CN111383303A - Method and device for automatically generating plane of residential building - Google Patents
Method and device for automatically generating plane of residential building Download PDFInfo
- Publication number
- CN111383303A CN111383303A CN202010170033.6A CN202010170033A CN111383303A CN 111383303 A CN111383303 A CN 111383303A CN 202010170033 A CN202010170033 A CN 202010170033A CN 111383303 A CN111383303 A CN 111383303A
- Authority
- CN
- China
- Prior art keywords
- residential building
- area
- plane
- house type
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012549 training Methods 0.000 claims abstract description 69
- 238000013210 evaluation model Methods 0.000 claims description 41
- 238000012545 processing Methods 0.000 claims description 19
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 9
- 238000009499 grossing Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 26
- 238000013473 artificial intelligence Methods 0.000 description 22
- 230000006870 function Effects 0.000 description 21
- 238000013461 design Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 7
- 230000004048 modification Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000009119 Giant Axonal Neuropathy Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000011960 computer-aided design Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 201000003382 giant axonal neuropathy 1 Diseases 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for automatically generating a residential building plane, wherein the method comprises the following steps: acquiring standard plane graphs of residential buildings in each regional range, and analyzing to obtain residential area, house type layout, house type outline and house structure size information corresponding to each standard plane graph as original training data; training the original training data in combination with the area range where the original training data is located to obtain a residential building plane confrontation generation network model; receiving a target area, a target house type outline and a target house type layout of a target residential building, and generating a planar house type model with a functional area according to a countermeasure generation network model; denoising and regularizing the planar house type model to obtain the residential building plane in the geometric figure meaning. The invention provides a scheme for automatically generating the plane of the residential building with high efficiency and high accuracy.
Description
Technical Field
The invention relates to the technical field of residential building plane generation, in particular to a method and a device for automatically generating a residential building plane.
Background
Residential buildings are increasingly concerned and paid more attention as important places for people to live, and people want to improve the level and convenience of living residences. With the development of the real estate industry, more and more residential buildings are built, and the demand for residential house type design is larger and larger. The requirements of each user on the house type design are different, and how to meet the house building design with different requirements of each user is very important.
At present, a residential building plane is generated by manually drawing by a designer, such as AutoCAD (automatic cad) provided by AutoDesk, using a cad (computer aided design) tool, and the whole process is purely manually drawn, designed and formed. The main disadvantages of using traditional CAD design are slow speed, almost all manual participation in the whole process, and the quality and speed of generation greatly depend on the experience and business level of the participators, and the residential design drawings cannot be produced in batches.
Another disadvantage is that the error rate is high, different mistakes may be made for different persons, and even for the same person, different mistakes may be made under different conditions, such as when multiple items are made simultaneously, or when the physical and mental conditions are poor. A further disadvantage is that the cost of correction is high, and for a person a modification often causes a large number of associated modifications, the time cost is high, and the chance of error is also high, let alone the case where a large number of modifications are required.
Therefore, how to provide a reasonable, efficient, accurate and mass residential building plane generation scheme is a technical problem to be urgently solved by those skilled in the art.
Disclosure of Invention
The invention provides a method and a device for automatically generating a residential building plane, which aim to solve the problem that no reasonable, efficient, accurate and batched residential building plane generation scheme exists in the prior art.
The invention provides a method for automatically generating a residential building plane, which comprises the following steps:
acquiring standard plane graphs of residential buildings in each regional range, and analyzing to obtain residential area, house type layout, house type outline and residential structure size information corresponding to each standard plane graph as original training data;
training the original training data in combination with the area range where the original training data is located to obtain a residential building plane confrontation generation network model;
receiving a target area, a target house type outline and a target house type layout of a target residential building, and generating a planar house type model with a functional area according to the confrontation generation network model;
and denoising and regularizing the planar house type model to obtain a residential building plane in the geometric figure meaning.
Optionally, wherein the method further comprises:
acquiring a preset residential building plane evaluation model;
and evaluating the residential building plane according to the evaluation model to obtain the residential building plane and outputting the residential building plane when the adjacent functional areas are consistent with the adjacent relation of the standard functional areas, and/or the areas of the functional areas are within the area range of the corresponding standard functional areas, and/or all the required functional areas are available.
Optionally, wherein the method further comprises:
acquiring a functional area adjacent relation in a standard plan of the residential building, and training the functional area adjacent relation with a corresponding area range where the residential building is located and a corresponding house type layout to obtain a functional area adjacent relation AI evaluation model;
and acquiring the area of the functional area in the standard plane graph of the residential building, and training the area range of the residential building and the corresponding house type layout to obtain a standard functional area AI evaluation model.
Optionally, the denoising and regularizing processing is performed on the planar house type model to obtain a residential building plane in the geometric figure sense, and the method includes:
denoising and regularizing the planar house type model, removing abnormal patterns according to a region smoothing and region attaching method, and adjusting and aligning region angles;
and optimizing the denoised and normalized planar house type model according to a preset functional area adjacent processing strategy to obtain a residential building plane in the geometric graphic meaning.
Optionally, wherein the method further comprises:
acquiring the area of a specific function area in a standard plan of the residential building, and training the area of the specific function area with the area range where the corresponding residential building is located and the corresponding house type layout to obtain an AI evaluation model of the specific function area;
and according to the AI evaluation model, when the area of the specific functional area in the residential building plane is evaluated to be minimum/maximum, confirming the residential building plane and outputting.
In another aspect, the present invention provides an apparatus for automatically generating a residential building plane, comprising: the system comprises a training data acquisition module, a model training module and a residential building plane generation module; wherein,
the training data acquisition module is connected with the model training module, acquires standard plane graphs of residential buildings in each region range, analyzes and obtains residential area, house type layout, house type outline and house structure size information corresponding to each standard plane graph and takes the residential area, the house type layout, the house type outline and the house structure size information as original training data;
the model training module is connected with the training data acquisition module and the residential building plane generation module, and trains the original training data in combination with the area range where the original training data is located to obtain a residential building plane confrontation generation network model;
the residential building plane generation module is connected with the model training module, receives a target area, a target house type outline and a target house type layout of a target residential building, and generates a plane house type model with a functional area according to the confrontation generation network model; and denoising and regularizing the planar house type model to obtain a residential building plane in the geometric figure meaning.
Optionally, wherein the apparatus further comprises: the residential building plane evaluation module is connected with the residential building plane generation module and used for acquiring a preset residential building plane evaluation model;
and evaluating the residential building plane according to the evaluation model to obtain the residential building plane and outputting the residential building plane when the adjacent functional areas are consistent with the adjacent relation of the standard functional areas, and/or the areas of the functional areas are within the area range of the corresponding standard functional areas, and/or all the required functional areas are available.
Optionally, wherein the apparatus further comprises: the residential building plane evaluation model training module is connected with the residential building plane evaluation module, obtains the functional area adjacency relation in a standard plane graph of the residential building, and trains the corresponding residential building layout and the area range where the corresponding residential building is located to obtain a functional area adjacency relation AI evaluation model;
and acquiring the area of the functional area in the standard plane graph of the residential building, and training the area range of the residential building and the corresponding house type layout to obtain a standard functional area AI evaluation model.
Optionally, wherein the residential building plane generation module comprises: a planar house type model generation unit and an optimization processing unit; wherein,
the planar house type model generation unit is connected with the model training module and the optimization processing unit, receives a target area, a target house type outline and a target house type layout of a target residential building, and generates a planar house type model with a functional area according to the confrontation generation network model;
the optimization processing unit is connected with the planar house type model generating unit, carries out denoising and regularizing processing on the planar house type model, removes malformed graphs according to a region smoothing and region attaching method, and adjusts and aligns region angles;
and optimizing the denoised and normalized planar house type model according to a preset functional area adjacent processing strategy to obtain a residential building plane in the geometric graphic meaning.
Optionally, wherein the apparatus further comprises: the specific function area evaluation module is connected with the residential building plane generation module, obtains the specific function area in the standard plane graph of the residential building, and trains the specific function area with the area range where the corresponding residential building is located and the corresponding house type layout to obtain a specific function area AI evaluation model;
and according to the AI evaluation model, when the area of the specific functional area in the residential building plane is evaluated to be minimum/maximum, confirming the residential building plane and outputting.
The method and the device for automatically generating the residential building plane adopt the traditional graphic algorithm and a deep learning method to automatically generate the residential building plane which can be used by users. The input is the area range of the building plane, the outer contour of the house type, several halls of a single house type and the number of the house of the whole building type plane. The plan is output to meet the requirements of the user, and the user can perform deep processing on the basis of the generated result and then download the plan in a standard CAD format for use. Compared with the prior art, the algorithm can be operated at the cloud end, does not depend on a fixed platform, and is convenient and efficient. Meanwhile, based on a pure algorithm model, a large number of compliant residential building plan graphs meeting the user input standard can be generated within a few seconds, and the design time is greatly shortened. And thirdly, the algorithm of the scheme is not mistaken and is not tired, so the generation quality and efficiency are very high. The following effects can be achieved: the speed is greatly improved (the design overhead is reduced by more than 95%); cost reduction (more than 70% reduction in labor cost); no error exists, and the accuracy is stronger; the local standard is met to the maximum extent; diversity, finding better solutions that one does not think of.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a flow diagram of a method for automatically generating a floor for a residential building in an embodiment of the present invention;
FIG. 2 is a schematic diagram of a standard floor plan for automatically generating a floor for a residential building in an embodiment of the present invention;
FIG. 3 is a schematic diagram of an editable house type generated by automatically generating a layout of several halls and several selected areas of a residential building plane according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of different house types spliced into a building type for automatically generating a residential building plane according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a final adjusted floor profile for automatically generating a floor plan for a residential building in an embodiment of the present invention;
FIG. 6 is a labeled training data residential building plan view as shown in an embodiment of the present invention;
FIG. 7 is a plan view of a home automatically generated by a counter-productive network in accordance with an embodiment of the present invention;
FIG. 8 is a schematic flow chart diagram of a second method of automatically generating a residential building plan in an embodiment of the present invention;
FIG. 9 is a schematic flow chart diagram of a third method for automatically generating a floor plan for a residential building in an embodiment of the present invention;
FIG. 10 is a schematic flow chart diagram illustrating a fourth method for automatically generating a floor plan for a residential building in an embodiment of the present invention;
FIG. 11 is a schematic flow chart diagram of a fifth method for automatically generating a floor plan for a residential building in an embodiment of the present invention;
FIG. 12 is a schematic diagram of an apparatus for automatically generating a floor for a residential building in an embodiment of the present invention;
FIG. 13 is a schematic diagram of a second apparatus for automatically generating a floor plan for a residential building in an embodiment of the present invention;
FIG. 14 is a schematic diagram of a third apparatus for automatically generating a floor plan for a residential building in an embodiment of the present invention;
FIG. 15 is a schematic diagram of a fourth apparatus for automatically generating a floor for a residential building in an embodiment of the present invention;
fig. 16 is a schematic structural diagram of a fifth apparatus for automatically generating a residential building plan according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the method for automatically generating the plane of the residential building in the embodiment, hundreds of thousands of standard plane graphs are obtained after the training model learns, the generated result conforms to the standard specification while ensuring the diversity, different results are generated according to different city specifications, and the standard plane graph pattern comprises functional attributes and length and width dimensions. As shown in fig. 1 to 5, fig. 1 is a flow chart illustrating a method for automatically generating a residential building plane according to the present embodiment; FIG. 2 is a schematic diagram of a standard floor pattern for automatically generating a floor for a residential building according to the present embodiment; FIG. 3 is a schematic diagram of an editable house type generated by automatically generating a layout of several halls and several selected areas of a residential building plane according to the embodiment; FIG. 4 is a schematic diagram of the automatic generation of the residential building planes according to the present embodiment, wherein different house types are spliced into a building type; fig. 5 is a schematic diagram of a final adjusted floor pattern for automatically generating a residential building plan in this embodiment. Specifically, the method comprises the following steps:
And 102, training the original training data by combining the area range where the original training data is located to obtain a residential building plane confrontation generation network model.
103, receiving a target area, a target house type outline and a target house type layout of a target residential building, and generating a planar house type model with a functional area according to the confrontation generation network model; denoising and regularizing the planar house type model to obtain the residential building plane in the geometric figure meaning.
The method for automatically generating the plane of the residential building based on the implementation is simple to modify the parameters for any modification, and then the modified result can be obtained immediately. The method can be used in the cloud, firstly, hundreds of thousands of house type graphs of China in the last 10 years are collected in a data set, a large amount of original training data exist from 1 house to 5 houses, and then functional area labeling is carried out on the training data. The marked data are used for automatically generating different house types by artificial intelligence engineers by utilizing deep learning technology, mainly countermeasure generation network technology. Fig. 6 is a labeled training data residential building plan, and fig. 7 is a plan of a house type automatically generated by the countermeasure generation network.
For the trained confrontation generation network model, the user needs to input:
a. a house type area; b. a house-type outer contour; c. the layout of several houses and several halls. The model automatically generates a flat house type model with functional areas. However, there is a certain noise in the model, and then a post-processing graphics algorithm (please specify the content of the graphics algorithm, which can be exemplified) is used to perform denoising and regularization on the previously generated polygon model (what is the specific strategy of denoising and regularization. The graphic algorithm in charge of post-processing mainly comprises a region smoothing and b clinging regions. Denoising and regularizing are to remove some malformed patterns generated by the GANs, and angle-adjust and align the regions.
Then, the evaluation model is used to evaluate whether the generated result meets the specification requirements, and if not, the result is eliminated (a plurality of different AI models are set in advance to generate a plurality of different results). If so, further windows and doors are generated, and the results of the algorithm portion are generated to the user. The evaluation model here mainly evaluates the following points: a. whether adjacent functional areas are reasonable; b. whether the area of a certain functional area is reasonable or not; c. whether the area of the corridor reaches the minimum available; d. whether all required functions are generated.
In some alternative embodiments, as shown in fig. 8, a flow chart of a second method for automatically generating a residential building plane in this embodiment is different from that in fig. 1, and further includes:
And step 202, evaluating the residential building plane according to the evaluation model to obtain the residential building plane and outputting the residential building plane when the adjacent functional areas are consistent with the adjacent relation of the standard functional areas, and/or the areas of the functional areas are within the area range of the corresponding standard functional areas, and/or all the required functional areas are available.
In some optional embodiments, as shown in fig. 9, a flowchart of a third method for automatically generating a residential building plane in this embodiment is different from that in fig. 8, further including:
And step 302, acquiring the area of the functional area in the standard plan of the residential building, and training the area range of the corresponding residential building and the corresponding house type layout to obtain a standard functional area AI evaluation model.
In some optional embodiments, as shown in fig. 10, which is a schematic flow chart of a fourth method for automatically generating a residential building plane in this embodiment, different from fig. 1, the denoising and regularizing process is performed on a planar house type model to obtain a residential building plane in a geometric sense, and the method includes:
And step 402, optimizing the denoised and normalized planar house type model according to a preset functional area adjacent processing strategy to obtain a residential building plane in the geometric sense.
In some optional embodiments, as shown in fig. 11, a flow chart of a fifth method for automatically generating a residential building plane in the present embodiment further includes, different from that in fig. 1:
and 501, acquiring the area of a specific function area in a standard plan of the residential building, and training the area of the specific function area with the area range where the corresponding residential building is located and the corresponding house type layout to obtain an AI evaluation model of the specific function area.
And 502, according to the AI evaluation model of the area of the specific function area, when the area of the specific function area in the residential building plane is evaluated to be minimum/maximum, confirming the residential building plane and outputting.
In some alternative embodiments, as shown in fig. 12, there is a schematic structural diagram of an apparatus for automatically generating a residential building plane in this embodiment, and the apparatus can be used to implement the above method for automatically generating a residential building plane. Specifically, the apparatus includes: a training data acquisition module 601, a model training module 602, and a residential building plane generation module 603.
The training data obtaining module 601 is connected to the model training module 602, obtains standard plane maps of residential buildings in each area range, and obtains residential area, house layout, house outline and house structure size information corresponding to each standard plane map through analysis as original training data.
And the model training module 602 is connected with the training data acquisition module 601 and the residential building plane generation module 603, and trains the original training data in combination with the area range where the original training data is located to obtain the residential building plane confrontation generation network model.
The residential building plane generation module 603 is connected with the model training module 602, receives a target area, a target house type outline and a target house type layout of a target residential building, and generates a plane house type model with a functional area according to the confrontation generation network model; denoising and regularizing the planar house type model to obtain the residential building plane in the geometric figure meaning.
In some alternative embodiments, as shown in fig. 13, a schematic structural diagram of the second apparatus for automatically generating a residential building plane in this embodiment, different from that in fig. 12, further includes: the residential building plane evaluation module 701 is connected with the residential building plane generation module 603 to obtain a preset residential building plane evaluation model; and evaluating the residential building plane according to the evaluation model to obtain the residential building plane and outputting the residential building plane when the adjacent functional areas are consistent with the adjacent relation of the standard functional areas, and/or the areas of the functional areas are within the area range of the corresponding standard functional areas, and/or all the required functional areas are available.
In some alternative embodiments, as shown in fig. 14, a schematic structural diagram of an apparatus for automatically generating a residential building plane for the third kind of the present embodiment, different from that in fig. 13, further includes: the residential building plane evaluation model training module 801 is connected with the residential building plane evaluation module 701 to obtain the functional area adjacency relationship in the standard plane diagram of the residential building, and train with the area range where the corresponding residential building is located and the corresponding house type layout to obtain the functional area adjacency relationship AI evaluation model.
And acquiring the area of the functional area in the standard plane graph of the residential building, and training the area range of the residential building and the corresponding house type layout to obtain a standard functional area AI evaluation model.
In some alternative embodiments, as shown in fig. 15, which is a schematic structural diagram of a fourth apparatus for automatically generating a residential building plane in this embodiment, different from fig. 12, the residential building plane generating module 603 includes: a planar house type model generation unit 901 and an optimization processing unit 902; wherein,
and a planar house type model generation unit 901, connected to the model training module 602 and the optimization processing unit 902, for receiving the target area, the target house type outline and the target house type layout of the target residential building, and generating a planar house type model with a functional area according to the countermeasure generation network model.
And the optimization processing unit 902 is connected to the planar house type model generating unit 901, and performs denoising and regularization on the planar house type model, removes a deformed pattern according to a region smoothing and region fitting method, and adjusts and aligns a region angle. And optimizing the denoised and normalized planar house type model according to a preset functional area adjacent processing strategy to obtain a residential building plane in the geometric sense.
In some alternative embodiments, as shown in fig. 16, a schematic structural diagram of a fifth apparatus for automatically generating a residential building plane in this embodiment, different from that in fig. 12, further includes: the specific function area evaluation module 1001 is connected to the residential building plane generation module 603, and obtains a specific function area in the standard plane map of the residential building, and trains the specific function area with the area range where the corresponding residential building is located and the corresponding house layout to obtain a specific function area AI evaluation model.
And according to the specific function area AI evaluation model, when the specific function area in the residential building plane is evaluated to be minimum/maximum, confirming the residential building plane and outputting.
Artificial Intelligence (AI), abbreviated in english, makes a computer simulate some thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.) of a human, and mainly comprises a principle that the computer realizes Intelligence, and a computer similar to human brain Intelligence is manufactured, so that the computer can realize higher-level application. The method integrates multiple advanced technologies such as artificial intelligence, big data and intelligent display, and is a simple and easy-to-use tool for automatically generating the residential building plane, so that a designer can be helped to easily finish the automatic generation of the residential building plane under various conditions, and real-time feedback can be modified in real time, so what you see is what you get. After the user obtains the result, the user can modify the residential building parameters at will, and the automatic generation result of the residential building plane is updated in real time, so that the modification of the residential building parameters and the return of the new residential building plane result are not a repeated interactive process any more, and the user can obtain the latest result immediately after modification.
In this embodiment, a computer device may also be included, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method of automatically generating a residential building plane as described above when executing the computer program.
A readable storage medium, storing a computer program, wherein the computer program, when executed by a processor, performs the steps of automatically generating a residential building plan as described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A method of automatically generating a residential building plane, comprising:
acquiring standard plane graphs of residential buildings in each regional range, and analyzing to obtain residential area, house type layout, house type outline and residential structure size information corresponding to each standard plane graph as original training data;
training the original training data in combination with the area range where the original training data is located to obtain a residential building plane confrontation generation network model;
receiving a target area, a target house type outline and a target house type layout of a target residential building, and generating a planar house type model with a functional area according to the confrontation generation network model;
and denoising and regularizing the planar house type model to obtain a residential building plane in the geometric figure meaning.
2. The method of automatically generating a residential building plane as claimed in claim 1, further comprising:
acquiring a preset residential building plane evaluation model;
and evaluating the residential building plane according to the evaluation model to obtain the residential building plane and outputting the residential building plane when the adjacent functional areas are consistent with the adjacent relation of the standard functional areas, and/or the areas of the functional areas are within the area range of the corresponding standard functional areas, and/or all the required functional areas are available.
3. The method of automatically generating a residential building plane as claimed in claim 2, further comprising:
acquiring a functional area adjacent relation in a standard plan of the residential building, and training the functional area adjacent relation with a corresponding area range where the residential building is located and a corresponding house type layout to obtain a functional area adjacent relation AI evaluation model;
and acquiring the area of the functional area in the standard plane graph of the residential building, and training the area range of the residential building and the corresponding house type layout to obtain a standard functional area AI evaluation model.
4. The method of automatically generating residential building planes as claimed in claim 1, wherein denoising and regularizing the planar house type model to obtain the residential building plane in the geometric sense is:
denoising and regularizing the planar house type model, removing abnormal patterns according to a region smoothing and region attaching method, and adjusting and aligning region angles;
and optimizing the denoised and normalized planar house type model according to a preset functional area adjacent processing strategy to obtain a residential building plane in the geometric graphic meaning.
5. The method of automatically generating a residential building plane according to any one of claims 1 to 4, further comprising:
acquiring the area of a specific function area in a standard plan of the residential building, and training the area of the specific function area with the area range where the corresponding residential building is located and the corresponding house type layout to obtain an AI evaluation model of the specific function area;
and according to the AI evaluation model, when the area of the specific functional area in the residential building plane is evaluated to be minimum/maximum, confirming the residential building plane and outputting.
6. An apparatus for automatically generating a residential building plan, comprising: the system comprises a training data acquisition module, a model training module and a residential building plane generation module; wherein,
the training data acquisition module is connected with the model training module, acquires standard plane graphs of residential buildings in each region range, analyzes and obtains residential area, house type layout, house type outline and house structure size information corresponding to each standard plane graph and takes the residential area, the house type layout, the house type outline and the house structure size information as original training data;
the model training module is connected with the training data acquisition module and the residential building plane generation module, and trains the original training data in combination with the area range where the original training data is located to obtain a residential building plane confrontation generation network model;
the residential building plane generation module is connected with the model training module, receives a target area, a target house type outline and a target house type layout of a target residential building, and generates a plane house type model with a functional area according to the confrontation generation network model; and denoising and regularizing the planar house type model to obtain a residential building plane in the geometric figure meaning.
7. The apparatus for automatically generating a residential building plane as recited in claim 6, further comprising: the residential building plane evaluation module is connected with the residential building plane generation module and used for acquiring a preset residential building plane evaluation model;
and evaluating the residential building plane according to the evaluation model to obtain the residential building plane and outputting the residential building plane when the adjacent functional areas are consistent with the adjacent relation of the standard functional areas, and/or the areas of the functional areas are within the area range of the corresponding standard functional areas, and/or all the required functional areas are available.
8. The apparatus for automatically generating a residential building plane as recited in claim 7, further comprising: the residential building plane evaluation model training module is connected with the residential building plane evaluation module, obtains the functional area adjacency relation in a standard plane graph of the residential building, and trains the corresponding residential building layout and the area range where the corresponding residential building is located to obtain a functional area adjacency relation AI evaluation model;
and acquiring the area of the functional area in the standard plane graph of the residential building, and training the area range of the residential building and the corresponding house type layout to obtain a standard functional area AI evaluation model.
9. The apparatus for automatically generating a residential building plane as claimed in claim 6, wherein said residential building plane generation module comprises: a planar house type model generation unit and an optimization processing unit; wherein,
the planar house type model generation unit is connected with the model training module and the optimization processing unit, receives a target area, a target house type outline and a target house type layout of a target residential building, and generates a planar house type model with a functional area according to the confrontation generation network model;
the optimization processing unit is connected with the planar house type model generating unit, carries out denoising and regularizing processing on the planar house type model, removes malformed graphs according to a region smoothing and region attaching method, and adjusts and aligns region angles;
and optimizing the denoised and normalized planar house type model according to a preset functional area adjacent processing strategy to obtain a residential building plane in the geometric graphic meaning.
10. An apparatus for automatically generating a residential building plane according to any one of claims 6 to 9, further comprising: the specific function area evaluation module is connected with the residential building plane generation module, obtains the specific function area in the standard plane graph of the residential building, and trains the specific function area with the area range where the corresponding residential building is located and the corresponding house type layout to obtain a specific function area AI evaluation model;
and according to the AI evaluation model, when the area of the specific functional area in the residential building plane is evaluated to be minimum/maximum, confirming the residential building plane and outputting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010170033.6A CN111383303A (en) | 2020-03-12 | 2020-03-12 | Method and device for automatically generating plane of residential building |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010170033.6A CN111383303A (en) | 2020-03-12 | 2020-03-12 | Method and device for automatically generating plane of residential building |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111383303A true CN111383303A (en) | 2020-07-07 |
Family
ID=71221508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010170033.6A Pending CN111383303A (en) | 2020-03-12 | 2020-03-12 | Method and device for automatically generating plane of residential building |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111383303A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112733246A (en) * | 2021-01-22 | 2021-04-30 | 上海建工四建集团有限公司 | Automatic building design method, device, terminal, storage medium and processor |
| CN113051642A (en) * | 2021-03-12 | 2021-06-29 | 深圳小库科技有限公司 | Non-residential landscape generation method, device, equipment and storage medium |
| CN113449355A (en) * | 2021-09-01 | 2021-09-28 | 江苏华邦工程造价咨询有限公司 | Building house type graph automatic generation method based on artificial intelligence |
| CN113553652A (en) * | 2021-07-28 | 2021-10-26 | 杭州群核信息技术有限公司 | Building layout generation method, building layout generation device and storage medium |
| CN113886938A (en) * | 2021-12-08 | 2022-01-04 | 深圳小库科技有限公司 | AI-based method for automatically generating indoor toilet and kitchen drainage system |
| CN114065342A (en) * | 2021-11-08 | 2022-02-18 | 深圳须弥云图空间科技有限公司 | Method and device for generating house type outline, storage medium and electronic equipment |
| WO2022047960A1 (en) * | 2020-09-04 | 2022-03-10 | 东南大学 | Artificial intelligence-based building block generation method for commercial district |
| CN114462135A (en) * | 2022-04-13 | 2022-05-10 | 南京赛博迪数字科技有限公司 | Hospital plane graph generation method and device, electronic equipment and storage medium |
| CN114489877A (en) * | 2020-11-13 | 2022-05-13 | 上海帝泰发展有限公司 | Shopping mall floor plane display method and system thereof |
| CN115712943A (en) * | 2022-11-24 | 2023-02-24 | 中国建筑设计研究院有限公司 | Image recognition-based rural residential house type plane generation method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009009598A (en) * | 2008-08-21 | 2009-01-15 | Renesas Technology Corp | Floor plan creation apparatus |
| CN101719174A (en) * | 2009-12-09 | 2010-06-02 | 广州天越电子科技有限公司 | Drawing optimal design generation method for realizing wireless network communication |
| CN106528904A (en) * | 2016-07-09 | 2017-03-22 | 陈志静 | Residential house chart building structure intelligent recognition and functional area automatic planning and designing method |
| CN110633553A (en) * | 2019-10-09 | 2019-12-31 | 郑豪 | Automatic generation method and system for residential house type plane graph |
| CN110795858A (en) * | 2019-11-06 | 2020-02-14 | 广东博智林机器人有限公司 | Method and device for generating home decoration design drawing |
-
2020
- 2020-03-12 CN CN202010170033.6A patent/CN111383303A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009009598A (en) * | 2008-08-21 | 2009-01-15 | Renesas Technology Corp | Floor plan creation apparatus |
| CN101719174A (en) * | 2009-12-09 | 2010-06-02 | 广州天越电子科技有限公司 | Drawing optimal design generation method for realizing wireless network communication |
| CN106528904A (en) * | 2016-07-09 | 2017-03-22 | 陈志静 | Residential house chart building structure intelligent recognition and functional area automatic planning and designing method |
| CN110633553A (en) * | 2019-10-09 | 2019-12-31 | 郑豪 | Automatic generation method and system for residential house type plane graph |
| CN110795858A (en) * | 2019-11-06 | 2020-02-14 | 广东博智林机器人有限公司 | Method and device for generating home decoration design drawing |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022047960A1 (en) * | 2020-09-04 | 2022-03-10 | 东南大学 | Artificial intelligence-based building block generation method for commercial district |
| CN114489877A (en) * | 2020-11-13 | 2022-05-13 | 上海帝泰发展有限公司 | Shopping mall floor plane display method and system thereof |
| CN112733246A (en) * | 2021-01-22 | 2021-04-30 | 上海建工四建集团有限公司 | Automatic building design method, device, terminal, storage medium and processor |
| CN113051642A (en) * | 2021-03-12 | 2021-06-29 | 深圳小库科技有限公司 | Non-residential landscape generation method, device, equipment and storage medium |
| CN113051642B (en) * | 2021-03-12 | 2023-01-06 | 深圳小库科技有限公司 | Non-residential landscape generation method, device, equipment and storage medium |
| CN113553652A (en) * | 2021-07-28 | 2021-10-26 | 杭州群核信息技术有限公司 | Building layout generation method, building layout generation device and storage medium |
| CN113449355A (en) * | 2021-09-01 | 2021-09-28 | 江苏华邦工程造价咨询有限公司 | Building house type graph automatic generation method based on artificial intelligence |
| CN114065342A (en) * | 2021-11-08 | 2022-02-18 | 深圳须弥云图空间科技有限公司 | Method and device for generating house type outline, storage medium and electronic equipment |
| CN113886938B (en) * | 2021-12-08 | 2022-03-08 | 深圳小库科技有限公司 | AI-based method for automatically generating indoor toilet and kitchen drainage system |
| CN113886938A (en) * | 2021-12-08 | 2022-01-04 | 深圳小库科技有限公司 | AI-based method for automatically generating indoor toilet and kitchen drainage system |
| CN114462135A (en) * | 2022-04-13 | 2022-05-10 | 南京赛博迪数字科技有限公司 | Hospital plane graph generation method and device, electronic equipment and storage medium |
| CN115712943A (en) * | 2022-11-24 | 2023-02-24 | 中国建筑设计研究院有限公司 | Image recognition-based rural residential house type plane generation method and system |
| CN115712943B (en) * | 2022-11-24 | 2024-01-30 | 中国建筑设计研究院有限公司 | Image recognition-based rural residential household type plane generation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111383303A (en) | Method and device for automatically generating plane of residential building | |
| US20220108043A1 (en) | Method and device for automatically generating residential building plan | |
| Zhao et al. | Reconstructing BIM from 2D structural drawings for existing buildings | |
| CN112883801B (en) | Accurate identification method for resident distribution box system diagram sub-graph in CAD distribution system diagram | |
| CN103336894B (en) | A kind of city plot ratio automatic Mesh Partition Method | |
| CN114329678B (en) | Intelligent building structure design system and method | |
| CN114840900B (en) | Automatic generation method of derivative BIM (building information modeling) component based on i-GBDT (generic block transformation) technology | |
| CN113449355A (en) | Building house type graph automatic generation method based on artificial intelligence | |
| CN109376941A (en) | Energy simulation and optimization method based on artificial neural network and BIM | |
| CN111598123B (en) | Power distribution network line vectorization method and device based on neural network | |
| CN109801346B (en) | Original painting auxiliary coloring method and device based on neural network | |
| CN115017805A (en) | Method and system for planning optimal path of nuclear retired field based on bidirectional A-x algorithm | |
| CN109800776A (en) | Material mask method, device, terminal and computer readable storage medium | |
| CN116704542A (en) | Layer classification method, device, equipment and storage medium | |
| CN113240219A (en) | Land utilization simulation and prediction method | |
| CN113724383A (en) | Robot topology map generation system, method, computer device and storage medium | |
| Adão et al. | Procedural generation of traversable buildings outlined by arbitrary convex shapes | |
| CN117056722A (en) | Prediction method and system for population quantity of planned land parcel | |
| CN114913305B (en) | Model processing method, device, equipment, storage medium and computer program product | |
| Yue et al. | Artificial intelligence-assisted interior layout design of cad painting | |
| Wang | Application of computer images in virtual simulation technology-apparel as an example | |
| CN114065359A (en) | Decoration design generation method and device, electronic equipment and storage medium | |
| CN113642090A (en) | Building layout generation method and device, computer equipment and storage medium | |
| US20220043952A1 (en) | Computational Platforms and Methods for Enabling CFD Simulation Processes | |
| CN114091560A (en) | Method, device and equipment for planning communication station address and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200707 |
|
| RJ01 | Rejection of invention patent application after publication |