CN110796304A - Building arrangement optimization method and device, electronic equipment and storage medium - Google Patents
Building arrangement optimization method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110796304A CN110796304A CN201911029245.6A CN201911029245A CN110796304A CN 110796304 A CN110796304 A CN 110796304A CN 201911029245 A CN201911029245 A CN 201911029245A CN 110796304 A CN110796304 A CN 110796304A
- Authority
- CN
- China
- Prior art keywords
- building
- model
- arrangement information
- building arrangement
- initial
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012549 training Methods 0.000 claims description 30
- 238000003062 neural network model Methods 0.000 claims description 17
- 230000002787 reinforcement Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 238000013461 design Methods 0.000 abstract description 13
- 238000010276 construction Methods 0.000 abstract description 6
- 230000009471 action Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 14
- 230000006870 function Effects 0.000 description 12
- 230000008901 benefit Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a building arrangement optimization method and device, electronic equipment and a storage medium, and belongs to the technical field of buildings. The method comprises the following steps: acquiring initial building arrangement information; and replanning the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain the building arrangement information meeting the requirements of building spacing and sunshine duration. In the embodiment of the application, when building design demand, acquire initial building information of arranging, then with the building information input who arranges at random to the model that has trained, utilize the model to carry out the repurposing to this building of arranging at random, the output satisfies building interval and the long building of length of sunshine requirement arrange, make constructor can directly be under construction based on the building overall arrangement of model output, design out reasonable building group architectural design, can practice thrift a large amount of manpowers and time cost.
Description
Technical Field
The application belongs to the technical field of buildings, and particularly relates to a building arrangement optimization method and device, electronic equipment and a storage medium.
Background
Along with the rapid development of the domestic industrialization process, in an industrialized city, city construction is rapidly promoted, the urban land is in shortage day by day, the improvement of the volume ratio is an important measure for improving the benefit, the improvement of the volume ratio is usually realized by increasing the number of floors of building houses and shortening the distance between the buildings, so the density of the building groups of high-rise buildings is continuously improved, some building houses can not reach the sunshine duration standard of the building houses specified by the regulation, people can not enjoy the sunshine, and the contradiction caused by the sunshine of the building houses is more and more prominent under the background that the city construction is continuously promoted, the urban land is in shortage, and the urban building is in high-rise.
The two most important factors influencing building arrangement are: the length of the sunlight duration of the buildings and the distance between the buildings are directly related to the house pricing, the two factors are two major factors which are emphasized by developers for pursuing benefit maximization, and the developers must reasonably plan the layout of the buildings for achieving the benefit maximization.
Therefore, the method is very important for the arrangement of the buildings, the arrangement of the buildings is manually planned according to a large number of planning requirements in the domestic building industry at present, a large number of various indexes such as the sunshine duration and the volume rate of the buildings need to be calculated, and a large number of human resources and time are consumed.
Disclosure of Invention
In view of this, an object of the present application is to provide a building layout optimization method, device, electronic device and storage medium, so as to solve the problem that the existing building needs to consume a large amount of human resources and time to obtain a reasonable building layout.
The embodiment of the application is realized as follows:
in a first aspect, an embodiment of the present application provides a building arrangement optimization method, including: acquiring initial building arrangement information; and replanning the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain the building arrangement information meeting the requirements of building spacing and sunshine duration.
In the embodiment of the application, when building design demand, acquire initial building information of arranging, then with the building information input who arranges at random to the model that has trained, utilize the model that has mastered the building law of arranging that satisfies building interval and long requirement of sunshine to plan again this building of arranging at random, the output satisfies building interval and long requirement of sunshine the building arrange, make constructor can directly be under construction based on the building overall arrangement of model output, design reasonable building group architectural design, can practice thrift a large amount of manpowers and time cost.
With reference to a possible implementation manner of the embodiment of the first aspect, replanning the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain building arrangement information meeting the requirements of building spacing and sunshine duration, including: re-planning the building arrangement in the initial building arrangement information through a first optimization model trained in advance to obtain building arrangement information meeting the building spacing requirement; and replanning the building arrangement in the building arrangement information meeting the requirement of the building spacing through a second optimization model trained in advance to obtain the building arrangement information meeting the requirement of the sunshine duration. In the embodiment of the application, the building arrangement information meeting the requirements of the building distance and the sunshine duration is obtained through two optimization models, the building information arranged randomly is input into a first optimization model which is trained well, the building arrangement information meeting the requirements of the building distance is output, on the basis, the information output by the first optimization model is used as the input of a second optimization model, the building arrangement information meeting the requirements of the sunshine duration is output through the second optimization model, and a new optimization mode is further provided.
With reference to a possible implementation manner of the embodiment of the first aspect, when the target optimization model is a neural network model, the trained target optimization model is obtained through training in the following steps: acquiring building arrangement data meeting the requirements of building spacing and sunshine duration; and training an initial neural network model by using the building arrangement data to obtain the trained target optimization model. In the embodiment of the application, when the target optimization model is the neural network model, the building arrangement data meeting the requirements of the building distance and the sunshine duration is acquired and used as the training data to train the building arrangement data, so that the building arrangement rule meeting the requirements of the building distance and the sunshine duration is learned, and the target optimization model can be used later.
With reference to a possible implementation manner of the embodiment of the first aspect, the initial building arrangement information is obtained through the following steps: randomly arranging a plurality of buildings on a blank land block, and inputting parameters of each building to obtain the initial building arrangement information, wherein the parameters comprise: the coordinates of the land where the building is located, the height and the width of the top view of the building, the height of the building and the rotation angle of the building. In the embodiment of the application, a blank land block is established on simulation software, a plurality of buildings are randomly arranged on the blank land block, parameters of each building are input, initial building arrangement information can be obtained, the operation is very convenient, and the buildings are randomly generated, so that the buildings do not need to meet special requirements, and the applicability is better.
With reference to one possible implementation manner of the embodiment of the first aspect, the objective optimization model is a reinforcement learning model. In the embodiment of the application, the building arrangement meeting the requirements of building distance and sunshine duration is obtained by adopting the reinforcement learning model trained in advance, and the training data is not needed for training the reinforcement learning model, so that the cost for acquiring the training data for training the model can be saved.
In a second aspect, an embodiment of the present application further provides a building arrangement optimization device, including: an acquisition module and a planning module; the acquisition module is used for acquiring initial building arrangement information; and the planning module is used for replanning the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain the building arrangement information meeting the requirements of the building spacing and the sunshine duration.
With reference to a possible implementation manner of the embodiment of the second aspect, the planning module is further configured to: re-planning the building arrangement in the initial building arrangement information through a first optimization model trained in advance to obtain building arrangement information meeting the building spacing requirement; and replanning the building arrangement in the building arrangement information meeting the requirement of the building spacing through a second optimization model trained in advance to obtain the building arrangement information meeting the requirement of the sunshine duration.
With reference to a possible implementation manner of the embodiment of the second aspect, the initial building arrangement information is obtained by the following steps: randomly arranging a plurality of buildings on a blank land block, and inputting parameters of each building to obtain the initial building arrangement information, wherein the parameters comprise: the coordinates of the land where the building is located, the height and the width of the top view of the building, the height of the building and the rotation angle of the building.
With reference to a possible implementation manner of the embodiment of the second aspect, when the target optimization model is a neural network model, the obtaining module is further configured to obtain building arrangement data meeting requirements on building spacing and sunshine duration; correspondingly, the device further comprises a training module which is used for training the initial neural network model without using the building configuration data to obtain the trained target optimization model.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a memory and a processor, the memory and the processor connected; the memory is used for storing programs; the processor is configured to invoke a program stored in the memory to perform the method according to the first aspect embodiment and/or any possible implementation manner of the first aspect embodiment.
In a fourth aspect, this application further provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the method provided in the foregoing first aspect and/or any possible implementation manner of the first aspect.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts. The foregoing and other objects, features and advantages of the application will be apparent from the accompanying drawings. Like reference numerals refer to like parts throughout the drawings. The drawings are not intended to be to scale as practical, emphasis instead being placed upon illustrating the subject matter of the present application.
Fig. 1 shows a training schematic diagram of a reinforcement learning model provided in an embodiment of the present application.
Fig. 2 shows a schematic flow chart of a building arrangement optimization method provided by the embodiment of the application.
Fig. 3 shows an initial building arrangement diagram of a random arrangement according to an embodiment of the present application.
Fig. 4 is a schematic flow chart illustrating a process for obtaining an optimal building layout based on an RL (Reinforcement Learning) model according to an embodiment of the present application.
Fig. 5 shows a re-planned building arrangement schematic diagram provided in an embodiment of the present application.
Fig. 6 is a schematic flow chart illustrating a process of obtaining an optimal building layout based on an HRL (Hierarchical reinforcement learning) model according to an embodiment of the present disclosure.
Fig. 7 shows a schematic block diagram of a building arrangement optimization device according to an embodiment of the present application.
Fig. 8 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, relational terms such as "first," "second," and the like may be used solely in the description herein to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Further, the term "and/or" in the present application is only one kind of association relationship describing the associated object, and means that three kinds of relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone.
In the building design stage of a building group, the length of the sunshine duration of a building and the distance between the buildings are two factors which have to be considered, reasonable design can fully utilize land space, and the optimal lighting effect is provided, so that how to quickly obtain reasonable building layout is very important.
In the embodiment of the application, through training the model, make its study satisfy building interval and the long building law of arranging of duration requirement of sunshine, then in the building information input that will arrange at random to the model that has trained, utilize the model to carry out the repurposing to this building of arranging at random, the output satisfies building interval and the long building of requirement of duration of sunshine and arranges, make constructor can directly be under construction based on the building overall arrangement of model output, design out reasonable building group architectural design.
As an implementation mode, the building arrangement meeting the requirements of building spacing and sunshine duration can be obtained through one model. For example, a neural network model trained on building arrangement data meeting the requirements of building spacing and sunshine duration is adopted to replan randomly arranged buildings, and the replanned building arrangement meeting the requirements of building spacing and sunshine duration is output. Before this, need obtain the building data of arranging (training data) that satisfy building interval and duration requirement, utilize this building data of arranging (training data), train initial neural network model, obtain the model that trains well.
In this embodiment, in addition to obtaining the building arrangement meeting the requirements of the building spacing and the sunshine duration by using the neural network model trained in advance, the randomly arranged buildings can be replanned by using the Reinforcement Learning (RL) model trained in advance, and the re-planned building arrangement meeting the requirements of the building spacing and the sunshine duration is output. Before this, the RL model needs to be trained in advance, wherein the RL model training process is as shown in fig. 1. Suppose that the building spacing function is F1(X) the solar function is F2(X), then the function f (X) W of the RL model1*F1(X)+W2*F2(X) wherein W1And W2Respectively is an adjustable weight parameter with the value range of [0, 1%]. The Reward (Reward) is defined as:a is an adjustable parameter, and the value thereof is determined according to specific situations, for example, the value can be between 0 and 1 (but not limited to between 0 and 1, and other values are also possible), and S ist+1Indicating the state at the current moment, StIndicating the state at the last time.
In the RL (reinforcement learning) model, an Agent determines the current State and determines the next Action of the Agent. When the requirement of the building spacing is met, the key Action is to move up, down, left and right; when the requirement of sunshine duration is met, the key actions are up, down, left and right movement and angular rotation. When an Agent interacts with the Environment of the Agent after each Action, rewarded at the moment is calculated, the State at the moment is judged, and the next Action of the Agent is determined according to the rewarded and the State, so that continuous circulation (returning to the beginning is a circular process), namely continuous training until convergence. It should be noted that the principles of reinforcement learning are well known to those skilled in the art and will not be described herein too much.
As another embodiment, the building arrangement which meets the requirements of building spacing and sunshine duration can be obtained by two models. Wherein, one model (such as a first model) is used for obtaining the building arrangement meeting the requirement of the building spacing, and the other model (such as a second model) is used for obtaining the building arrangement meeting the requirement of the sunshine duration. For example, the randomly arranged buildings are replanned through a first model trained in advance, the replanned buildings arranged to meet the requirements of the space between the buildings are output, and the output of the first model is used as the input of a second model, so that the buildings arranged to meet the requirements of the sunshine duration are obtained. Before this, the first model and the second model need to be trained separately. For example, when the first model and the second model are both neural network models, building arrangement data (as training data of the first model) meeting the building spacing and building arrangement data (as training data of the second model) meeting the sunshine duration requirement need to be acquired respectively to train the first model and the second model respectively, so as to obtain trained models.
In this embodiment, the first model and the second model may be a Reinforcement Learning (RL) model in addition to the neural network model. For example, a first model (RL1 model) is adopted to replan the randomly arranged buildings, the replanned buildings arranged meeting the requirements of the space between the buildings are output and used as the input of a second model (RL2 model), the buildings arranged meeting the requirements of the sunshine duration after replanning are replanned through the RL2 model, and the replanned buildings arranged meeting the requirements of the sunshine duration are output. Before this, the RL1 model and RL2 model need to be trained separately, wherein the RL1 model and the RL2 model are trained in accordance with the RL model training process described above. For the RL1 model, the function is the building spacing function F1(X), wherein Reward1 (Reward 1) is defined as:
in the RL1 model, Agent1 (Agent 1) determines the next Action1 (Action 1) of Agent1 (Agent 1) by determining the current State1 (State 1), and key Action1 (Action 1) is up, down, left, and right movement. When Agent1 (Agent 1) interacts with Environment1 (Environment 1) after performing Action1 (Action 1) each time, Reward1 (Reward 1) at the moment is calculated, State1 (State 1) at the moment is judged, and then Action1 (Action) 1 of the next step of Agent1 (Agent 1) is determined, so that continuous circulation (returning to the beginning is a circular process), namely continuous training until convergence.
For the RL2 model, the function is the sunshine function F2(X), wherein Reward2 (Reward 2) is defined as:
in the model of RL2, it is shown that,agent2 (Agent 2) determines the next Action2 (Action 2) of Agent2 (Agent 2) by determining the current State2 (State 2), and the key Action2 (Action 2) is up, down, left, right movement and angular rotation. When the Agent2 (Agent 2) interacts with the Environment2 (Environment 2) in which it is located after performing Action2 (Action 2) each time, and calculates Reward2 (Reward 2) and judges State2 (State 2) at this time, and determines the next Action2 (Action 2) of the Agent2 (Agent 2) according to the interaction, the continuous circulation (returning to the beginning is a circulation process), namely continuous training until convergence.
Because the reinforcement learning model does not need training data during training, the reinforcement learning model is adopted to obtain the building arrangement meeting the requirements of building distance and sunshine duration, and the cost for acquiring the training data for training the model can be saved.
Referring to fig. 2, steps included in a building arrangement optimization method provided in an embodiment of the present application will be described with reference to fig. 2.
Step S101: and acquiring initial building arrangement information.
When building design requirements of a building exist, namely the arrangement of the building needs to be optimized, initial building arrangement information is obtained. As an embodiment, the initial building arrangement information is obtained by: a plurality of buildings are randomly arranged on a blank land block, and the parameters of each building are input to obtain initial building arrangement information, wherein the schematic diagram of the initial building arrangement is shown in FIG. 3. Wherein the parameters include: the coordinates of the land where the building is located, the length and the width of the top view of the building, the height of the building and the rotation angle of the building.
A blank land block simulating a real land is created on a visual interface of simulation software, then buildings are randomly arranged on the blank land block, and parameters of each building are input, so that initial building arrangement information (including initial building arrangement pictures and related building parameters) is obtained. The parameters include: the coordinates of the land where the building is located, the height and the width of the top view of the building, the height of the building and the rotation angle of the building. Wherein, the number of the buildings randomly arranged on the blank land is the same as the number of the buildings planned actually.
Wherein the meaning of the individual parameters is as follows: x, y: coordinates of a land block where the building is located; w, h: the width and height of the top view of the building; h: the floor height of the building; θ: the rotation angle of the building can allow the building to rotate a certain angle in order to meet the requirement of sunshine duration.
Step S102: and replanning the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain the building arrangement information meeting the requirements of building spacing and sunshine duration.
After the initial building arrangement information is obtained, re-planning the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain building arrangement information meeting the requirements of the building spacing and the sunshine duration, namely after obtaining randomly arranged building pictures and related parameters, inputting the initial building arrangement information into the pre-trained target optimization model to generate a building arrangement picture meeting the minimum requirements of the building spacing and the sunshine duration, and outputting the updated parameters, wherein a process schematic diagram is shown in fig. 4. The schematic diagram of the building arrangement meeting the minimum requirements of the building distance and the sunshine duration after the re-planning by inputting the randomly arranged building pictures and the related parameters into the target optimization model is shown in fig. 5. It should be noted that, here, only the case where the target optimization model is the RL model is shown, and the target optimization model may be a neural network model in addition to the RL model.
In addition, except the implementation mode that the buildings meeting the requirements of the building distance and the sunshine duration are arranged through one model, the buildings meeting the requirements of the building distance and the sunshine duration can be arranged through two models. At this time, the process (step S102) may be: re-planning the building arrangement in the initial building arrangement information through a first optimization model trained in advance to obtain building arrangement information meeting the building spacing requirement; and replanning the building arrangement in the building arrangement information meeting the requirement of the building spacing through a second optimization model trained in advance to obtain the building arrangement information meeting the requirement of the sunshine duration. After the initial building arrangement information is obtained, the randomly arranged building pictures and related parameters are input into a first optimization model trained in advance to generate a building arrangement picture meeting the minimum requirement of the building distance, updated parameters are output, on the basis, the generated pictures and the parameters are input into a second optimization model trained in advance to generate a building arrangement picture meeting the minimum requirement of the building duration and sunshine, and the updated parameters are output, and a process schematic diagram is shown in fig. 6. It should be noted that, here, only the case where the first optimization model and the second optimization model are both RL models is shown, and in addition, the first optimization model and the second optimization model may be a neural network model in addition to the RL model.
The principle of model training is referred to the above description, which is not described herein again, and the target optimization model may be one or two. The model may be a neural network model or an RL model.
In the embodiment of the application, through training the model, make it study the building law of arranging that satisfies building interval and/or sunshine duration requirement, then input the building information of arranging at random into the model that has trained, utilize the model to carry out the repurposing to the building of arranging at random, the output satisfies building interval and the building of sunshine duration requirement arrange, make constructor can directly be under construction based on the building overall arrangement of model output, design out reasonable building group architectural design. The building arrangement which meets the requirements of the building spacing and the sunshine duration can be obtained based on one model (such as an RL model), and the building arrangement which meets the requirements of the building spacing and the sunshine duration can be obtained based on two models (such as an RL1 model and an RL2 model).
The embodiment of the present application further provides a building arrangement optimization apparatus 100, as shown in fig. 7, the building arrangement optimization apparatus 100 includes: an acquisition module 110 and a planning module 120.
The obtaining module 110 is configured to obtain initial building configuration information. Obtaining the initial building arrangement information through the following steps: randomly arranging a plurality of buildings on a blank land block, and inputting parameters of each building to obtain the initial building arrangement information, wherein the parameters comprise: the coordinates of the land where the building is located, the height and the width of the top view of the building, the height of the building and the rotation angle of the building.
And the planning module 120 is used for replanning the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain the building arrangement information meeting the requirements of the building spacing and the sunshine duration. Optionally, the planning module 120 is further configured to: re-planning the building arrangement in the initial building arrangement information through a first optimization model trained in advance to obtain building arrangement information meeting the building spacing requirement; and replanning the building arrangement in the building arrangement information meeting the requirement of the building spacing through a second optimization model trained in advance to obtain the building arrangement information meeting the requirement of the sunshine duration.
When the target optimization model is a neural network model, the obtaining module 110 is further configured to obtain building arrangement data meeting the requirements of building spacing and sunshine duration; correspondingly, the device further comprises a training module which is used for training the initial neural network model without using the building configuration data to obtain the trained target optimization model.
The building layout optimization apparatus 100 provided in the embodiment of the present application has the same implementation principle and technical effect as those of the foregoing method embodiments, and for brief description, reference may be made to corresponding contents in the foregoing method embodiments for the parts of the embodiment that are not mentioned in the description.
As shown in fig. 8, fig. 8 is a block diagram illustrating a structure of an electronic device 200 according to an embodiment of the present disclosure. The electronic device 200 includes: a transceiver 210, a memory 220, a communication bus 230, and a processor 240.
The elements of the transceiver 210, the memory 220, and the processor 240 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, the components may be electrically coupled to each other via one or more communication buses 230 or signal lines. The transceiver 210 is used for transceiving data. The memory 220 is used for storing a computer program, such as a software functional module shown in fig. 7, i.e., the building arrangement optimizing apparatus 100. The building configuration optimization apparatus 100 includes at least one software function module, which may be stored in the memory 220 in the form of software or firmware (firmware) or solidified in an Operating System (OS) of the electronic device 200. The processor 240 is configured to execute executable modules stored in the memory 220, such as software functional modules or computer programs included in the building layout optimization apparatus 100. For example, the processor 240 is configured to obtain initial building configuration information; and the system is used for replanning the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain the building arrangement information meeting the requirements of building spacing and sunshine duration.
The Memory 220 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The processor 240 may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor 240 may be any conventional processor or the like.
The electronic device 200 includes, but is not limited to, a notebook computer, a desktop computer, a tablet computer, and the like.
The embodiment of the present application further provides a non-volatile computer-readable storage medium (hereinafter, referred to as a storage medium), where the storage medium stores a computer program, and when the computer program is run by the electronic device 200 as described above, the building configuration optimization method shown in the above method embodiment is executed.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a notebook computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A building arrangement optimization method is characterized by comprising the following steps:
acquiring initial building arrangement information;
and replanning the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain the building arrangement information meeting the requirements of building spacing and sunshine duration.
2. The method of claim 1, wherein the re-planning of the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain building arrangement information meeting the requirements of building spacing and sunshine duration comprises:
re-planning the building arrangement in the initial building arrangement information through a first optimization model trained in advance to obtain building arrangement information meeting the building spacing requirement;
and replanning the building arrangement in the building arrangement information meeting the requirement of the building spacing through a second optimization model trained in advance to obtain the building arrangement information meeting the requirement of the sunshine duration.
3. The method of claim 1, wherein when the target optimization model is a neural network model, the trained target optimization model is obtained by training through the following steps:
acquiring building arrangement data meeting the requirements of building spacing and sunshine duration;
and training an initial neural network model by using the building arrangement data to obtain the trained target optimization model.
4. The method of claim 1, wherein the initial building configuration information is obtained by:
randomly arranging a plurality of buildings on a blank land block, and inputting parameters of each building to obtain the initial building arrangement information, wherein the parameters comprise: the coordinates of the land where the building is located, the height and the width of the top view of the building, the height of the building and the rotation angle of the building.
5. The method of claim 1, 2 or 4, wherein the target optimization model is a reinforcement learning model.
6. A building arrangement optimizing device is characterized by comprising:
the acquisition module is used for acquiring initial building arrangement information;
and the planning module is used for replanning the building arrangement in the initial building arrangement information through a pre-trained target optimization model to obtain the building arrangement information meeting the requirements of the building spacing and the sunshine duration.
7. The apparatus of claim 6, wherein the planning module is further configured to:
re-planning the building arrangement in the initial building arrangement information through a first optimization model trained in advance to obtain building arrangement information meeting the building spacing requirement;
and replanning the building arrangement in the building arrangement information meeting the requirement of the building spacing through a second optimization model trained in advance to obtain the building arrangement information meeting the requirement of the sunshine duration.
8. The apparatus of claim 6, wherein the initial building configuration information is obtained by:
randomly arranging a plurality of buildings on a blank land block, and inputting parameters of each building to obtain the initial building arrangement information, wherein the parameters comprise: the coordinates of the land where the building is located, the height and the width of the top view of the building, the height of the building and the rotation angle of the building.
9. An electronic device, comprising: a memory and a processor, the memory and the processor connected;
the memory is used for storing programs;
the processor to invoke a program stored in the memory to perform the method of any of claims 1-4.
10. A storage medium having stored thereon a computer program which, when executed by a processor, performs the method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911029245.6A CN110796304A (en) | 2019-10-25 | 2019-10-25 | Building arrangement optimization method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911029245.6A CN110796304A (en) | 2019-10-25 | 2019-10-25 | Building arrangement optimization method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110796304A true CN110796304A (en) | 2020-02-14 |
Family
ID=69441421
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911029245.6A Pending CN110796304A (en) | 2019-10-25 | 2019-10-25 | Building arrangement optimization method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110796304A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111445059A (en) * | 2020-03-06 | 2020-07-24 | 广东博智林机器人有限公司 | Modeling method and system of land planning preliminary model |
| CN111563290A (en) * | 2020-04-30 | 2020-08-21 | 深圳集智数字科技有限公司 | Building arrangement method and device |
| CN113158312A (en) * | 2021-04-26 | 2021-07-23 | 深圳小库科技有限公司 | Construction plan generation method and device for construction land, storage medium and processor |
| CN114528625A (en) * | 2022-02-17 | 2022-05-24 | 深圳须弥云图空间科技有限公司 | Building spacing calibration method and device |
| CN114547727A (en) * | 2022-01-12 | 2022-05-27 | 万翼科技有限公司 | Building arrangement method and device, electronic equipment and storage medium |
| CN117828705A (en) * | 2024-01-11 | 2024-04-05 | 北京建筑大学 | Residence layout generation design method and system based on genetic algorithm search |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341296A (en) * | 2017-06-19 | 2017-11-10 | 中国建筑第八工程局有限公司 | A kind of high-rise group building daylighting optimized treatment method based on BIM technology |
| CN110347670A (en) * | 2019-07-17 | 2019-10-18 | 广联达科技股份有限公司 | Method, system and the computer readable storage medium of Digital Architecture historical data precipitating |
-
2019
- 2019-10-25 CN CN201911029245.6A patent/CN110796304A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341296A (en) * | 2017-06-19 | 2017-11-10 | 中国建筑第八工程局有限公司 | A kind of high-rise group building daylighting optimized treatment method based on BIM technology |
| CN110347670A (en) * | 2019-07-17 | 2019-10-18 | 广联达科技股份有限公司 | Method, system and the computer readable storage medium of Digital Architecture historical data precipitating |
Non-Patent Citations (2)
| Title |
|---|
| 卢玫等: "住区规划中日照环境优化设计策略探析", 《四川建筑科学研究》, no. 01, 25 February 2013 (2013-02-25) * |
| 潘智敏等: "建筑工程设计与项目管理", 吉林科学技术出版社, pages: 165 - 167 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111445059A (en) * | 2020-03-06 | 2020-07-24 | 广东博智林机器人有限公司 | Modeling method and system of land planning preliminary model |
| CN111563290A (en) * | 2020-04-30 | 2020-08-21 | 深圳集智数字科技有限公司 | Building arrangement method and device |
| CN111563290B (en) * | 2020-04-30 | 2023-02-21 | 深圳集智数字科技有限公司 | Building arrangement method and device |
| CN113158312A (en) * | 2021-04-26 | 2021-07-23 | 深圳小库科技有限公司 | Construction plan generation method and device for construction land, storage medium and processor |
| CN114547727A (en) * | 2022-01-12 | 2022-05-27 | 万翼科技有限公司 | Building arrangement method and device, electronic equipment and storage medium |
| CN114528625A (en) * | 2022-02-17 | 2022-05-24 | 深圳须弥云图空间科技有限公司 | Building spacing calibration method and device |
| CN117828705A (en) * | 2024-01-11 | 2024-04-05 | 北京建筑大学 | Residence layout generation design method and system based on genetic algorithm search |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110796304A (en) | Building arrangement optimization method and device, electronic equipment and storage medium | |
| Alghais et al. | Modelling future impacts of urban development in Kuwait with the use of ABM and GIS | |
| Wang et al. | Sustainable transportation network design with stochastic demands and chance constraints | |
| KR102166490B1 (en) | System and apparatus for cost estimation of architecture and construction | |
| Liu et al. | Sustainable infrastructure design framework through integration of rating systems and building information modeling | |
| CN113987664B (en) | Building layout scheme generation method, system, device, terminal and storage medium | |
| CN104134159A (en) | Method for predicting maximum information spreading range on basis of random model | |
| Nazarko et al. | Sectoral foresight in Poland: thematic and methodological analysis | |
| KR102157775B1 (en) | Method, system and non-transitory computer-readable recording medium for providing information on value of real estate | |
| Li et al. | An integrated design of sustainable land use and transportation system with uncertainty in future population | |
| Choudhary et al. | Influence of district features on energy consumption in non-domestic buildings | |
| Zoraghein et al. | Data-enriched interpolation for temporally consistent population compositions | |
| Zhang et al. | An optimization model for guiding pedestrian–vehicle mixed flows during an emergency evacuation | |
| Nase et al. | Impact of quality-led design on real estate value: a spatiotemporal analysis of city centre apartments | |
| Chen et al. | Gravitational scaling analysis on spatial diffusion of COVID-19 in Hubei Province, China | |
| CN110413722B (en) | Address selection method, device and non-transient storage medium | |
| Dong et al. | A review of approaches and applications in building stock energy and indoor environment modelling | |
| CN108875032B (en) | Region type determination method and device | |
| Zhao et al. | LandSys II: Agent-based land use–forecast model with artificial neural networks and multiagent model | |
| CN107239889B (en) | Method for quantitatively evaluating building vulnerability of mountainous area under debris flow stress | |
| CN112287503A (en) | Dynamic space network construction method for traffic demand prediction | |
| Munn et al. | Spatial multi-criteria evaluation in 3D context: Suitability analysis of urban vertical development | |
| Liu et al. | Predicting construction accidents on sites: An improved atomic search optimization algorithm approach | |
| Debnath et al. | Opportunities and limitations of integrating computational and collaborative approaches to scenario planning | |
| Dodel | E‐skill's Effect on Occupational Attainment: A PISA‐Based Panel Study |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200214 |