Building plane optimization method and device based on graph axis coding and storage medium

Abstract

The invention relates to a building plane optimization method and device based on graph axis coding and a storage medium. The method comprises the steps that initial plane topological data and multivariate constraint condition data corresponding to an initial architectural plane graph are determined, the initial plane topological data are obtained after the initial architectural plane graph is segmented and coded based on a graph axis, and the multivariate constraint condition data are associated with the graph axis and represent limitation information related to the initial architectural plane graph; optimizing the initial plane topological data based on the multivariate constraint condition data to obtain target plane topological data; and obtaining a target architectural plane graph based on the target plane topological data. According to the embodiment of the invention, a strategy based on the graph axis can be used to effectively encode the architectural plane graph into a form which can be calculated and optimized by a computer while reserving necessary elements and information, so that the optimization process of the architectural plane graph is realized. And the contradiction among the data volume, the operability and the operation precision can be effectively balanced in the optimization process.

Description

Technical Field

[0001] The present disclosure relates to the field of computer-aided architectural design, and particularly to an architectural floor plan optimization method, device, and storage medium based on graph axis coding. Background Art

[0002] With the development of computer technology, the generation and transformation of architectural floor plans using relevant computer technologies have gradually become a classic problem in the field of computer-aided architectural design (CAAD). However, how to convert the architectural floor plans used by architects into a form that can be computed by a computer and further assist in architectural renovation remains the core challenge in this field. In the process of architectural floor plan optimization, the choice of coding method is crucial. An efficient coding method can not only improve the computational efficiency of the optimization process but also significantly optimize the quality of the final result, providing more accurate and flexible support for architectural renovation.

[0003] In existing coding methods, there is often a problem of over-simplifying architectural elements in architectural floor plans, and most methods lack attention to room boundary information and often process the floor plan in the form of wall segments, room units, etc. These methods increase the complexity of common operations (such as wall movement, room function conversion, etc.) in architectural renovation and limit the scalability of the method. Therefore, there is an urgent need for a flexible architectural floor plan optimization method that can encode architectural floor plans into a form computable by a computer to support the need for optimizing architectural floor plans and effectively balance the contradiction among data volume, operability, and operation accuracy during the optimization process. Summary of the Invention

[0004] In view of this, the present disclosure provides an architectural floor plan optimization method, device, and storage medium based on graph axis coding.

[0005] According to one aspect of the present disclosure, an architectural floor plan optimization method based on graph axis coding is provided.

[0006] The method includes:

[0007] Determine the initial plane topology data and multi-constraint condition data corresponding to the initial architectural floor plan. The initial plane topology data is obtained by segmenting and coding the initial architectural floor plan based on graph axes, and the multi-constraint condition data is associated with the graph axes and represents the restriction information related to the initial architectural floor plan;

[0008] Optimize the initial plane topology data based on the multi-constraint condition data to obtain the target plane topology data;

[0009] Based on the target plane topology data, obtain the target architectural floor plan.

[0010] In a possible implementation, the initial planar topology data includes a graph axis sequence, which is used to indicate the position information of the graph axes in at least two preset directions. The at least two directions include the horizontal and vertical directions, and each direction includes at least two graph axes.

[0011] In a possible implementation, the initial planar topology data further includes a function matrix and a boundary matrix. Determining the initial planar topology data and the multi - constraint condition data corresponding to the initial building floor plan includes:

[0012] Based on the graph axes in at least two directions, divide the initial building floor plan into multiple cells;

[0013] Based on the multiple cells, determine the function matrix and the boundary matrix;

[0014] Among them, the function matrix is used to indicate the function information of each cell, and the boundary matrix is used to indicate the boundary information of each cell in at least two directions.

[0015] In a possible implementation, the function information indicates that the cell is any one or more of the outside world, living room, dining room, kitchen, bathroom, master bedroom, secondary bedroom, balcony, open area, master bathroom, storage room, load - bearing structure, custom function type;

[0016] The boundary information is used to represent that the associated cell boundary is any one or more of completely open connection, invisible partition, openable passage connection, exterior wall, custom boundary type.

[0017] In a possible implementation, determining the initial planar topology data and the multi - constraint condition data corresponding to the initial building floor plan includes:

[0018] Based on the objective restriction information and / or quantifiable user demand information, use the index identifier of the graph axis and the position in the preset coordinate system to represent the multi - constraint condition data;

[0019] Among them, the objective restriction information includes any one or more of the load - bearing wall position information, exterior window position information, ventilation duct position information, drainage facility pipeline position information; the user demand information includes any one or more of the demand information related to the number and scale of rooms, the expected wall transformation ratio of the user, other user - defined restriction information.

[0020] In a possible implementation, optimizing the initial planar topology data based on the multi - constraint condition data to obtain the target planar topology data includes:

[0021] Under the constraint of multi-constraint condition data, mutate and cross the initial planar topological data to obtain multiple updated planar topological data. The mutation operation and the cross operation include operations on any one or more of the graph axis sequence, the function matrix, and the boundary matrix;

[0022] Calculate the fitness function values corresponding to the multiple updated planar topological data respectively;

[0023] Optimize the initial planar topological data based on the fitness function values corresponding to the multiple updated planar topological data respectively to obtain the target planar topological data.

[0024] In a possible implementation manner, the fitness function value is determined based on any one or more of the scale evaluation results of each room in the planar topological data, the shape evaluation results of each room, the openness evaluation result of the building floor plan corresponding to the planar topological data, and the inspection results of the multi-constraint condition data.

[0025] In a possible implementation manner, the method further includes:

[0026] Based on the initial planar topological data corresponding to the initial building floor plan and / or the multi-constraint condition data, match the initial building floor plan with the building case floor plans in the preset dataset to obtain one or more matching floor plans;

[0027] Use one or more matching floor plans as the initial building floor plan, and use the planar topological data of the matching floor plan as the initial planar topological data.

[0028] According to another aspect of the present disclosure, there is provided a building floor plan optimization device based on graph axis coding. The device includes:

[0029] A first determination module, configured to determine the initial planar topological data corresponding to the initial building floor plan and the multi-constraint condition data. The initial planar topological data is obtained by segmenting and encoding the initial building floor plan based on the graph axis. The multi-constraint condition data is associated with the graph axis and represents the restriction information related to the initial building floor plan;

[0030] An optimization module, configured to optimize the initial planar topological data based on the multi-constraint condition data to obtain the target planar topological data;

[0031] A second determination module, configured to obtain the target building floor plan based on the target planar topological data.

[0032] In a possible implementation manner, the initial planar topological data includes a graph axis sequence, and the graph axis sequence is used to indicate the position information of the graph axes in at least two preset directions. The at least two directions include the horizontal and vertical directions, and each direction includes at least two graph axes.

[0033] In a possible implementation, the initial planar topological data further includes a function matrix and a boundary matrix. The first determination module is configured to:

[0034] Divide the initial building floor plan into multiple cells based on the graph axes in at least two directions;

[0035] Determine the function matrix and the boundary matrix based on the multiple cells;

[0036] Wherein, the function matrix is used to indicate the function information of each cell, and the boundary matrix is used to indicate the boundary information of each cell in at least two directions.

[0037] In a possible implementation, the function information indicates that the cell is any one or more of the outside world, living room, dining room, kitchen, bathroom, master bedroom, secondary bedroom, balcony, open area, master bathroom, storage room, load-bearing structure, custom function type;

[0038] The boundary information is used to represent that the associated cell boundary is any one or more of a fully open connection, an invisible partition, an openable and closable passage connection, an external wall, a custom boundary type.

[0039] In a possible implementation, the first determination module is configured to:

[0040] Based on the objective constraint information and / or the quantifiable user demand information, use the index identifier of the graph axis and the position of the preset coordinate system to represent the multi-constraint condition data;

[0041] Wherein, the objective constraint information includes any one or more of load-bearing wall position information, external window position information, ventilation duct position information, drainage facility pipeline position information; the user demand information includes any one or more of demand information related to the number and scale of rooms, the expected wall renovation ratio of the user, other user-defined constraint information.

[0042] In a possible implementation, the optimization module is configured to:

[0043] Under the constraint of the multi-constraint condition data, perform mutation and crossover operations on the initial planar topological data to obtain multiple updated planar topological data. The mutation operation and the crossover operation include operations on any one or more of the graph axis sequence, the function matrix, and the boundary matrix;

[0044] Calculate the fitness function values corresponding to the multiple updated planar topological data respectively;

[0045] Optimize the initial planar topological data based on the fitness function values respectively corresponding to the multiple updated planar topological data to obtain the target planar topological data.

[0046] In a possible implementation, the fitness function value is determined based on any one or more of the scale evaluation results of each room in the planar topology data, the shape evaluation results of each room, the openness evaluation result of the building floor plan corresponding to the planar topology data, and the inspection result of the multi-constraint condition data.

[0047] In a possible implementation, the apparatus further includes:

[0048] A matching module, configured to match the initial building floor plan with the building case floor plans in the preset dataset based on the initial planar topology data corresponding to the initial building floor plan and / or the multi-constraint condition data, to obtain one or more matching floor plans;

[0049] A third determination module, configured to use one or more matching floor plans as the initial building floor plan, and use the planar topology data of the matching floor plan as the initial planar topology data.

[0050] According to another aspect of the present disclosure, there is provided a building floor plan optimization apparatus based on graph axis coding, including a memory, a processor, and a computer program stored on the memory, where the processor executes the computer program to implement the steps of the above method.

[0051] According to another aspect of the present disclosure, there is provided a non-volatile computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0052] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, or a non-volatile computer-readable storage medium carrying the computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0053] According to an embodiment of the present disclosure, by determining initial plane topology data corresponding to an initial building floor plan and multi - constraint condition data, the initial plane topology data is obtained by segmenting and encoding the initial building floor plan based on graph axes, and the multi - constraint condition data is associated with the graph axes and represents restriction information related to the initial building floor plan; optimizing based on the initial plane topology data and the multi - constraint condition data to obtain target plane topology data; and obtaining a target building floor plan based on the target plane topology data, it is possible to use a graph - axis - based strategy to effectively encode the building floor plan into a form that can be calculated and optimized by a computer while retaining necessary elements and information, realizing the optimization process of the building floor plan. Among them, by adding graph - axis elements and constructing the topological relationship in mathematics of the plane topology data structure, the decoupling of the real position of building elements in the actual physical space and the position of elements in the plane topology data is realized, thereby reducing the arithmetic operations in computer language for morphological operations such as moving walls, moving rooms, and cutting rooms in the architectural sense, significantly reducing the operation complexity, and the types of building elements can be expanded at any time according to requirements. By associating the multi - constraint condition data with the graph axes, the relevant restriction information can be recorded and operated by associating with the graph axes without separate storage, and the data volume is more streamlined. The embodiment of the present disclosure can effectively balance the contradiction among data volume, operability, and operation accuracy during the optimization process.

[0054] Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The drawings included in and constituting a part of this specification, together with the specification, illustrate exemplary embodiments, features, and aspects of the present disclosure and are used to explain the principles of the present disclosure.

[0056] Figure 1 A schematic diagram showing the encoding of a building floor plan using a rectangular frame arrangement.

[0057] Figure 2 A schematic diagram showing the encoding of a building floor plan using a graph structure.

[0058] Figure 3 A schematic diagram showing the encoding of a building floor plan using a grid.

[0059] Figure 4 A schematic diagram showing an application scenario according to an embodiment of the present disclosure.

[0060] Figure 5 A flowchart showing a method for optimizing a building floor plan based on graph - axis encoding according to an embodiment of the present disclosure.

[0061] Figure 6 An example of a building floor plan according to an embodiment of the present disclosure.

[0062] Figure 7 A schematic diagram showing the segmentation of an architectural floor plan using a graph axis according to an embodiment of the present disclosure.

[0063] Figure 8 A schematic diagram showing the encoding of an architectural floor plan according to an embodiment of the present disclosure.

[0064] Figure 9 A schematic diagram showing the operation of planar topological data according to an embodiment of the present disclosure.

[0065] Figure 10 A schematic diagram showing multi - constraint condition data according to an embodiment of the present disclosure.

[0066] Figure 11 A structural diagram showing a building plane optimization device based on graph - axis encoding according to an embodiment of the present disclosure.

[0067] Figure 12 It is a block diagram of a device 1900 for building plane optimization shown according to an exemplary embodiment. Detailed implementation manners

[0068] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the drawings denote elements having the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings do not have to be drawn to scale unless otherwise specified.

[0069] As used herein, the terms "comprising", "including", "having", or their variants are open - ended and include one or more stated features, wholes, elements, steps, components, or functions, but do not exclude the existence or addition of one or more other features, wholes, elements, steps, components, functions, or groups thereof.

[0070] When an element is referred to as being "connected", "coupled", "responsive" or a variant thereof to another element, it can be directly connected, coupled, or responsive to the other element, or there can be an intermediate element.

[0071] Although terms such as first, second, third, etc. may be used herein to describe various elements / operations, these elements / operations should not be limited by these terms. These terms are only used to distinguish one element / operation from another. Thus, without departing from the teachings of the inventive concept, a first element / operation in some embodiments can be referred to as a second element / operation in other embodiments.

[0072] The word "exemplary" used herein means "serving as an example, embodiment, or illustration". Any embodiment illustrated as "exemplary" herein does not have to be construed as being superior to or better than other embodiments.

[0073] In addition, to better illustrate the present disclosure, numerous specific details are given in the following detailed description. Those skilled in the art should understand that the present disclosure can be implemented without some specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art are not described in detail so as to highlight the gist of the present disclosure.

[0074] With the development of computer technology, generating and transforming architectural floor plans using related computer technology has gradually become a classic problem in the field of Computer Aided Architecture Design (CAAD). However, how to convert the architectural floor plans used by architects into a form that can be computed by a computer and further assist in architectural renovation remains the core challenge in this field. In the process of architectural floor plan optimization, the choice of coding method is crucial. An efficient coding method can not only improve the computational efficiency of the optimization process but also significantly optimize the quality of the final result, providing more accurate and flexible support for architectural renovation.

[0075] In existing coding methods, there is often a problem of over-simplifying architectural elements in architectural floor plans, and most methods lack attention to room boundary information and often process the floor plan in the form of wall segments, room units, etc. Some exemplary existing classic coding methods include:

[0076] (1) A method of encoding an architectural floor plan using a point cloud and rectangular frame arrangement. Among them, the method using a point cloud often does not include the description of room boundaries and internal connectivity relationships in the floor plan, missing a lot of information in the architectural floor plan. And the method using rectangular frame arrangement uses rectangular dissection as a specific layout unit. When determining the number of rooms and searching for all possible combination ways of rooms as much as possible, due to the geometric properties of the rectangle itself, the number of solution spaces will be smaller than that of the point cloud. Figure 1 A schematic diagram showing the encoding of an architectural floor plan using a rectangular frame arrangement is shown. As Figure 1 shown, H1 to H4 are different schematic diagrams of rectangular frame arrangements, and the identification of room functions is within the square frame.

[0077] (2) A method of encoding an architectural floor plan using a graph structure. Figure 2 A schematic diagram showing the encoding of an architectural floor plan using a graph structure is shown. As Figure 2 shown, the graph structure coding method is similar to the function bubble diagram commonly used in the architectural field. See Figure 2In (a) and (b), rooms are mostly used as nodes (such as the circular blocks in the figure, with the identification of room functions inside the circles), and the connection relationships between connected rooms are stored through the connection of edges (such as the line segments connecting each circular block in the figure), and additional boundary information can be stored therein. However, for similar methods of storing elements such as rooms and boundaries separately, during the optimization process, when a single element is changed, it is necessary to calculate new boundaries and update the relevant nodes involved. The operation of node update is complex, and the change of a single node will affect multiple nodes. This increases the cost of dividing space and adding or deleting elements in the calculation. Operations such as dividing space and moving boundaries are also very complex.

[0078] (3) A method of encoding the building floor plan using a grid. Figure 3 A schematic diagram showing the encoding of the building floor plan using a grid. As Figure 3 shown, the encoding method using a grid is the most intuitive encoding method, which directly discretizes the building floor plan and represents it in the form of a grid (such as the blue lines in the figure). As shown in the upper left and lower left figures in the figure, they represent the grid forms before and after optimization respectively. The rightmost figure in the figure represents the room range division corresponding to the optimized grid (the division area includes the identification of room functions). It can be seen that the room range is completely determined by the grid it occupies. Since the encoding method using a grid directly discretizes the floor plan, the formed room size data is an approximation of the real floor plan. In terms of accuracy, the accuracy of a rough grid is insufficient, while a fine grid will bring too much computational overhead, and it is difficult to balance accuracy and computational overhead. In addition, its room division is determined by the initial grid size, and it is also difficult to continuously and finely adjust the size during subsequent optimization.

[0079] In the problem of remodeling the building floor plan, especially optimizing the residential floor plan, a more suitable floor plan expression method is needed. For high-quality floor plan optimization tasks, the encoding method needs to balance flexible changes and precise operations on spatial boundaries. Currently, there is still a lack in this aspect in this field.

[0080] As mentioned above, these methods increase the complexity of common operations (such as wall movement, room function conversion, etc.) in building remodeling and limit the scalability of the method. Therefore, there is an urgent need for a flexible building plane optimization method that can encode the building floor plan into a form that can be operated by a computer to support the need for optimizing the building floor plan and effectively balance the contradiction between data volume, operability, and operation accuracy during the optimization process.

[0081] In view of this, the present disclosure provides a method, an apparatus, and a storage medium for optimizing building plans based on graph-axis encoding. The method of the embodiments of the present disclosure determines initial planar topological data and multi-constraint condition data corresponding to an initial building plan. The initial planar topological data is obtained by segmenting and encoding the initial building plan based on graph axes, and the multi-constraint condition data is associated with the graph axes and represents the restriction information related to the initial building plan. Optimization is performed based on the initial planar topological data and the multi-constraint condition data to obtain target planar topological data. Based on the target planar topological data, a target building plan is obtained. It is possible to use a graph-axis-based strategy to effectively encode the building plan into a form that can be calculated and optimized by a computer while retaining necessary elements and information, and to implement the optimization process of the building plan. By adding graph-axis elements, the topological relationship in the mathematical structure of the planar topological data is constructed, realizing the decoupling of the actual physical space position of the building elements from their positions in the planar topological data. Thus, the computational operations in computer language for morphological operations such as moving walls, moving rooms, and cutting rooms in the architectural sense are reduced, significantly lowering the operation complexity, and the types of building elements can be expanded at any time according to requirements. By associating the multi-constraint condition data with the graph axes, the relevant restriction information can be recorded and operated by associating with the graph axes without separate storage, making the data volume more concise. The embodiments of the present disclosure can effectively balance the contradiction among data volume, operability, and operation accuracy during the optimization process.

[0082] Figure 4 FIG. shows a schematic diagram of an application scenario according to an embodiment of the present disclosure. The system for optimizing building plans based on graph-axis encoding according to the embodiments of the present disclosure can be used in scenarios for optimizing residential floor plans, such as Figure 4 As shown, the system for optimizing building plans based on graph-axis encoding according to the embodiments of the present disclosure can obtain an initial building plan to be renovated and the renovation requirements of a user, so as to determine the initial planar topological data and multi-constraint condition data corresponding to the initial building plan. By performing optimization based on the initial planar topological data and the multi-constraint condition data, target planar topological data is obtained. Finally, the system for optimizing building plans based on graph-axis encoding can output the renovated building plan corresponding to the target planar topological data.

[0083] The system for optimizing building plans based on graph-axis encoding according to the embodiments of the present disclosure can also be used in scenarios for optimizing building plans of other types (such as office premises, etc.) other than residential floor plans. The embodiments of the present disclosure do not limit this.

[0084] The above-mentioned building floor plan optimization system based on graph-axis coding can be deployed on a terminal device or a server. The terminal device involved in the embodiments of the present disclosure can be any one or more of a mobile phone, a foldable electronic device, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a personal digital assistant (PDA), and a vehicle-mounted device. The embodiments of the present disclosure do not impose any special restrictions on the specific type of the terminal device, and it can have wired or wireless communication functions.

[0085] The server involved in the embodiments of the present disclosure can be located locally or in the cloud. It can be a physical device or a virtual device, such as a virtual machine, a container, etc., and has a wireless communication function. Among them, the wireless communication function can be set in the chip (system) or other components or assemblies of the server. The wireless communication function can be implemented, for example, through mobile communication technologies such as 2G / 3G / 4G / 5G, as well as Wi-Fi, Bluetooth, frequency modulation (FM), data radio, satellite communication, etc. It can also communicate through a wired connection to achieve interaction with other devices.

[0086] The following takes the scenario of renovating a residential floor plan as an example to introduce the building floor plan optimization method based on graph-axis coding in the embodiments of the present disclosure. Refer to Figure 5 , which shows a flowchart of the building floor plan optimization method based on graph-axis coding according to the embodiments of the present disclosure. This method can be used in the above-mentioned building floor plan optimization system, such as Figure 5 shown, this method may include:

[0087] Step S501, determining the initial plane topology data and multi-constraint condition data corresponding to the initial building floor plan.

[0088] The initial building floor plan can be the building floor plan to be renovated, which is used to represent the building space layout, and usually shows the relative positions and dimensions of building elements such as rooms, walls, doors, windows, and stairs from a top-down perspective. The building floor plan in the embodiments of the present disclosure can be a residential floor plan. Figure 6 shows an example of a building floor plan according to the embodiments of the present disclosure. As Figure 6 shown, this building floor plan shows the outer contour boundary of the residential floor and the internal layout of the residence (including the functions, positions, and relative dimensions of each room). The horizontal and vertical dimensions are shown around the building floor plan, indicating the specific lengths of each part of the building.

[0089] Relative to Figure 6The building plan shown, the initial building plan of the embodiment of the present disclosure may include more or less content, for example, only showing the outer contour boundary of the building.

[0090] The following first introduces the method of obtaining plan topology data based on the encoding of the building plan in the embodiment of the present disclosure. The present disclosure is that the building plan can be converted into a list, a two-dimensional array, etc. that can be calculated and indexed by a computer in the embodiment. The building plan can be calculated and optimized using an algorithm, can be added, deleted, modified, and checked conveniently, and the elements and information of the original building plan are retained as much as possible.

[0091] In the process of architectural design, the axis is generally used as the basic reference skeleton of the building plan to indicate the layout of the main support system and enclosure structure (including columns, beams, walls, slabs, etc.) of the building. In the embodiment disclosed in the present invention, the idea of enclosure in architectural design to generate space and the axis network formed by the axis is used to control the overall scale and layout of the building. The building plan is divided into cells for digital coding based on the axis in at least two directions, thereby constructing a coding method that can retain the information in the original plan as much as possible, facilitate algorithm operation and calculation, and maintain a streamlined data volume. It not only conforms to the layout idea of the architectural design process, but also solves the shortcomings faced by the existing plan coding method, and is helpful for the subsequent process of building plan optimization.

[0092] The initial plane topology data can be obtained by segmenting and encoding the initial building floor plan based on the graph axis.

[0093] Figure 7 A schematic diagram of segmenting a building plan using a graph axis according to an embodiment of the present disclosure is shown. Figure 7 The axes shown in the figure will be Figure 6 The building plan shown in the figure is divided, and the axes may include axes in at least two directions. For example, the at least two directions may include a horizontal direction (i.e., a horizontal axis, such as the green dotted line in the figure) and a vertical direction (i.e., a longitudinal axis, such as the red dotted line in the figure), and each direction may include a preset number (at least two) of axes.

[0094] In the disclosed embodiment, the building plan may be encoded by an axis sequence, a functional matrix, and a boundary matrix, and the initial plane topology data may include the axis sequence, the functional matrix, and the boundary matrix obtained after encoding the initial building plan.

[0095] In step S501, the sequence of graph axes may be determined according to the position information of the graph axes, and further:

[0096] Based on at least two directions of drawing axes, the initial building plan is divided into a plurality of cells; based on the plurality of cells, a function matrix and a boundary matrix are determined.

[0097] In the encoding method of the embodiments of the present disclosure, the building floor plan is divided into multiple cells, such that a room is essentially a collection of a series of cells. Several adjacent cells with the same functional label and connected boundaries can be judged as a separate room. The "room" in the embodiments of the present disclosure does not depend on specific position or topological information, and any operation on a room can be converted into an operation on cells. Therefore, any building-related operation only needs to traverse the cells and boundaries involved, which can effectively save computing resources. For example, to determine whether two rooms are adjacent, it is not necessary to calculate their geometric positions, but only to judge whether there is an intersection in their boundary indices; for another example, the change of the room boundary can be converted into an operation on cells without affecting other objects.

[0098] Figure 8 A schematic diagram showing the encoding of a building floor plan according to an embodiment of the present disclosure is presented. Based on Figure 7 the axis division method shown in, examples of the axis sequence, functional matrix, and boundary matrix obtained after encoding the building floor plan can be as Figure 8 shown in.

[0099] The axis sequence can be used to indicate the position information of the axes in at least two preset directions. The at least two directions include the horizontal and vertical directions, and each direction includes at least two axes. This position information can be the position in a preset coordinate system, and this preset coordinate system can be the preset coordinate system in the building floor plan, such as Figure 8 the coordinate system with the upper left corner as the origin shown in. The position information of the axes in different directions can be represented by different axis sequences. As shown in the figure, for i horizontal axes and j vertical axes, it can be represented as [[a_1,…,a_i],[b_1,…,b_i]]. The axis sequence corresponding to the 0 axis can represent the positions of the axes in the horizontal direction (in the form of [a_1,…,a_i], and each element corresponds to the position of a horizontal axis), and the axis sequence corresponding to the 1 axis can represent the positions of the axes in the vertical direction (in the form of [b_1,…,b_i], and each element corresponds to the position of a vertical axis). The positions of the axes can be associated with the outer contour and / or internal boundaries of the building. By combining the axis positions indicated in the axis sequence with the subsequent boundary matrix, the outer contour and internal boundaries of the building can be determined.

[0100] For the encoded building floor plan, the number of axes can be increased or decreased to meet the requirements of refinement or coarsening. The spacing and order of the axes can also be adjusted to meet different design requirements.

[0101] The function matrix can be used to indicate the function information of each cell. For examples of cells, reference can be made to the 35 (7×5) cells obtained by dividing with 8 horizontal axes and 6 vertical axes in the figure. The function information can represent any one or more of the following for the cell: the outside world, living room, dining room, kitchen, bathroom, master bedroom, secondary bedroom, balcony, open area (i.e., public areas in the building plan, such as corridors, porches, foyers, corner spaces, transition spaces, circulation halls, etc.), master bathroom, storage room, load-bearing structure, and custom function types. Table 1 shows an example of the function matrix coding according to an embodiment of the present disclosure.

[0102] Table 1

[0103]

[0104] Referring to Table 1, for i horizontal axes and j vertical axes, the number of cells that can be divided is (i - 1)×(j - 1). The size of the function matrix can be (i - 1)×(j - 1), and each element can correspond to a cell (arranged in the order from left to right and top to bottom in the building plan). The value of each element, which is the above-mentioned digital code, can be determined according to the function of the corresponding cell.

[0105] For a room in the building plan, it can be divided into one or more cells. Refer to Figure 7 the 10 rooms (room0 to room9, and the functions of different rooms are represented by the text labels in Table 1). Taking room2 (text label 'living room', representing the living room) as an example, this living room is divided into six cells. Then these six cells point to the same functional space. Refer to Figure 8 and their values in the function matrix are all 0.

[0106] The boundary matrix can be used to indicate the boundary information of each cell in at least two directions. The boundary information is used to represent the type of the boundary of the associated cell, for example, including fully open connection (i.e., the cell boundary is in the open space inside the building and there is no partition), invisible partition (i.e., the cell boundary is an invisible partition inside the building, such as an internal wall), openable passage connection (i.e., the cell boundary is a door, window, etc.), external wall (i.e., the cell boundary is the building external wall), and any one or more of custom boundary types. The boundary matrix can include one or more, and the boundary information in each direction can correspond to a boundary matrix, representing the boundary type of each cell in this direction. Table 2 shows an example of the boundary matrix coding according to an embodiment of the present disclosure.

[0107] Table 2

[0108]

[0109] Referring to Table 2, in the order of cells from left to right and from top to bottom in the building floor plan, each element in the boundary matrix can represent the boundary type of the cell in that direction, and the value of each element is the digital code in Table 2, which can be determined according to the corresponding boundary type (such as the function name in Table 2).

[0110] For i horizontal axes and j vertical axes, (i - 1)×(j - 1) cells can be divided. The boundary information of the boundaries of each cell in the horizontal direction on the horizontal axis (such as the upper boundary and the lower boundary) can be referred to Figure 8 in the boundary matrix corresponding to axis 0 in [reference]. Its size can be i×(j - 1). Among them, the matrix rows can be used to indicate the corresponding horizontal axes, and the matrix columns can be used to indicate the corresponding boundary segments on the horizontal axes. Each element can correspond to a segment of the boundary on the horizontal axis (that is, the upper boundary / lower boundary of a certain cell). For example, the first element in the first row of the boundary matrix corresponding to axis 0 can represent the boundary type of the first horizontal axis in the segment [0, 60] (the value is 3, indicating an external wall), the second element in the first row can represent the boundary type of the first horizontal axis in the segment [60, 100], the first element in the second row can represent the boundary type of the second horizontal axis in the segment [0, 60], and so on.

[0111] The boundary matrix in the vertical direction can be referred to Figure 8 in the boundary matrix corresponding to axis 1 in [reference]. Its size can be (i - 1)×j. Among them, the matrix columns can be used to indicate the corresponding vertical axes, and the matrix rows can be used to indicate the corresponding boundary segments on the vertical axes. Each element can correspond to a segment of the boundary on the vertical axis (that is, the left boundary / right boundary of a certain cell). For example, the first element in the first row of the boundary matrix corresponding to axis 1 can represent the boundary type of the first vertical axis in the segment [0, 240] (the value is 3, indicating an external wall), the first element in the second row can represent the boundary type of the first vertical axis in the segment [240, 350], the first element in the second row can represent the boundary type of the second vertical axis in the segment [0, 240], and so on. Figure 8 In the above, the boundary matrix is only shown by taking the position of the external wall of the residence as an example, and the boundaries of the internal rooms of the residence can also be represented by the boundary matrix, which is not limited in the embodiments of the present disclosure.

[0112] The digital codes involved in Table 1 and Table 2 can be increased or decreased as needed to meet the usage requirements such as different building types, different spatial connection relationships, specific limiting conditions such as daylighting and ventilation, etc. For unconventional structures that may exist in a building (such as large support columns), uncommon building elements (such as indoor elevator shafts), etc., the coding of unconventional structures can be achieved by adding functions, corresponding digital codes in the boundary matrix, etc. For irregular shapes, the coding of irregular shapes can also be achieved by additionally introducing boundary vertices (for example, additional tuples can be added to the boundary matrix, and the boundary vertices of the irregular shape are recorded in the tuples) or adding inclined direction diagram axes, etc., which has great scalability.

[0113] By using the diagram axis sequence, boundary matrix, and function matrix of the embodiments of the present disclosure to represent the building floor plan, the boundary positions and types of the overall building plane and the interior can be determined, and the description of the functions of the interior spaces of the building can be realized.

[0114] In the embodiments of the present disclosure, by introducing the diagram axis, the preset coordinate system position in the building floor plan can be transformed into a corresponding spatial index (i.e., the diagram axis sequence) with the help of the axis network to quickly judge the spatial relationship. By using the diagram axis elements as scale control factors, while greatly reducing the number of divided cells, the continuous and accurate real spatial position expression is achieved by relying on the movement of the diagram axis.

[0115] In addition, by constructing the topological relationship of the data structure in mathematics, the planar topological data is obtained, realizing the decoupling of the real position of the element in the actual physical space and the position of the element in the data structure, thereby reducing the arithmetic operations in computer language for morphological operations such as moving walls, moving rooms, and cutting rooms in the architectural sense. See Figure 9 , which shows a schematic diagram of operating on the planar topological data according to the embodiments of the present disclosure. As Figure 9 The uppermost figure in shows an example of dividing a building floor plan into 6 cells by using 3 vertical axes and 4 horizontal axes, and different colors in the cells represent different functions. Based on the data structure of the embodiments of the present disclosure, as shown in the middle figure, if you want to modify the functional attribute of cell 2, only the value of the corresponding cell in the function matrix needs to be modified; as shown in the lowermost figure, if you want to modify the functional attribute of cell 3 and modify the position of horizontal axis 1, only the value of the corresponding cell 3 in the function matrix needs to be modified, and the position corresponding to horizontal axis 1 in the diagram axis sequence needs to be modified. It can be seen that, for example, when the boundary position changes or the corresponding diagram axis position changes, only the corresponding data in the diagram axis sequence needs to be modified, without changing the record of the position information corresponding to the edges in the corresponding topological structure, because the position information of the edges can be obtained from the diagram axis sequence through the natural index association relationship.

[0116] The planar topological data structure constructed in the embodiments of the present disclosure uses cells and graph axes as basic units. When performing a change operation on a certain element, it can greatly reduce the impact on the remaining data, reduce the element operation cost, and facilitate the use of various subsequent optimization algorithms. Moreover, through such a coding method, it can be closely connected by means of reliable index association characteristics to accurately describe the adjacent relationship, topological structure, and position information, and construct a coding method that can retain as much information as possible in the original floor plan, facilitate algorithm operations and calculations, and at the same time maintain a reduced data volume, which is convenient for flexible and precise changes to the dimensions during the subsequent optimization process of the building floor plan.

[0117] The multi-constraint condition data can represent the optimization objectives applicable to the above coding method. This multi-constraint condition data is associated with the graph axis and can represent the restriction information related to the initial building floor plan. In step S501, it is possible to:

[0118] Based on the objective restriction information and / or quantifiable user demand information, use the index identifier of the graph axis and the position in the preset coordinate system to represent the multi-constraint condition data.

[0119] Among them, the objective restriction information can include any one or more of the load-bearing wall position information, external window position information, ventilation duct position information, and drainage facility pipeline position information; the user demand information includes demand information related to the number and scale of rooms, the expected wall transformation ratio of the user (for example, due to cost considerations, the user may expect to retain as much of the original wall as possible), and any one or more of other user-defined restriction information (such as whether to accept an open kitchen, whether to customize special rooms, etc.). In addition, according to the different optimization objectives and optimization methods used, the above objective restriction information and user demand information can not only include quantitative data and hard constraints, but may also include other quantifiable soft constraints or flexible requirements, which can be extended according to the needs of specific application scenarios. The types and forms of design restrictions can also be extended according to user needs, such as adding cost restriction conditions, lighting and ventilation restriction conditions, etc.

[0120] The objective restriction information and user demand information can be linear restriction information (such as the restriction information related to load-bearing walls, external windows, etc.), or non-linear restriction information (such as the room restriction information about surfaces).

[0121] The index identifier of the graph axis can be used to indicate the direction of the graph axis (for example, the graph axis in the horizontal direction or the vertical direction). In the embodiments of the present disclosure, there is no limitation on the method of converting the objective restriction information and / or quantifiable user demand information into multi-constraint condition data represented by the index identifier of the graph axis and the position in the preset coordinate system. According to different implementation conditions, it can be converted based on related technologies such as manual entry, rule-based translation, existing data, algorithm generation, and large model method generation.

[0122] Figure 10 A schematic diagram showing multi - constraint condition data according to an embodiment of the present disclosure. As Figure 10 shown, an example of converting objective restriction information and user requirement information into the expression of multi - constraint condition data based on the data structure of planar topological data is given.

[0123] For example, multi - constraint condition data can be constructed through a special "Restriction" class. The line - type restriction information in the above - mentioned multi - constraint condition data can be described by a tuple internally containing two sub - tuples. The first sub - tuple can have two numerical elements (for example, of int type), which are used to describe the index identifier of the axis in the graph where the object related to the constraint is located and the corresponding coordinate position of the axis (the position in a preset coordinate system). The second sub - tuple can also have two numerical elements (for example, of int type), which are used to describe the starting coordinate position and the ending coordinate position of the constraint. For example, for the constraint on the location of the entry door, the first sub - tuple (1, 1100) can indicate that the entry door is on the vertical axis with a coordinate position of 1100 (the corresponding graph axis index identifier is 1). The second sub - tuple (420, 520) can indicate that the starting coordinate position of the entry door on this vertical axis is 420 and the ending coordinate position is 520.

[0124] Since the above - mentioned coordinate positions can be transformed into corresponding spatial index identifiers with the help of the axis network to quickly judge spatial relationships, many restriction conditions can be flexibly represented by coordinate positions without worrying about the complexity of determination and calculation.

[0125] For non - line - type restriction information, it can be described according to the corresponding coordinate positions. For example, for planar room restrictions (such as the 'living room' in the example), it can be described by the four coordinate positions of the four corners.

[0126] In the subsequent optimization process, it is possible to correct sub - optimal optimization schemes or eliminate in advance the optimization directions that do not meet the requirements by verifying whether the above - mentioned restriction factors are met in the optimization scheme, so as to complete the guidance for the subsequent floor plan generation direction.

[0127] In the embodiment of the present disclosure, the initial building floor plan may include less content. For example, only the outer contour is shown. When the change in optimization requirements is relatively large, it is less efficient to start the optimization from the current initial building floor plan. In order to quickly and efficiently generate a suitable pattern type in the subsequent optimization process. The method may further include:

[0128] Based on the initial planar topology data corresponding to the initial building floor plan and / or the multi-constraint condition data, match the initial building floor plan with the building case floor plans in the preset dataset to obtain one or more matching floor plans; use the one or more matching floor plans as the initial building floor plan, and use the planar topology data of the matching floor plans as the initial planar topology data.

[0129] Among them, the preset dataset may include at least one preset building case floor plan. Among them, by calculating the similarity between the initial planar topology data and / or the multi-constraint condition data corresponding to the initial building floor plan and the preset building case floor plan, select one or more building case floor plans with the highest similarity as the matching floor plans, and further optimize on the basis of these matching floor plans to obtain the target planar topology data that meets the optimization requirements.

[0130] In the process of calculating the similarity, some or all dimensions can be selected from the initial planar topology data and / or the multi-constraint condition data for similarity comparison according to the needs of the actual application scenario. For example, in the scenario of residential floor plan optimization, the multi-constraint conditions include the position constraints of the bathroom, kitchen, and living room. Then, the relative positions of the bathroom, kitchen, and living room and the outer contour of the residential floor plan can be used together as the standard for similarity calculation to ensure that the matching cases can better meet the multi-constraint conditions of the current residential renovation task.

[0131] The above process of calculating the similarity can be implemented based on related technologies, such as using comparison methods of geometric distance or statistical indicators. The embodiments of the present disclosure do not limit this.

[0132] Step S502, optimize the initial planar topology data based on the multi-constraint condition data to obtain the target planar topology data.

[0133] The optimization method can be any optimization generation method. In the embodiments of the present disclosure, a genetic algorithm (GA) can be used for optimization, which has advantages such as parallel search, strong inclusiveness, ability to find Pareto optimal solutions, easy combination with other methods, dynamic adaptation to the environment, and maintenance of solution diversity (i.e., preventing premature convergence to local optimal solutions). In step S502, it can be:

[0134] Under the constraints of the multi-constraint condition data, perform mutation and crossover operations on the initial planar topology data to obtain multiple updated planar topology data; calculate the fitness function values corresponding to the multiple updated planar topology data respectively; optimize based on the fitness function values corresponding to the multiple updated planar topology data respectively to obtain the target planar topology data.

[0135] Among them, the mutation operation and the crossover operation may include operations on any one or more of the graph axis sequence, the function matrix, and the boundary matrix.

[0136] For example, the mutation operation can be performed by constructing a mutation operator. Under the premise of meeting the constraint conditions (i.e., the constraint conditions indicated by the multi-constraint condition data), any one or more of the graph axis movement mutation, function matrix mutation, boundary matrix mutation, room contraction mutation, and room jump mutation can be carried out.

[0137] As an example of the mutation method, in the graph axis movement mutation, the mutation operator can select a free graph axis (i.e., an axis that can be moved. For example, the axis that can be moved can be preset in advance, or it can be determined whether the axis can be moved based on the multi-constraint condition data) for movement; in the function matrix mutation, the mutation operator can randomly select a boundary of a certain room and retrieve the cell functions on both sides of the boundary to exchange the functions on both sides (such as migrating the function outside the room to the cell inside the room, etc.); in the boundary matrix mutation, the mutation operator can change the value of any one or more segments of the boundary in the boundary matrix; in the room contraction mutation, the mutation operator can select all the cells represented by the minimum / maximum index of a certain room in the horizontal / vertical direction (for example, if the values of adjacent cells in this direction in the function matrix are the same, they can be considered as cells in the same room, and thus all the cells included in this room in this direction can be identified), give up all their functions and transfer them to the adjacent room to achieve a large-scale adjustment of the room boundary at a close distance; in the room jump mutation, the mutation operator can randomly select a room as the takeoff position and randomly select one of the cells included in another room as the landing position. The function of the room at the takeoff position will replace the value of the function matrix at the landing position. The adjacent cells at the landing position will be transformed into open areas to try to establish channels, and the room at the original takeoff position will be incorporated into the adjacent position, so as to provide more layout possibilities in the optimization task of adding new rooms.

[0138] The mutated planar topological data (corresponding to the mutated graphic individual) can be obtained through mutation operations. The crossover operator can be used to perform crossover operations based on the graph axes. In one example, a vertical axis and a horizontal axis can be randomly generated in the graphic individual before mutation (such as the initial building floor plan) and the graphic individual after mutation respectively. These two axes divide the graphic individual into four independent regions. A certain region in the graphic individual before mutation can be selected and replaced with the corresponding region in another mutated graphic individual. This replacement operation includes the graph axis sequence, function matrix, and boundary matrix within this region. Thus, the crossover recombination between the two graphic individuals is achieved. Since the crossover can be mutual and can be performed multiple times, no matter where the local structure worth preserving is located, it has the opportunity to be segmented and recombined by overlapping crossover operations. Thereby, not only the adaptability and efficiency of the genetic algorithm in dealing with planar structure optimization problems are enhanced, but also it helps to explore and implement more complex and diverse spatial function configuration schemes.

[0139] Thus, multiple (which can be two) updated planar topological data can be obtained. The fitness function value can be determined based on any one or more of the scale evaluation results of each room in the planar topological data, the shape evaluation results of each room, the openness evaluation result of the building floor plan corresponding to the planar topological data, and the inspection results of the multi - constraint condition data. The present application does not limit the specific calculation method of the fitness function value.

[0140] For example, for any updated planar topological data, the scale evaluation result of each room can represent the consistency of any one or more of the face width, depth, ratio, and area of each room in the floor plan corresponding to this planar topological data with a preset target (which can be determined based on the multi - constraint condition data). The higher the scale evaluation result of each room, the higher the corresponding fitness function value can be.

[0141] The shape evaluation result of each room is used to represent the compactness and regularity of the geometric shape of the room, and can be obtained by calculating the ratio of the actual area of the room to the area of the minimum circumscribed rectangle. The higher the shape evaluation result of each room, the higher the corresponding fitness function value can be.

[0142] The openness evaluation result of the building floor plan corresponding to the planar topological data can be determined by evaluating the openness of the entire floor plan (for example, it can be determined based on the ratio of the area of the above - mentioned open area to the total area of the floor plan), the stretching degree of the space in terms of face width and depth, whether there is an annular flow line or other excellent topological structures that promote spatial connectivity, etc. The higher the openness evaluation result of the building floor plan, the higher the corresponding fitness function value can be.

[0143] The inspection results of the multi-constraint condition data can be used to evaluate whether the building floor plan meets the constraints indicated by the multi-constraint condition data. When any constraint is violated, the fitness function value can be set to 0, indicating that the current optimization plan (i.e., the floor plan corresponding to the updated planar topological data) is infeasible.

[0144] Selection can be made based on the fitness function values corresponding to multiple updated planar topological data respectively, to obtain the selected planar topological data as the new initial planar topological data, and iteratively execute the above-mentioned mutation and crossover operations based on the initial planar topological data and the multi-constraint condition data, to obtain multiple updated planar topological data and subsequent steps, so as to obtain the selected planar topological data with the fitness function value meeting the preset conditions (such as the fitness function value converges or reaches the maximum number of iterations, etc.) as the target planar topological data.

[0145] The above selection method can be based on the tournament selection method, the elite selection method or the hybrid selection method. The embodiments of the present disclosure do not limit this. In an example of the hybrid selection method, when the fitness function values corresponding to multiple updated planar topological data are all 0, the one closer to the initial planar topological data can be selected as the selected planar topological data; for the case where the fitness function values corresponding to multiple updated planar topological data are equal and non-zero, one of them can be randomly selected as the selected planar topological data; for the case where the fitness function values corresponding to multiple updated planar topological data are not equal and are all non-zero, the one with the highest fitness function value can be selected as the selected planar topological data. Thus, the optimization process can converge at a faster speed, reduce the generation time, and maintain more population diversity, so as to promote the optimization process to explore the unknown solution space and find a better solution.

[0146] Step S503, based on the target planar topological data, obtain the target building floor plan.

[0147] According to the embodiment of the present disclosure, by determining the initial plane topology data and multivariate constraint data corresponding to the initial building plan, the initial plane topology data is obtained by segmenting and encoding the initial building plan based on the graph axis, and the multivariate constraint data is associated with the graph axis to represent the restriction information related to the initial building plan; optimization is performed based on the initial plane topology data and the multivariate constraint data to obtain the target plane topology data; based on the target plane topology data, the target building plan is obtained, and the use of a graph axis-based strategy can be achieved to effectively encode the building plan into a form that can be calculated and optimized by a computer while retaining necessary elements and information, thereby realizing the optimization process of the building plan, wherein by adding graph axis elements, the mathematical topological relationship of the plane topology data structure is constructed, and the decoupling of the real position of the building element in the actual physical space and the position of the element in the plane topology data is realized, thereby reducing the calculation operations of morphological operations in the architectural sense such as moving walls, moving rooms, and cutting rooms in computer language, so that the operation complexity is significantly reduced, and the types of building elements can be expanded at any time according to demand. By associating the multivariate constraint condition data with the graph axis, the relevant restriction information can be associated with the graph axis for recording and operation without separate storage, and the data volume is more streamlined. The disclosed embodiment can effectively balance the contradiction between data volume, operability and operation accuracy during the optimization process.

[0148] Among them, according to the encoding process of the above-mentioned building plan, based on the axis sequence, function matrix and boundary matrix of the target plane topology data, the spatial area of the plane under the preset coordinate system can be restored to obtain the target building plan. Through the encoding process and the restoration process, the geometric coordinates of the physical space can be converted into the basic cell index in the code, the lines of the physical space can be converted into the boundary index in the code, and the encoded file (i.e., the plane topology data) can also be effectively converted into the spatial area of the original building plan, realizing the conversion of the real physical space and the code.

[0149] Because the encoding process of the embodiment of the present disclosure retains various types of information and elements of the building floor plan as much as possible, according to the needs of the actual application scenario, the target plane topology data can also be converted into other floor plan encoding methods such as bitmap, point group, rectangle, graph structure, etc., and the embodiment of the present disclosure is not limited in comparison.

[0150] Figure 11 FIG. 2 shows a structural diagram of a building plane optimization device based on graph axis coding according to an embodiment of the present disclosure. Figure 11 As shown, the device comprises:

[0151] The first determination module 1101 is configured to determine the initial planar topology data and the multi - constraint condition data corresponding to the initial building floor plan. The initial planar topology data is obtained by segmenting and encoding the initial building floor plan based on the graph axes. The multi - constraint condition data is associated with the graph axes and represents the restriction information related to the initial building floor plan.

[0152] The optimization module 1102 is configured to optimize the initial planar topology data based on the multi - constraint condition data to obtain the target planar topology data.

[0153] The second determination module 1103 is configured to obtain the target building floor plan based on the target planar topology data.

[0154] In a possible implementation, the initial planar topology data includes a graph axis sequence, and the graph axis sequence is used to indicate the position information of the graph axes in at least two preset directions. The at least two directions include the horizontal and vertical directions, and each direction includes at least two graph axes.

[0155] In a possible implementation, the initial planar topology data further includes a function matrix and a boundary matrix. The first determination module is configured to:

[0156] Divide the initial building floor plan into multiple cells based on the graph axes in at least two directions;

[0157] Determine the function matrix and the boundary matrix based on the multiple cells;

[0158] Among them, the function matrix is used to indicate the function information of each cell, and the boundary matrix is used to indicate the boundary information of each cell in at least two directions.

[0159] In a possible implementation, the function information indicates that the cell is any one or more of the outside world, living room, dining room, kitchen, bathroom, master bedroom, secondary bedroom, balcony, open area, master bathroom, storage room, load - bearing structure, custom function type.

[0160] The boundary information is used to represent that the associated cell boundary is any one or more of a completely open connection, an invisible partition, an openable and closable passage connection, an exterior wall, a custom boundary type.

[0161] In a possible implementation, the first determination module is configured to:

[0162] Utilize the index identifier of the graph axis and the position in the preset coordinate system to represent the multi - constraint condition data based on the objective restriction information and / or quantifiable user demand information.

[0163] Among them, the objective constraint information includes any one or more of the load-bearing wall position information, external window position information, ventilation duct position information, and drainage facility pipeline position information; the user demand information includes any one or more of the demand information related to the number and scale of rooms, the expected wall reconstruction ratio of the user, and other user-defined constraint information.

[0164] In a possible implementation manner, the optimization module is used for:

[0165] Under the constraint of the multi-constraint condition data, perform mutation and crossover operations on the initial plane topology data to obtain multiple updated plane topology data. The mutation operation and the crossover operation include operations on any one or more of the graph axis sequence, function matrix, and boundary matrix;

[0166] Calculate the fitness function values corresponding to the multiple updated plane topology data respectively;

[0167] Optimize the initial plane topology data based on the fitness function values corresponding to the multiple updated plane topology data respectively to obtain the target plane topology data.

[0168] In a possible implementation manner, the fitness function value is determined based on any one or more of the scale evaluation results of each room in the plane topology data, the shape evaluation results of each room, the openness evaluation result of the building floor plan corresponding to the plane topology data, and the inspection results of the multi-constraint condition data.

[0169] In a possible implementation manner, the device further includes:

[0170] A matching module, configured to match the initial building floor plan with the building case floor plans in the preset dataset based on the initial plane topology data corresponding to the initial building floor plan and / or the multi-constraint condition data to obtain one or more matching floor plans;

[0171] A third determination module, configured to use one or more matching floor plans as the initial building floor plan and use the plane topology data of the matching floor plan as the initial plane topology data.

[0172] According to an embodiment of the present disclosure, by determining initial planar topological data corresponding to an initial building floor plan and multi - constraint condition data, the initial planar topological data is obtained by segmenting and encoding the initial building floor plan based on graph axes, and the multi - constraint condition data is associated with the graph axes and represents restriction information related to the initial building floor plan; optimizing based on the initial planar topological data and the multi - constraint condition data to obtain target planar topological data; and obtaining a target building floor plan based on the target planar topological data, it is possible to use a graph - axis - based strategy to effectively encode the building floor plan into a form that can be calculated and optimized by a computer while retaining necessary elements and information, realizing the optimization process of the building floor plan. Among them, by adding graph - axis elements and constructing the topological relationship in mathematics of the planar topological data structure, the decoupling of the real position of building elements in the actual physical space and the position of elements in the planar topological data is achieved, thereby reducing the arithmetic operations in computer language for morphological operations such as moving walls, moving rooms, and cutting rooms in the architectural sense, significantly reducing the operation complexity, and the types of building elements can be expanded at any time according to requirements. By associating the multi - constraint condition data with the graph axes, the relevant restriction information can be recorded and operated by associating with the graph axes without separate storage, and the data volume is more streamlined. The embodiment of the present disclosure can effectively balance the contradiction among data volume, operability, and operation accuracy during the optimization process.

[0173] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the methods described in the above - mentioned method embodiments. The specific implementation can refer to the description of the above - mentioned method embodiments. For the sake of brevity, it will not be repeated here.

[0174] The embodiment of the present disclosure also provides a building plane optimization device based on graph - axis encoding, including a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the above - mentioned method.

[0175] The embodiment of the present disclosure also provides a non - volatile computer - readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above - mentioned method are implemented.

[0176] The embodiment of the present disclosure also provides a computer program product, including a computer program, or a non - volatile computer - readable storage medium carrying the computer program. When the computer program is executed by a processor, the steps of the above - mentioned method are implemented.

[0177] Figure 12 It is a block diagram of a device 1900 for building plane optimization shown according to an exemplary embodiment. For example, the device 1900 can be provided as a server or a terminal device. Refer to Figure 12, Device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by a memory 1932 for storing instructions executable by the processing component 1922, such as application programs. The application programs stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above-described method.

[0178] Device 1900 may also include a power component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input / output interface 1958 (I / O interface). Device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server TM , MacOS X TM , Unix TM , Linux TM , FreeBSD TM or the like.

[0179] In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided, such as the memory 1932 including computer program instructions, and the computer program instructions can be executed by the processing component 1922 of the device 1900 to complete the above-described method.

[0180] A computer-readable storage medium can be a tangible device that can retain and store programs / instructions used by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punched card or raised structures in grooves storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage medium used herein is not construed as an instantaneous signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through an optical fiber cable), or electrical signals transmitted through wires.

[0181] The computer programs (or computer-readable program instructions) described herein can be downloaded to various computing / processing devices from a computer-readable storage medium or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0182] The computer program (or computer program instructions) for performing the operations of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer-readable program instructions can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of the computer-readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present disclosure.

[0183] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0184] These computer-readable program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to produce a machine such that the instructions, when executed by the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more boxes of the flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that causes a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises a manufacture, including instructions that implement various aspects of the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0185] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other devices implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0186] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of code, or a portion of an instruction, and the module, segment of code, or portion of an instruction may include one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the boxes may occur out of the order noted in the figures. For example, two consecutive blocks may, in fact, be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions.

[0187] The embodiments of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the market, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A building floor plan optimization method based on graph axis encoding, characterized in that The method includes: Determining initial planar topology data and multi - constraint condition data corresponding to an initial building floor plan, where the initial planar topology data is obtained by segmenting and encoding the initial building floor plan based on graph axes, and the multi - constraint condition data is associated with the graph axes and represents restriction information related to the initial building floor plan; Optimizing the initial planar topology data based on the multi - constraint condition data to obtain target planar topology data; Obtaining a target building floor plan based on the target planar topology data.

2. The method according to claim 1, wherein The initial planar topology data includes a graph axis sequence, and the graph axis sequence is used to indicate the position information of graph axes in at least two preset directions, where the at least two directions include horizontal and vertical directions, and each direction includes at least two graph axes.

3. The method according to claim 2, wherein The initial planar topology data further includes a function matrix and a boundary matrix. The determining of the initial planar topology data and multi - constraint condition data corresponding to the initial building floor plan includes: Dividing the initial building floor plan into multiple cells based on the graph axes in the at least two directions; Determining the function matrix and the boundary matrix based on the multiple cells; Wherein, the function matrix is used to indicate the function information of each cell, and the boundary matrix is used to indicate the boundary information of each cell in the at least two directions.

4. The method according to claim 3, wherein The function information represents that the cell is any one or more of the outside world, living room, dining room, kitchen, bathroom, master bedroom, secondary bedroom, balcony, open area, master bathroom, storage room, load - bearing structure, custom function type; The boundary information is used to represent that the associated cell boundary is any one or more of a completely open connection, an invisible partition, an openable and closable passage connection, an exterior wall, a custom boundary type.

5. The method according to claim 1, characterized in that The determining of the initial planar topology data and multi - constraint condition data corresponding to the initial building floor plan includes: Based on objective restriction information and / or quantifiable user demand information, using the index identifier of the graph axis and the position in a preset coordinate system to represent the multi - constraint condition data; Wherein, the objective restriction information includes any one or more of load - bearing wall position information, exterior window position information, ventilation duct position information, drainage facility pipeline position information; the user demand information includes any one or more of demand information related to the number and size of rooms, the expected wall transformation ratio of the user, other user - defined restriction information.

6. The method according to claim 1, characterized in that The optimizing of the initial planar topology data based on the multi - constraint condition data to obtain target planar topology data includes: Under the constraint of the multi - constraint condition data, performing mutation and crossover operations on the initial planar topology data to obtain multiple updated planar topology data, and the mutation operation and the crossover operation include operations on any one or more of the graph axis sequence, the function matrix, and the boundary matrix; Calculating the fitness function values corresponding to the multiple updated planar topology data respectively; Optimizing the initial planar topology data based on the fitness function values respectively corresponding to the multiple updated planar topology data to obtain target planar topology data.

7. The method according to claim 6, characterized in that, The fitness function value is determined based on any one or more of the scale evaluation results of each room in the planar topological data, the shape evaluation results of each room, the openness evaluation result of the building floor plan corresponding to the planar topological data, and the inspection results of the multi-constraint condition data.

8. The method according to claim 1, wherein The method further includes: Based on the initial planar topological data and / or the multi-constraint condition data corresponding to the initial building floor plan, matching the initial building floor plan with the building case floor plans in the preset dataset to obtain one or more matching floor plans; Using the one or more matching floor plans as the initial building floor plan, and using the planar topological data of the matching floor plan as the initial planar topological data.

9. An architectural floor plan optimization device based on graph axis encoding, characterized in that, The device includes: A first determination module, configured to determine the initial planar topological data and the multi-constraint condition data corresponding to the initial building floor plan, where the initial planar topological data is obtained by segmenting and encoding the initial building floor plan based on the graph axis, and the multi-constraint condition data is associated with the graph axis and represents the restriction information related to the initial building floor plan; An optimization module, configured to optimize the initial planar topological data based on the multi-constraint condition data to obtain the target planar topological data; A second determination module, configured to obtain the target building floor plan based on the target planar topological data.

10. An architectural floor plan optimization device based on graph axis encoding, comprising a memory, a processor, and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.

11. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program, or a non-volatile computer-readable storage medium carrying the computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 8.

Images