trigger the building patrol and virtual personal assistant detour method; when guiding the route, there are buildings along the way, and according to the suggestions of the recommendation engine, the building detour and virtual personal assistant detour method will be actively triggered to introduce some scenic spots, buildings, Internet celebrity check-in spots, etc. along the way.

[0147] In the embodiment of the present application, a method is designed to plan the running trajectory of the camera and the virtual personal assistant by performing real-time calculation according to the browsing needs of the target building model based on the information provided by any 3D building model in the map. This method uses different methods to design camera patrol trajectories according to different situations to display buildings. Combined with the method of displaying the target building with the assistance of a virtual personal assistant, it can effectively enhance interactivity and realize a personalized user experience. Through the intelligent analysis of the virtual personal assistant, the system can provide personalized building displays according to user interests, display the detailed construction of the building, and enhance the interaction between users and buildings through a variety of display methods, thereby improving the quality of the viewing experience.

[0148] Embodiment 2

[0149] Based on the same inventive concept, the embodiment of the present invention also provides a building inspection device based on a virtual personal assistant, referring to Fig.18 As shown, the device comprises:

[0150] The first judgment module 101 is used to judge whether the camera visual frustum can completely cover the target building based on the acquired target building coordinate range and camera visual frustum range:

[0151] The first acquisition module 102 is configured to make the camera move around horizontally from a current position if the camera viewing cone can completely cover the target building, and during the horizontal movement of the camera, make the virtual personal assistant be below the line connecting the anchor points of the camera and the target building, and move around the target building;

[0152] The second acquisition module 103 is used to determine multiple camera viewing angles or multiple camera reference positions according to the camera viewing angle range and the target building coordinate range if the camera viewing frustum cannot completely cover the target building, so that the camera starts from the lowest viewing angle or the lowest reference position and horizontally circles around each viewing angle or each reference position, and during the horizontal circle of the camera, the virtual personal assistant starts to rise from an entry position and circles around the target building.

[0153] Embodiment 3

[0154] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the building inspection method based on a virtual personal assistant as described in the above embodiment 1 is implemented.

[0155] Embodiment 4

[0156] Based on the same inventive concept, an embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the building inspection method based on a virtual personal assistant as described in the first embodiment above is implemented.

[0157] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0158] 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.

[0159] 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 comprising 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.

[0160] 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.

[0161] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A building inspection method based on virtual personal assistant, It is characterized in that include: Based on the acquired target building coordinate range and camera viewing frustum range, determine whether the camera viewing frustum can completely cover the target building: If yes, the camera is moved horizontally from the current position to make a circle, and during the horizontal circle of the camera, the virtual personal assistant is placed below the line connecting the anchor points of the camera and the target building, and circles the target building; If not, multiple camera viewing angles or multiple camera reference positions are determined according to the camera viewing frustum range and the target building coordinate range, so that the camera starts from the lowest viewing angle or the lowest reference position and moves around horizontally at each viewing angle or each reference position, and during the horizontal movement of the camera, the virtual personal assistant moves around the target building from an entry position.

2. The method according to claim 1, It is characterized in that The method of determining a plurality of camera viewing angles or a plurality of camera reference positions according to the camera viewing frustum range and the target building coordinate range, causing the camera to start from the lowest viewing angle or the lowest reference position and to horizontally circle around each viewing angle or each reference position, and causing the virtual personal assistant to circle around the target building from an entry position during the horizontal circle of the camera, comprises: Determine whether the total range covered by the camera's visual frustum can completely cover the target building after the camera at the current position adjusts its viewing angle: If so, the camera browsing coverage ratio under the first scheme and the camera browsing coverage ratio under the second scheme are determined in the following manner. If the camera browsing coverage ratio under the first scheme is greater than the camera browsing coverage ratio under the second scheme, the first scheme is executed, otherwise the second scheme is executed: The first scheme is: determining a plurality of camera viewing angles according to the camera viewing cone range and the target building coordinate range, making the camera circle around the target building in a horizontal direction in each camera viewing angle in a bottom-to-top order, and making the virtual personal assistant circle around the target building from an entry position during the horizontal circle of the camera; The second solution is: determining a plurality of camera reference positions according to the camera viewing frustum range and the target building coordinate range, and making the camera orbit in the horizontal direction at each camera reference position in order from bottom to top, and making the virtual personal assistant orbit the target building from the entry position during the horizontal orbit of the camera; If not, the second solution is executed.

3. The method according to claim 2, It is characterized in that The method further comprises: determining a plurality of camera viewing angles according to the camera viewing frustum range and the target building coordinate range, causing the camera to orbit horizontally in each camera viewing angle in a sequence from bottom to top, and causing the virtual personal assistant to orbit the target building from an entry position during the horizontal orbit of the camera, including: Determine the total coverage angle required for the target building under the horizontal viewing angle according to the camera viewing frustum range and the target building coordinate range; Determining the viewing angles of the multiple cameras according to the vertical field of view angles of the cameras and the total coverage angle; From bottom to top, make the camera move around in the horizontal direction in each camera angle; During the horizontal movement of the camera, the virtual personal assistant is caused to move around the target building from an entry position, and the virtual personal assistant is always within the range of the camera's visual cone.

4. The method according to claim 3, It is characterized in that The determining the multiple camera viewing angles according to the vertical field of view angle of the camera and the total coverage angle comprises: Taking the vertical field of view angle of the camera as the rotation angle, under the current orientation of the camera, the camera is rotated upward and / or downward so that the total rotation angle of the camera is not less than the total coverage angle, and the viewing angles of the multiple cameras are determined; or, Under the current orientation of the camera, the camera is rotated upward and / or downward so that the total rotation angle of the camera is equal to the total coverage angle, and the multiple camera viewing angles are determined.

5. The method according to claim 4, It is characterized in that Under the current orientation of the camera, the camera is rotated upward and / or downward so that the total rotation angle of the camera is equal to the total coverage angle, and the multiple camera viewing angles are determined, including: According to the vertical field of view angle of the camera and the total coverage angle, determine whether the angle of rotating the camera upward and / or downward is greater than the vertical field of view angle of the camera under the current orientation of the camera. If so, during the process of rotating the camera upward and / or downward, first use the vertical field of view angle of the camera as the rotation angle to determine the final rotation angle of the camera upward and / or downward.

6. The method according to claim 2, It is characterized in that The method further comprises: determining a plurality of camera reference positions according to the camera viewing frustum range and the target building coordinate range, causing the camera to horizontally orbit around each camera reference position in a bottom-to-top order, and causing the virtual personal assistant to orbit around the target building from an entry position during the horizontal orbit of the camera, including: Determine the viewing frustum coverage distance under the horizontal viewing angle according to the camera viewing frustum range and the target building coordinate range; Determine the total coverage distance required for the target building under the horizontal viewing angle according to the target building coordinate range; Determining a plurality of camera reference positions according to the viewing frustum coverage distance, the total coverage distance and the initial position of the camera; From bottom to top, make the camera move around horizontally at each camera reference position; During the horizontal movement of the camera, the virtual personal assistant is caused to move around the target building from an entry position, and the virtual personal assistant is always within the range of the camera's visual cone.

7. The method according to any one of claims 2 to 6, It is characterized in that The camera viewing coverage ratio is calculated in the following way: Determine the horizontal coverage angle of the viewing cone according to the viewing cone range of the camera, and determine the horizontal coverage ratio; Determining a vertical coverage ratio according to a vertical field of view angle and a total coverage angle of the camera or a frustum coverage distance and a total coverage distance of the camera; The browsing coverage ratio is determined according to the horizontal coverage ratio and the vertical coverage ratio.

8. The method according to any one of claims 2 to 6, It is characterized in that The virtual personal assistant is caused to go around the target building from the entry position by: Determine whether the anchor point of the target building is within the range of the camera's viewing frustum: If yes, causing the virtual personal assistant to go around the target building from below the line connecting the camera and the anchor point of the target building; If not, the virtual personal assistant is caused to circle the target building starting from below the angular bisector of the vertical field of view of the camera.

9. A building inspection device based on a virtual personal assistant, It is characterized in that include: The first judgment module is used to judge whether the camera visual frustum can completely cover the target building based on the acquired target building coordinate range and camera visual frustum range: A first acquisition module is used for making the camera horizontally circle around the target building if the camera viewing cone can completely cover the target building, and making the virtual personal assistant be below the line connecting the anchor points of the camera and the target building during the horizontal circle of the camera, and circle around the target building; The second acquisition module is used to determine multiple camera viewing angles or multiple camera reference positions according to the camera viewing angle range and the target building coordinate range if the camera viewing frustum cannot completely cover the target building, so that the camera starts from the lowest viewing angle or the lowest reference position and horizontally circles around each viewing angle or each reference position, and during the horizontal circle of the camera, the virtual personal assistant rises from an entry position and circles around the target building.

10. A computer-readable storage medium storing instructions, which, when executed on a terminal, enables the terminal to execute the building inspection method based on a virtual personal assistant as described in any one of claims 1 to 9.

11. A computer device, It is characterized in that The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the building inspection method based on a virtual personal assistant as described in any one of claims 1 to 9 is implemented.

Images