CN117540509A - Intelligent building information analysis method and system applied to artificial intelligence - Google Patents
Intelligent building information analysis method and system applied to artificial intelligence Download PDFInfo
- Publication number
- CN117540509A CN117540509A CN202211629569.5A CN202211629569A CN117540509A CN 117540509 A CN117540509 A CN 117540509A CN 202211629569 A CN202211629569 A CN 202211629569A CN 117540509 A CN117540509 A CN 117540509A
- Authority
- CN
- China
- Prior art keywords
- wiring design
- abnormal wiring
- bim model
- arrays
- building electrical
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 107
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 16
- 238000013461 design Methods 0.000 claims abstract description 398
- 230000002159 abnormal effect Effects 0.000 claims abstract description 384
- 238000003491 array Methods 0.000 claims abstract description 194
- 238000012512 characterization method Methods 0.000 claims abstract description 180
- 238000012545 processing Methods 0.000 claims abstract description 62
- 238000000034 method Methods 0.000 claims description 37
- 230000000007 visual effect Effects 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 3
- 239000000523 sample Substances 0.000 description 98
- 238000005457 optimization Methods 0.000 description 16
- 239000013598 vector Substances 0.000 description 11
- 230000008569 process Effects 0.000 description 8
- 230000006872 improvement Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000009429 electrical wiring Methods 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241000579895 Chlorostilbon Species 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000010976 emerald Substances 0.000 description 1
- 229910052876 emerald Inorganic materials 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- ZLIBICFPKPWGIZ-UHFFFAOYSA-N pyrimethanil Chemical compound CC1=CC(C)=NC(NC=2C=CC=CC=2)=N1 ZLIBICFPKPWGIZ-UHFFFAOYSA-N 0.000 description 1
- 239000013074 reference sample Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Structural Engineering (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Design And Manufacture Of Integrated Circuits (AREA)
Abstract
The invention relates to a smart building information analysis method and a system applied to artificial intelligence, which are used for carrying out abnormal wiring design recognition processing on a building electrical BIM model of a target smart building according to R first target space structure characterization arrays obtained by arranging a first space structure characterization array and R second space structure characterization arrays of the building electrical BIM model of the target smart building, so that abnormal wiring design recognition results of the building electrical BIM model of the target smart building can be quickly and accurately obtained, classification recognition processing on a plurality of abnormal wiring design categories in the building electrical BIM model of the target smart building is realized, and overall and fine abnormal wiring design judgment is carried out on the whole building electrical BIM model, thereby providing accurate and reliable basis for subsequent construction design.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an intelligent building information analysis method and system applied to artificial intelligence.
Background
BIM technology not only can improve the stability of design result in the electrical design's of wisdom building in-process, but also can provide a good basic environment for building electrical use. BIM technology is introduced into building electricity, and is mainly applied to the aspects of strong current partial function design, weak current network adjustment, improvement of related design schemes and the like. However, in the practical design process of building electrical, some abnormal wiring designs often exist in the corresponding BIM model, and how to accurately classify and identify the abnormal wiring designs is one of the technical problems to be solved currently.
Disclosure of Invention
In a first aspect, an embodiment of the present invention provides a smart building information analysis method applied to artificial intelligence, and applied to a smart building information analysis system, where the method includes:
carrying out space structure representation analysis on a building electrical BIM model of a target intelligent building through the acquired intelligent building information analysis application to obtain a first space structure representation array of the building electrical BIM model, wherein the building electrical BIM model comprises E abnormal wiring design categories, and E is more than or equal to 2;
the first space structure representation array and R second space structure representation arrays are arranged to obtain R first target space structure representation arrays, the R second space structure representation arrays and the R first target space structure representation arrays are corresponding to R abnormal wiring design categories one by one, the R second space structure representation arrays are obtained through determination of a first building information analysis template, the first building information analysis template comprises at least one building electrical BIM model sample and sample annotation of each building electrical BIM model sample corresponding to each abnormal wiring design category in the R abnormal wiring design categories, R is not less than E, and the E abnormal wiring design categories are contained in the R abnormal wiring design categories;
And based on the R first target space structure representation arrays, carrying out abnormal wiring design identification processing on the building electrical BIM model to obtain an abnormal wiring design identification result of the building electrical BIM model.
In some optional embodiments, the sorting the first spatial structure characterization array with the R second spatial structure characterization arrays to obtain R first target spatial structure characterization arrays includes:
multiplying the first space structure representation array and the R second space structure representation array to obtain a R third space structure representation array, wherein R is an integer which is more than or equal to 1 and less than or equal to R;
performing difference on the first space structure representation array and the r second space structure representation array to obtain a fourth space structure representation array;
performing array integration on the first space structure representation array, the R third space structure representation array and the R fourth space structure representation array to obtain a R first target space structure representation array in the R first target space structure representation arrays; the R second spatial structure characterization array, the R third spatial structure characterization array, the R fourth spatial structure characterization array, and the R first target spatial structure characterization array are spatial structure characterization arrays corresponding to the R abnormal wiring design category of the R abnormal wiring design categories.
In some optional embodiments, the performing, based on the R first target spatial structure characterization arrays, abnormal wiring design recognition processing on the building electrical BIM model to obtain an abnormal wiring design recognition result of the building electrical BIM model includes:
based on the R first target space structure representation arrays, processing the building electrical BIM model according to abnormal wiring design categories, and determining R abnormal wiring design sub-models corresponding to the building electrical BIM model, wherein the R abnormal wiring design sub-models correspond to the R abnormal wiring design categories one by one;
and determining the abnormal wiring design recognition result based on the R abnormal wiring design submodels.
In some optional embodiments, the processing the building electrical BIM model according to the abnormal wiring design category based on the R first target spatial structure characterization arrays, determining R abnormal wiring design sub-models corresponding to the building electrical BIM model includes: loading the R first target space structure representation arrays to a BIM model analysis algorithm, and determining the R abnormal wiring design sub-models based on the BIM model analysis algorithm and the R first target space structure representation arrays by processing the building electrical BIM model according to the abnormal wiring design types.
In some optional embodiments, the processing the building electrical BIM model according to the abnormal wiring design category based on the R first target spatial structure characterization arrays, determining R abnormal wiring design sub-models corresponding to the building electrical BIM model includes: for an R first target space structure representation array in the R first target space structure representation arrays, determining an R abnormal wiring design sub-model in the R abnormal wiring design sub-models corresponding to the building electrical BIM based on the R first target space structure representation array, wherein the R abnormal wiring design sub-model comprises building electrical model data of which the abnormal wiring design category in the building electrical BIM is the R abnormal wiring design category in the R abnormal wiring design categories.
In some alternative embodiments, the intelligent building information analysis method applied to artificial intelligence is implemented using a depth residual network.
In some optional embodiments, the network training set of the depth residual network includes a first to-be-processed building electrical BIM model sample including not less than two of the R abnormal wiring design categories, an abnormal wiring design identification sample annotation of the first to-be-processed building electrical BIM model sample, and the first building information analysis template;
The method further comprises the steps of:
performing spatial structure characterization analysis on the first building electrical BIM model sample to be processed through the depth residual error network to obtain a fifth spatial structure characterization array of the first building electrical BIM model sample to be processed, and performing spatial structure characterization analysis on target building electrical BIM model samples corresponding to different wiring design categories in the R abnormal wiring design categories through the depth residual error network to obtain R fifth spatial structure characterization arrays, wherein the R fifth spatial structure characterization array corresponds to the R abnormal wiring design categories one by one, and the target building electrical BIM model sample corresponding to each abnormal wiring design category is one of at least one building electrical BIM model sample corresponding to each abnormal wiring design category;
determining R sixth spatial structure characterization arrays based on sample annotations of target building electrical BIM model samples corresponding to different wiring design categories in the R fifth spatial structure characterization arrays and the R abnormal wiring design categories, and sorting the fifth spatial structure characterization arrays and the R sixth spatial structure characterization arrays to obtain R second target spatial structure characterization arrays, wherein the R sixth spatial structure characterization arrays and the R second target spatial structure characterization arrays are corresponding to the R abnormal wiring design categories one by one;
Based on the R second target space structure characterization arrays, carrying out abnormal wiring design identification processing on the first to-be-processed building electrical BIM model sample to obtain an abnormal wiring design identification result of the first to-be-processed building electrical BIM model sample;
determining an abnormal wiring design recognition offset based on the abnormal wiring design recognition result of the first to-be-processed building electrical BIM model sample and the abnormal wiring design recognition sample annotation;
and optimizing the depth residual error network based on the abnormal wiring design identification offset to obtain an optimized depth residual error network.
In some optional embodiments, the sample annotation of the target building electrical BIM model sample corresponding to each abnormal wiring design category of the R abnormal wiring design categories is a set of salient visual features;
the determining R sixth spatial structure characterization arrays based on the R fifth spatial structure characterization arrays and the sample annotations of the target building electrical BIM model samples corresponding to the respective abnormal wiring design categories of the R abnormal wiring design categories includes:
and extracting features of the R fifth spatial structure characterization arrays based on the R fifth spatial structure characterization arrays and the salient visual feature sets of the target building electrical BIM model samples corresponding to the R abnormal wiring design types in the R abnormal wiring design types to obtain R sixth spatial structure characterization arrays in the R sixth spatial structure characterization arrays, wherein the R fifth spatial structure characterization arrays and the R sixth spatial structure characterization arrays are spatial structure characterization arrays corresponding to the R abnormal wiring design types in the R abnormal wiring design types.
In some alternative embodiments, prior to optimizing the depth residual network based on the first building electrical BIM model to be processed, the abnormal wiring design identification sample annotation of the first building electrical BIM model to be processed, and the first building information analysis template, the method further comprises:
the method comprises the steps of combining a second building electrical BIM model sample to be processed, abnormal wiring design identification sample notes of the second building electrical BIM model sample to be processed, and a second building information analysis template, pre-optimizing the depth residual error network, wherein the second building information analysis template comprises a plurality of building electrical BIM model samples corresponding to each abnormal wiring design category in T abnormal wiring design categories and sample notes of each building electrical BIM model sample, the R abnormal wiring design categories are derived abnormal wiring design categories outside the T abnormal wiring design categories, and the second building electrical BIM model sample to be processed comprises at least two abnormal wiring design categories in the T abnormal wiring design categories.
In some alternative embodiments, the method further comprises: and determining the R second space structure characterization arrays based on the first building information analysis template and the optimized depth residual error network.
In some optional embodiments, the sample annotation of building electrical BIM model samples corresponding to each abnormal wiring design category of the R abnormal wiring design categories is a set of salient visual features;
the determining the R second spatial structure characterization arrays based on the first building information analysis template and the optimized depth residual network includes:
carrying out space structure characterization analysis on building electrical BIM model samples corresponding to each abnormal wiring design category in the R abnormal wiring design categories through the optimized depth residual error network to obtain R eighth space structure characterization arrays;
performing feature extraction on an R eighth spatial structure representation array in the R eighth spatial structure representation arrays based on the R eighth spatial structure representation array and a salient visual feature set of a building electrical BIM model sample corresponding to an R abnormal wiring design category in the R abnormal wiring design categories to obtain an R second spatial structure representation array in the R second spatial structure representation arrays; the eighth and second space structure characterization arrays are space structure characterization arrays corresponding to the R-th abnormal wiring design category of the R abnormal wiring design categories.
In a second aspect, an embodiment of the present invention further provides a smart building information analysis system, including a processing engine, a network module, and a memory, where the processing engine and the memory communicate through the network module, and the processing engine is configured to read and run a computer program from the memory to implement the method described above.
In the following description, other features will be partially set forth. Upon review of the ensuing disclosure and the accompanying figures, those skilled in the art will in part discover these features or will be able to ascertain them through production or use thereof. Features of the present invention may be implemented and obtained by practicing or using various aspects of the methods, tools, and combinations listed in the detailed examples described below.
In the embodiment of the invention, the first space structure representation array of the building electrical BIM model of the target intelligent building is obtained by carrying out space structure representation analysis on the building electrical BIM model of the target intelligent building, which comprises E abnormal wiring design categories, the first space structure representation array is arranged with R second space structure representation arrays which are obtained by determining on the basis of the first building information analysis templates of the R abnormal wiring design categories, the R first space structure representation array is obtained, the R second space structure representation arrays can be used for reflecting different abnormal wiring design sub-models of the R abnormal wiring design categories, the E abnormal wiring design categories are contained in the R abnormal wiring design categories, on the basis of the R first space structure representation arrays obtained by arranging the first space structure representation array and the R second space structure representation arrays of the building electrical BIM model of the target intelligent building, the abnormal wiring design identification processing is carried out on the building electrical BIM model of the target intelligent building, the abnormal wiring design identification result of the building electrical BIM model of the target intelligent building can be obtained rapidly and accurately, and accordingly, the abnormal wiring design of the building electrical BIM in the intelligent building electrical BIM model can be accurately judged and comprehensively judged according to the abnormal wiring design categories.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
The methods, systems, and/or programs in the accompanying drawings will be described further in terms of exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein reference numerals represent similar mechanisms throughout the several views of the drawings.
Fig. 1 is a schematic diagram of hardware and software components in an exemplary intelligent building information analysis system, according to some embodiments of the invention.
FIG. 2 is a flow chart illustrating an exemplary intelligent building information analysis method and/or process for artificial intelligence in accordance with some embodiments of the present invention.
Detailed Description
In order to better understand the above technical solutions, the following detailed description of the technical solutions of the present invention is made by using the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and the embodiments of the present invention are detailed descriptions of the technical solutions of the present invention, and not limiting the technical solutions of the present invention, and the technical features of the embodiments and the embodiments of the present invention may be combined with each other without conflict.
In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant teachings. It will be apparent, however, to one skilled in the art that the invention can be practiced without these details. In other instances, well known methods, procedures, systems, components, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present invention.
These and other features, together with the functions of the presently disclosed invention, the methods of performing, the functions of the related elements of structure and the combination of parts and economies of manufacture, may become more apparent upon consideration of the following description with reference to the accompanying drawings, all of which form a part of this invention. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the invention. It should be understood that the drawings are not to scale. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the invention. It should be understood that the figures are not to scale.
The present invention uses a flowchart to illustrate the execution of a system according to an embodiment of the present invention. It should be clearly understood that the execution of the flowcharts may be performed out of order. Rather, these implementations may be performed in reverse order or concurrently. Additionally, at least one other execution may be added to the flowchart. One or more of the executions may be deleted from the flowchart.
As shown in fig. 1, the intelligent building information analysis system 100 may include a processing engine 110, a network module 120, and a memory 130, the processing engine 110 and the memory 130 communicating through the network module 120.
Processing engine 110 may process the relevant information and/or data to perform one or more functions described herein. For example, in some embodiments, processing engine 110 may include at least one processing engine (e.g., a single core processing engine or a multi-core processor). By way of example only, the processing engine 110 may include a central processing unit (CentralProcessingUnit, CPU), an Application-specific integrated circuit (Application-SpecificIntegratedCircuit, ASIC), a special instruction set processor (ASIP), a graphics processing unit (GraphicsProcessingUnit, GPU), a physical processing unit (PhysicsProcessingUnit, PPU), a digital signal processor (DigitalSignalProcessor, DSP), a field Programmable gate array (FieldProgrammableGateArray, FPGA), a Programmable logic device (Programmable LogicDevice, PLD), a controller, a microcontroller unit, a reduced instruction set computer (Reduced Instruction-SetComputer, RISC), a microprocessor, or the like, or any combination thereof.
The network module 120 may facilitate the exchange of information and/or data. In some embodiments, the network module 120 may be any type of wired or wireless network or combination thereof. By way of example only, the network module 120 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the internet, a local area network (LocalAreaNetwork, LAN), a wide area network (WideAreaNetwork, WAN), a wireless local area network (WirelessLocalAreaNetwork, WLAN), a metropolitan area network (MetropolitanAreaNetwork, MAN), a public switched telephone network (public switched SwitchedNetwork, PSTN), a bluetooth network, a wireless personal area network, a near field communication (NearField Communication, NFC) network, or the like, or any combination thereof. In some embodiments, the network module 120 may include at least one network access point. For example, the network module 120 may include a wired or wireless network access point, such as a base station and/or a network access point.
The memory 130 may be, but is not limited to, random access memory (RandomAccessMemory, RAM), read only memory (ReadOnlyMemory, ROM), programmable read only memory (programmable read-OnlyMemory, PROM), erasable read only memory (Erasable ProgrammableRead-OnlyMemory, EPROM), electrically erasable read only memory (Electric ErasableProgrammableRead-OnlyMemory, EEPROM), and the like. The memory 130 is used for storing a program, and the processing engine 110 executes the program after receiving an execution instruction.
It is to be understood that the configuration shown in fig. 1 is illustrative only and that the intelligent building information analysis system 100 may also include more or fewer components than shown in fig. 1 or have a different configuration than shown in fig. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.
FIG. 2 is a flow chart illustrating an exemplary intelligent building information analysis method and/or process for artificial intelligence according to some embodiments of the present invention, wherein the intelligent building information analysis method for artificial intelligence is applied to the intelligent building information analysis system 100 in FIG. 1, and further comprises the technical solutions described in steps 11-13.
And 11, analyzing the spatial structure representation of the building electrical BIM model of the target intelligent building through the acquired intelligent building information analysis application, and obtaining a first spatial structure representation array of the building electrical BIM model of the target intelligent building.
Further, the building electrical BIM model of the target intelligent building comprises E abnormal wiring design categories, wherein E is more than or equal to 2.
In the embodiment of the invention, the intelligent building information analysis application can be, for example, a request sent by other building data servers to the intelligent building information analysis system for processing the building electrical BIM model of the target intelligent building. The analysis of spatial structure characterization of the building electrical BIM model of the target intelligent building can be understood as performing spatial structure vector mining on the building electrical BIM model of the target intelligent building, so as to obtain a first spatial structure vector (i.e., a first spatial structure characterization array). Further, the target smart building may be an office building or a factory, for example, and the building electrical BIM model may include a structural arrangement model of building electrical, an electrical wiring model, and the like, for example. In response, the first spatial structure characterization array may reflect structural arrangement features of building electrical, routing and wiring features (including routing and wiring features of various power protection devices), and the like.
And step 12, arranging the first space structure representation array and the R second space structure representation arrays to obtain R first target space structure representation arrays, wherein the R second space structure representation arrays and the R first target space structure representation arrays are corresponding to R abnormal wiring design categories one by one.
Further, the R second spatial structure characterization arrays are determined and obtained through a first building information analysis template, wherein the first building information analysis template includes at least one building electrical BIM model sample corresponding to each abnormal wiring design category of R abnormal wiring design categories and sample annotation of each building electrical BIM model sample, R is not less than E, and the E abnormal wiring design categories are included in the R abnormal wiring design categories. In addition, the first building information analysis template may be understood as a first reference sample, and the sample annotation may be understood as annotation information.
In the embodiment of the present invention, the sorting of the first spatial structure representation array and the R second spatial structure representation arrays may be, for example, performing fusion processing on the first spatial structure representation array and the R second spatial structure representation arrays (second spatial structure vectors).
And 13, performing abnormal wiring design recognition processing on the building electrical BIM model of the target intelligent building according to the R first target space structure representation arrays to obtain an abnormal wiring design recognition result of the building electrical BIM model of the target intelligent building.
For example, the abnormal wiring design recognition processing is performed on the building electrical BIM model of the target intelligent building, and model data corresponding to different abnormal wiring design categories can be distinguished, so that the whole building electrical BIM model is split, the abnormal wiring design recognition result can be conveniently analyzed and used locally, and the whole building electrical BIM model is not required to be processed in the later stage.
Step 11-step 13 is implemented, through carrying out space structure characterization analysis on the building electrical BIM model of the target intelligent building including E abnormal wiring design categories, obtain the first space structure characterization array of the building electrical BIM model of the target intelligent building, the first space structure characterization array is organized with R second space structure characterization arrays which are obtained based on the determination of the first building information analysis templates of R abnormal wiring design categories, obtain R first target space structure characterization arrays, in view of the fact that R second space structure characterization arrays can be used for reflecting different abnormal wiring design sub-models of R abnormal wiring design categories, E abnormal wiring design categories are contained in R abnormal wiring design categories, based on the R first target space structure characterization arrays obtained according to the first space structure characterization arrays and the R second space structure characterization arrays of the building electrical BIM model of the target intelligent building, abnormal wiring design recognition processing is carried out on the building electrical BIM model of the target intelligent building, abnormal wiring design recognition results of the building electrical BIM model of the target intelligent building can be obtained rapidly and accurately, and accordingly, the abnormal wiring design of the building electrical BIM in the intelligent building electrical design can be accurately judged according to the detailed overall wiring design, and the abnormal wiring design can be accurately judged.
In some alternative embodiments, the intelligent building information analysis method applied to artificial intelligence is implemented using a deep residual network.
Further, by combining a depth residual error network, classification and identification processing of a plurality of abnormal wiring design categories in the building electrical BIM model of the target intelligent building can be realized, so that overall and fine abnormal wiring design judgment is carried out on the overall building electrical BIM model, and accurate and reliable basis is provided for subsequent construction design.
In some examples, the depth residual network includes a spatial structure characterization analysis subnet, a model disassembly subnet, a model reconstruction subnet, and a BIM model analysis algorithm.
Further, carrying out space structure representation analysis on the building electrical BIM model of the target intelligent building by means of a space structure representation analysis subnet in the depth residual error network to obtain a ninth space structure representation array of the building electrical BIM model of the target intelligent building; and after the ninth space structure representation array of the building electrical BIM model of the target intelligent building passes through the model disassembly sub-network in the depth residual error network, obtaining a first space structure representation array of the building electrical BIM model of the target intelligent building.
In some alternative embodiments, the first spatial structure characterization array and the R second spatial structure characterization arrays are sorted to obtain R first target spatial structure characterization arrays, which may include the following records in steps 121-123.
Step 121, multiplying the first spatial structure representation array and the R second spatial structure representation array by aiming at the R second spatial structure representation array in the R second spatial structure representation arrays to obtain a R third spatial structure representation array, wherein R is an integer which is more than or equal to 1 and less than or equal to R.
In the embodiment of the present invention, multiplying the first spatial structure representation array and the r second spatial structure representation array may be understood as performing a vector dot product on the first spatial structure vector and the r second spatial structure vector, so as to obtain a r third spatial structure vector (third spatial structure representation array).
Step 122, performing difference on the first space structure representation array and the r second space structure representation array to obtain a fourth space structure representation array.
In the embodiment of the present invention, performing a difference between the first spatial structure representation array and the r second spatial structure representation array may be understood as performing a vector subtraction on the first spatial structure vector and the r second spatial structure vector, so as to obtain a r fourth spatial structure vector (i.e., a fourth spatial structure representation array).
And 123, carrying out array integration on the first space structure representation array, the R third space structure representation array and the R fourth space structure representation array to obtain the R first target space structure representation array in the R first target space structure representation arrays.
Further, the R second spatial structure characterization array, the R third spatial structure characterization array, the R fourth spatial structure characterization array, and the R first target spatial structure characterization array are spatial structure characterization arrays corresponding to the R abnormal wiring design category of the R abnormal wiring design categories.
In view of adding R second space structure representation arrays corresponding to R abnormal wiring design categories in the process of carrying out abnormal wiring design identification processing on the building electrical BIM of the target intelligent building, in order to avoid misguidance caused by the R second space structure representation arrays, the R third space structure representation arrays obtained by multiplying the first space structure representation array of the building electrical BIM of the target intelligent building and the R second space structure representation arrays of the building electrical BIM of the target intelligent building and the R fourth space structure representation arrays obtained by subtracting the first space structure representation arrays of the building electrical BIM of the target intelligent building and the R second space structure representation arrays are subjected to array integration, so that the R first target space structure representation arrays corresponding to the R abnormal wiring design categories in the R first target space structure representation arrays capable of improving the resolution prediction accuracy are obtained.
In one example, the model reconstruction subnetwork in the depth residual error network implements the above multi-spatial structure representation array arrangement method, multiplies the first spatial structure representation array and the R second spatial structure representation arrays of the building electrical BIM model of the target smart building respectively to obtain R third spatial structure representation arrays, differents the first spatial structure representation array and the R second spatial structure representation arrays of the building electrical BIM model of the target smart building respectively to obtain R third spatial structure representation arrays, and integrates the first spatial structure representation arrays, the R third spatial structure representation arrays and the R third spatial structure representation arrays, thereby obtaining R first target spatial structure representation arrays.
In some optional embodiments, according to the R first target spatial structure characterization arrays, performing abnormal wiring design identification processing on the building electrical BIM model of the target smart building to obtain an abnormal wiring design identification result of the building electrical BIM model of the target smart building, which may include the following contents: according to the R first target space structure representation arrays, processing the building electrical BIM model of the target intelligent building according to the abnormal wiring design types, and determining R abnormal wiring design sub-models corresponding to the building electrical BIM model of the target intelligent building, wherein the R abnormal wiring design sub-models correspond to the R abnormal wiring design types one by one; and determining an abnormal wiring design recognition result according to the R abnormal wiring design submodels.
It can be understood that, in view of the fact that the R first target spatial structure characterization arrays combine different abnormal wiring design sub-models of the R abnormal wiring design categories and the first spatial structure characterization arrays of the building electrical BIM model of the target intelligent building, based on this, the building electrical BIM model of the target intelligent building is processed according to the abnormal wiring design categories according to the R first target spatial structure characterization arrays, the R abnormal wiring design sub-models corresponding to the R abnormal wiring design categories one by one can be obtained, so that by sorting the R abnormal wiring design sub-models, an abnormal wiring design recognition result of the building electrical BIM model of the target intelligent building can be obtained.
In some optional embodiments, according to the R first target spatial structure representation arrays, processing the building electrical BIM model of the target smart building according to the abnormal wiring design category, and determining R abnormal wiring design sub-models corresponding to the building electrical BIM model of the target smart building may include the following contents: loading R first target space structure representation arrays to a BIM model analysis algorithm, and processing a building electrical BIM model of a target intelligent building according to abnormal wiring design categories based on the BIM model analysis algorithm and the R first target space structure representation arrays to determine R abnormal wiring design sub-models.
It can be understood that in view of the fact that better sub-model discrimination can be achieved by the BIM model analysis algorithm, based on the fact that the building electrical BIM model of the target intelligent building is processed according to the abnormal wiring design category by means of the BIM model analysis algorithm and the R first target space structure representation arrays, R abnormal wiring design sub-models corresponding to the building electrical BIM model of the target intelligent building can be effectively obtained, and further abnormal wiring design recognition results of the building electrical BIM model of the target intelligent building are obtained.
Based on the above, the R first target spatial structure characterization arrays are loaded to the same BIM model analysis algorithm in the depth residual error network, and then the BIM model analysis algorithm can generate an abnormal wiring design recognition result of the building electrical BIM model of the target intelligent building.
In some optional embodiments, according to the R first target spatial structure representation arrays, processing the building electrical BIM model of the target smart building according to the abnormal wiring design category, and determining R abnormal wiring design sub-models corresponding to the building electrical BIM model of the target smart building may include the following contents: aiming at an R first target space structure representation array in the R first target space structure representation arrays, determining an R abnormal wiring design sub-model in R abnormal wiring design sub-models corresponding to a building electrical BIM model of the target intelligent building according to the R first target space structure representation array.
Further, the R-th abnormal wiring design sub-model includes building electrical model data of the R-th abnormal wiring design category among the R abnormal wiring design categories as an abnormal wiring design category in the building electrical BIM model of the target smart building.
It can be understood that, considering that the R first target spatial structure characterization array can be used to perform abnormal wiring design recognition processing on the R abnormal wiring design category in the R abnormal wiring design categories, based on this, according to the R first target spatial structure characterization array, abnormal wiring design recognition processing can be effectively performed on building electrical model data of which the abnormal wiring design category is the R abnormal wiring design category in the building electrical BIM model of the target intelligent building, so as to obtain the R abnormal wiring design sub-model in the R abnormal wiring design sub-models corresponding to the building electrical BIM model of the target intelligent building.
In one example, for an R first target spatial structure characterization array of the R first target spatial structure characterization arrays, after the R first target spatial structure characterization array passes through a BIM model analysis algorithm in the depth residual network, the BIM model analysis algorithm may generate R abnormal wiring design recognition results corresponding to the R first target spatial structure characterization array, where the abnormal wiring design classification in the building electrical BIM model including the target smart building in the abnormal wiring design recognition results is building electrical model data of each abnormal wiring design classification in the R abnormal wiring design classifications.
For example, when r=3 and p=1, there are three abnormal wiring design categories and three first target space structure characterization arrays corresponding to the three abnormal wiring design categories one by one, and for a first target space structure characterization array (corresponding to a first abnormal wiring design category in the three abnormal wiring design categories) in the three first target space structure characterization arrays, after the first target space structure characterization array passes through a BIM model analysis algorithm in the depth residual network, the BIM model analysis algorithm generates three abnormal wiring design recognition results corresponding to the first target space structure characterization array: the first abnormal wiring design identification result comprises building electrical BIM model abnormal wiring design data of the target intelligent building, wherein the building electrical BIM model abnormal wiring design data is of the first abnormal wiring design type; the second abnormal wiring design identification result comprises building electrical model data of which the abnormal wiring design category is the second abnormal wiring design category in the building electrical BIM model of the target intelligent building; the third abnormal wiring design recognition result includes building electrical model data of which the abnormal wiring design class in the building electrical BIM model of the target intelligent building is the third abnormal wiring design class. Because the first target space structure representation array can be used for carrying out abnormal wiring design recognition processing on the first abnormal wiring design category, only the first abnormal wiring design recognition result in three abnormal wiring design recognition results corresponding to the first target space structure representation array is extracted based on the first abnormal wiring design recognition result and is used for determining the first abnormal wiring design sub-model corresponding to the building electrical BIM model of the target intelligent building.
For example, when r=3, there are three abnormal wiring design classes and three first target space structure characterization arrays corresponding to each other, the first abnormal wiring design sub-model including building electrical model data of the first abnormal wiring design class in the building electrical BIM model of the target smart building can be determined according to the first target space structure characterization array (corresponding to the first abnormal wiring design class of the three abnormal wiring design classes), the third abnormal wiring design sub-model including building electrical wiring model data of the third abnormal wiring design class in the building electrical BIM model of the target smart building can be determined according to the second first target space structure characterization array (corresponding to the second abnormal wiring design class of the three abnormal wiring design classes), the second abnormal wiring design sub-model including building electrical model data of the second abnormal wiring design class in the building electrical BIM model of the target smart building can be determined according to the first target space structure characterization array (corresponding to the third abnormal wiring design class of the three abnormal wiring design classes), and the abnormal wiring result is processed according to the third abnormal wiring sub-design sub-model of the building electrical wiring model of the third abnormal wiring design class. The abnormal wiring design sub-model may be local data of the abnormal wiring design recognition result.
It will be appreciated that the depth residual network needs to be optimized before it can be used to classify and identify a plurality of abnormal wiring design categories in the building electrical BIM model of the target smart building. And optimizing the depth residual error network, namely optimizing a space structure representation analysis subnet, a model disassembly subnet, a model reconstruction subnet and a BIM model analysis algorithm in the depth residual error network.
In some optional embodiments, the network training set of the depth residual network includes a first building electrical BIM model sample to be processed, an abnormal wiring design identification sample annotation of the first building electrical BIM model sample to be processed, and a first building information analysis template, the first building electrical BIM model sample to be processed including at least two abnormal wiring design categories of the R abnormal wiring design categories; the intelligent building information analysis method applied to artificial intelligence may further include the following steps 201 to 205.
Step 201, performing spatial structure characterization analysis on the first building electrical BIM model sample to be processed through a depth residual error network to obtain a fifth spatial structure characterization array of the first building electrical BIM model sample to be processed, and performing spatial structure characterization analysis on the target building electrical BIM model sample corresponding to each abnormal wiring design category in the R abnormal wiring design categories through the depth residual error network to obtain R fifth spatial structure characterization arrays.
Further, the R fifth spatial structure characterization arrays correspond to the R abnormal wiring design categories one by one, and the target building electrical BIM model sample corresponding to each abnormal wiring design category is one of at least one building electrical BIM model sample corresponding to each abnormal wiring design category.
Step 202, determining R sixth spatial structure characterization arrays according to sample annotations of target building electrical BIM model samples corresponding to each abnormal wiring design category in the R fifth spatial structure characterization arrays and the R abnormal wiring design categories, and sorting the fifth spatial structure characterization arrays and the R sixth spatial structure characterization arrays to obtain R second target spatial structure characterization arrays.
Further, the R sixth spatial structure characterization arrays and the R second target spatial structure characterization arrays each correspond to the R abnormal wiring design categories one by one.
And 203, performing abnormal wiring design recognition processing on the first building electrical BIM model sample to be processed according to the R second target space structure representation arrays to obtain an abnormal wiring design recognition result of the first building electrical BIM model sample to be processed.
And 204, determining abnormal wiring design recognition offset according to the abnormal wiring design recognition result of the first to-be-processed building electrical BIM model sample and the abnormal wiring design recognition sample annotation.
In the embodiment of the present invention, the abnormal wiring design recognition offset can be understood as an abnormal wiring design recognition loss.
And 205, identifying offset according to the abnormal wiring design, and optimizing the depth residual error network to obtain an optimized depth residual error network.
It can be understood that, by using the first building information analysis template including at least one building electrical BIM model sample corresponding to each of the R abnormal wiring design categories and the sample annotation of each building electrical BIM model sample, the first building electrical BIM model sample to be processed including at least two of the R abnormal wiring design categories, and the abnormal wiring design identification sample annotation of the first building electrical BIM model sample to be processed, the optimized depth residual network performs the classification identification processing on at least two abnormal wiring design categories, so that the optimized depth residual network can quickly and accurately obtain the abnormal wiring design identification result of the building electrical BIM model including the target smart building of at least two of the R abnormal wiring design categories, thereby realizing the classification identification processing on at least two abnormal wiring design categories.
In some possible embodiments, the first building electrical BIM model sample to be processed, the target building electrical BIM model samples corresponding to each of the R abnormal wiring design categories, and the sample annotations for each of the target building electrical BIM model samples are loaded into the depth residual network. And a space structure characterization analysis subnet in a shared depth residual error network between the first building electrical BIM model sample to be processed and the target building electrical BIM model sample corresponding to each abnormal wiring design category in the R abnormal wiring design categories.
Further, spatial structure characterization analysis is performed on the first to-be-processed building electrical BIM model sample and target building electrical BIM model samples corresponding to different wiring design categories in the R abnormal wiring design categories through a shared spatial structure characterization analysis subnet, so as to obtain a tenth spatial structure characterization array and R fifth spatial structure characterization arrays of the first to-be-processed building electrical BIM model sample. And after the tenth space structure representation array of the first building electrical BIM model sample to be processed passes through the model disassembly sub-network in the depth residual error network, obtaining a fifth space structure representation array of the first building electrical BIM model sample to be processed.
In some alternative embodiments, the sample annotation of the target building electrical BIM model sample for each of the R abnormal wiring design categories is a set of salient visual features (window annotation features). In view of this, determining R sixth spatial structure characterization arrays according to the R fifth spatial structure characterization arrays and the sample annotations of the target building electrical BIM model samples corresponding to the respective abnormal wiring design categories of the R abnormal wiring design categories in step 202 may include the following: and aiming at an R fifth space structure representation array in the R fifth space structure representation arrays, carrying out feature extraction according to the R fifth space structure representation array and a salient visual feature set of a target building electrical BIM model sample corresponding to an R abnormal wiring design category in the R abnormal wiring design categories, and obtaining an R sixth space structure representation array in the R sixth space structure representation arrays.
Further, the R fifth spatial structure characterization array and the R sixth spatial structure characterization array are spatial structure characterization arrays corresponding to the R abnormal wiring design category of the R abnormal wiring design categories.
It can be understood that, in view of that when the R fifth spatial structure characterization arrays obtained by directly extracting the spatial structure characterization analysis subnet are arranged with the fifth spatial structure characterization arrays of the first to-be-processed building electrical BIM model example, the operation pressure is relatively large, and based on this, the R fifth spatial structure characterization arrays are extracted by using the corresponding significant visual feature set to obtain R sixth spatial structure characterization arrays, so that when the R sixth spatial structure characterization arrays are arranged with the fifth spatial structure characterization arrays of the first to-be-processed building electrical BIM model example, the operation pressure can be reduced, and then the R second target spatial structure characterization arrays can be obtained quickly and efficiently.
In some examples, for an R fifth spatial structure characterization array of the R fifth spatial structure characterization arrays, a model reconstruction subnet of the depth residual network performs feature extraction according to the R fifth spatial structure characterization array and a salient visual feature set of a target building electrical BIM model sample corresponding to an R abnormal wiring design category of the R abnormal wiring design categories, to obtain an R sixth spatial structure characterization array corresponding to the R abnormal wiring design category of the R sixth spatial structure characterization arrays.
In some alternative embodiments, the fifth spatial structure characterization array and the R sixth spatial structure characterization arrays are sorted to obtain R second target spatial structure characterization arrays, which may include the following: multiplying the fifth spatial structure representation array and the R sixth spatial structure representation array by aiming at the R sixth spatial structure representation array in the R sixth spatial structure representation arrays to obtain an R eleventh spatial structure representation array, wherein R is an integer which is more than or equal to 1 and less than or equal to R; performing difference on the fifth space structure representation array and the r sixth space structure representation array to obtain a twelfth space structure representation array; performing array integration on the fifth space structure representation array, the R eleventh space structure representation array and the R twelfth space structure representation array to obtain an R second target space structure representation array in the R second target space structure representation arrays; the R sixth spatial structure characterization array, the R eleventh spatial structure characterization array, the R twelfth spatial structure characterization array, and the R second target spatial structure characterization array are all spatial structure characterization arrays corresponding to the R abnormal wiring design category of the R abnormal wiring design categories.
In the optimization process of one round, target building electrical BIM model samples corresponding to different wiring design categories in R abnormal wiring design categories are arbitrarily selected, and in order to avoid misleading caused by the arbitrary selection, array classification ideas are characterized through a multi-space structure. The model reconstruction sub-network in the depth residual error network implements the multi-space structure representation array arrangement mode, multiplies the fifth space structure representation array of the first to-be-processed building electrical BIM model sample by the R sixth space structure representation arrays to obtain R eleventh space structure representation arrays, performs difference on the fifth space structure representation array of the first to-be-processed building electrical BIM model sample and the R sixth space structure representation arrays to obtain R twelfth space structure representation arrays, and performs array integration on the fifth space structure representation array, the R eleventh space structure representation arrays and the R twelfth space structure representation arrays to obtain R second target space structure representation arrays.
It can be understood that the R second target spatial structure characterization arrays are loaded to the same BIM model analysis algorithm in the depth residual error network, and the BIM model analysis algorithm performs processing according to the abnormal wiring design category on the building electrical BIM model sample to be processed, so as to output the abnormal wiring design recognition result of the first building electrical BIM model sample to be processed. Further, the exemplary split concept is similar to the split concept described above for the building electrical BIM model of the target smart building.
Based on the abnormal wiring design recognition result of the first to-be-processed building electrical BIM model sample and the abnormal wiring design recognition sample annotation of the first to-be-processed building electrical BIM model sample, the abnormal wiring design recognition offset of the depth residual network can be determined, and then network variables (network variables of the adjustment space structure characterization analysis sub-network, the model disassembly sub-network, the model reconstruction sub-network and the BIM model analysis algorithm) of the depth residual network are adjusted according to the abnormal wiring design recognition offset, so that the principal optimization of the depth residual network is completed. And obtaining an optimized depth residual error network meeting the set index by performing multi-cycle optimization.
In some alternative embodiments, cross entropy loss may be used to determine abnormal wiring design identification offset, and other types of loss may be used to determine abnormal wiring design identification offset.
In some alternative embodiments, before the first building electrical BIM model to be processed, the abnormal wiring design identification sample annotation of the first building electrical BIM model to be processed, and the first building information analysis template optimize the depth residual network, the intelligent building information analysis method applied to artificial intelligence may further include the following: and pre-optimizing the depth residual error network by combining the second building electrical BIM model sample to be processed, the abnormal wiring design identification sample annotation of the second building electrical BIM model sample to be processed and the second building information analysis template.
Further, the second building information analysis template includes a plurality of building electrical BIM model examples corresponding to each abnormal wiring design category of the T abnormal wiring design categories and sample annotation of each building electrical BIM model example, the R abnormal wiring design categories are derived abnormal wiring design categories other than the T abnormal wiring design categories, and the second building electrical BIM model example to be processed includes at least two abnormal wiring design categories of the T abnormal wiring design categories.
It will be appreciated that the T abnormal wiring design categories are reference categories, each abnormal wiring design category of the T abnormal wiring design categories corresponds to a plurality of building electrical BIM model examples, and the R abnormal wiring design categories are derivative abnormal wiring design categories other than the T abnormal wiring design categories, i.e., fewer building electrical BIM model examples corresponding to each abnormal wiring design category of the R abnormal wiring design categories, e.g., each abnormal wiring design category corresponds to only 1 building electrical BIM model example (1-model), or each abnormal wiring design category corresponds to only 5 building electrical BIM model examples (5-model). In the embodiment of the invention, the building electrical BIM model sample corresponding to each abnormal wiring design category in R abnormal wiring design categories can be further expanded to 10-model or more model numbers.
It can be understood that the first link optimization is performed on the depth residual network by using the second building electrical BIM model set corresponding to the T abnormal wiring design categories, the second building electrical BIM model sample to be processed and the abnormal wiring design identification sample annotation of the second building electrical BIM model sample to be processed, so that the depth residual network optimized through the first link has the performance of classifying and identifying the abnormal wiring design categories, and the second link optimization is performed on the depth residual network by using the first building electrical BIM model set corresponding to the R abnormal wiring design categories, the first building electrical BIM model sample to be processed and the abnormal wiring design identification sample annotation of the first building electrical BIM model sample to be processed, so that the depth residual network optimized through the second link has the performance of classifying and identifying the abnormal wiring design categories in the R abnormal wiring design categories serving as new categories.
It can be understood that the actual optimization idea of the first link optimization performed on the depth residual network is annotated by using the second building electrical BIM model set, the second building electrical BIM model sample to be processed and the abnormal wiring design identification sample of the second building electrical BIM model sample to be processed corresponding to the T abnormal wiring design categories, which is similar to the actual optimization idea of the second link optimization performed on the depth residual network by using the first building electrical BIM model set, the first building electrical BIM model sample to be processed and the abnormal wiring design identification sample of the first building electrical BIM model sample to be processed corresponding to the R abnormal wiring design categories.
For some examples, the invention shows a concept of two-link optimization of a depth residual network. Firstly, annotating abnormal wiring design identification samples of a second building electrical BIM model sample to be processed and a second building electrical BIM model sample to be processed by using a second building information analysis template corresponding to T abnormal wiring design categories serving as reference categories, and performing first link optimization on a depth residual error network; and performing second link optimization on the depth residual error network optimized through the first link by using the first building information analysis template corresponding to the R abnormal wiring design categories serving as the new category, the first building electrical BIM model sample to be processed and the abnormal wiring design identification sample annotation of the first building electrical BIM model sample to be processed, so as to obtain a final optimized depth residual error network.
In some alternative embodiments, the intelligent building information analysis method applied to artificial intelligence may further include the following: and determining R second space structure characterization arrays according to the first building information analysis template and the optimized depth residual error network.
Through the depth residual error network after the optimization of the two links, R second space structure characterization arrays used for disassembling R abnormal wiring design categories serving as new categories later can be determined.
In some alternative embodiments, determining R second spatial structure characterization arrays from the first building information analysis template and the optimized depth residual network may include: carrying out space structure characterization analysis on building electrical BIM model samples corresponding to each abnormal wiring design category in R abnormal wiring design categories through an optimized depth residual error network to obtain R eighth space structure characterization arrays; aiming at an R eighth space structure representation array in the R eighth space structure representation arrays, carrying out feature extraction according to the R eighth space structure representation array and a salient visual feature set of a building electrical BIM model sample corresponding to an R abnormal wiring design category in the R abnormal wiring design categories to obtain an R second space structure representation array in the R second space structure representation arrays; the eighth and second space structure characterization arrays are space structure characterization arrays corresponding to the R abnormal wiring design category of the R abnormal wiring design categories.
In the embodiment of the invention, aiming at an R-th abnormal wiring design category in R abnormal wiring design categories, a spatial structure representation analysis subnet in a depth residual error network after optimization through two links is utilized to carry out spatial structure representation analysis on a building electrical BIM model sample corresponding to the R-th abnormal wiring design category to obtain an R-th eighth spatial structure representation array (corresponding to the R-th abnormal wiring design category in R abnormal wiring design categories), and then a model reconstruction subnet in the depth residual error network after optimization through two links is utilized to carry out feature extraction according to the R-th eighth spatial structure representation array and a significant visual feature set of the building electrical BIM model sample corresponding to the R-th abnormal wiring design category to obtain an R-th second spatial structure representation array (corresponding to the R-th abnormal wiring design category in R abnormal wiring design categories). The actual processing ideas of the space structure representation analysis subnet and the model reconstruction subnet are similar to the optimization flow.
In some alternative embodiments, when each abnormal wiring design category in the R abnormal wiring design categories corresponds to only one building electrical BIM model sample (1-model), the R second spatial structure characterization arrays for performing abnormal wiring design identification processing on the R abnormal wiring design categories can be obtained by performing the spatial structure characterization analysis and the feature reduction processing one round last time. And when each abnormal wiring design category in the R abnormal wiring design categories corresponds to a plurality of building electrical BIM model samples, repeatedly implementing the analysis of the spatial structure characterization and the characteristic reduction processing for the last time for a plurality of times, and obtaining R second spatial structure characterization arrays for carrying out the abnormal wiring design identification processing on the R abnormal wiring design categories.
For example, in a 5-model scene, 5 rounds of previous space structure characterization analysis and feature reduction processing are repeatedly implemented, aiming at the same abnormal wiring design category, building electrical BIM model samples selected in each round are different, and averaging processing is carried out on second space structure characterization arrays corresponding to each abnormal wiring design category in the R abnormal wiring design categories obtained in the 5 rounds, so as to obtain the last R second space structure characterization arrays.
After the R second space structure representation arrays of different abnormal wiring design submodels for representing R abnormal wiring design categories are determined by using a depth residual error network optimized through two links and a first building information analysis template corresponding to the R abnormal wiring design categories, in the subsequent actual abnormal wiring design recognition processing process, a first building electrical BIM model set is not required to be loaded to the depth residual error network, and only the building electrical BIM model and R second space structure representation arrays of the target intelligent building are required to be loaded to the depth residual error network, so that classification recognition processing of a plurality of abnormal wiring design categories in the building electrical BIM model of the target intelligent building can be realized, and accordingly comprehensive and detailed abnormal wiring design judgment can be carried out on the whole building electrical BIM model, and accurate and reliable basis is provided for subsequent construction design.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements and adaptations of the invention may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within the present disclosure, and therefore, such modifications, improvements, and adaptations are intended to be within the spirit and scope of the exemplary embodiments of the present disclosure.
Meanwhile, the present invention uses specific terms to describe embodiments of the present invention. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the invention. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various portions of this specification are not necessarily all referring to the same embodiment. Furthermore, certain features, structures, or characteristics of at least one embodiment of the present invention may be combined as suitable.
In addition, those skilled in the art will appreciate that the various aspects of the invention are illustrated and described in the context of a number of patentable categories or conditions, including any novel and useful processes, machines, products, or materials, or any novel and useful improvements thereof. Accordingly, aspects of the invention may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "unit," component, "or" system. Furthermore, aspects of the invention may be embodied as a computer product in at least one computer-readable medium, the product comprising computer-readable program code.
The computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer readable signal medium may be propagated through any suitable medium including radio, electrical, fiber optic, RF, or the like, or any combination of the foregoing.
Computer program code required for carrying out aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming such as Java, scala, smalltalk, eiffel, JADE, emerald, C ++, c#, vb net, python, etc., or similar conventional programming languages such as C programming language, visual basic, fortran2003, perl, COBOL2002, PHP, ABAP, dynamic programming languages such as Python, ruby and Groovy, or other programming languages. The programming code may execute entirely on the user's computer, or as a stand-alone software package, or partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as software as a service (SaaS).
Furthermore, the order in which the processing elements and sequences are described, the use of numerical letters, or other designations are used is not intended to limit the order in which the processes and methods of the invention are performed unless specifically recited in the claims. While in the foregoing disclosure there has been discussed, by way of various examples, some embodiments of the invention which are presently considered to be useful, it is to be understood that this detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments of the invention. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.
It should also be appreciated that in the foregoing description of at least one embodiment of the invention, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of at least one embodiment of the invention. This method of disclosure, however, is not intended to imply that more features than are required by the subject invention. Indeed, less than all of the features of a single embodiment disclosed above.
Claims (10)
1. A smart building information analysis method applied to artificial intelligence, characterized in that it is applied to a smart building information analysis system, the method comprising:
carrying out space structure representation analysis on a building electrical BIM model of a target intelligent building through the acquired intelligent building information analysis application to obtain a first space structure representation array of the building electrical BIM model, wherein the building electrical BIM model comprises E abnormal wiring design categories, and E is more than or equal to 2;
the first space structure representation array and R second space structure representation arrays are arranged to obtain R first target space structure representation arrays, the R second space structure representation arrays and the R first target space structure representation arrays are corresponding to R abnormal wiring design categories one by one, the R second space structure representation arrays are obtained through determination of a first building information analysis template, the first building information analysis template comprises at least one building electrical BIM model sample and sample annotation of each building electrical BIM model sample corresponding to each abnormal wiring design category in the R abnormal wiring design categories, R is not less than E, and the E abnormal wiring design categories are contained in the R abnormal wiring design categories;
And based on the R first target space structure representation arrays, carrying out abnormal wiring design identification processing on the building electrical BIM model to obtain an abnormal wiring design identification result of the building electrical BIM model.
2. The method of claim 1, wherein the sorting the first spatial structure characterization array with the R second spatial structure characterization arrays to obtain R first target spatial structure characterization arrays comprises:
multiplying the first space structure representation array and the R second space structure representation array to obtain a R third space structure representation array, wherein R is an integer which is more than or equal to 1 and less than or equal to R;
performing difference on the first space structure representation array and the r second space structure representation array to obtain a fourth space structure representation array;
performing array integration on the first space structure representation array, the R third space structure representation array and the R fourth space structure representation array to obtain a R first target space structure representation array in the R first target space structure representation arrays; the R second spatial structure characterization array, the R third spatial structure characterization array, the R fourth spatial structure characterization array, and the R first target spatial structure characterization array are spatial structure characterization arrays corresponding to the R abnormal wiring design category of the R abnormal wiring design categories.
3. The method according to claim 1, wherein the performing, based on the R first target spatial structure characterization arrays, abnormal wiring design recognition processing on the building electrical BIM model to obtain an abnormal wiring design recognition result of the building electrical BIM model includes:
based on the R first target space structure representation arrays, processing the building electrical BIM model according to abnormal wiring design categories, and determining R abnormal wiring design sub-models corresponding to the building electrical BIM model, wherein the R abnormal wiring design sub-models correspond to the R abnormal wiring design categories one by one;
and determining the abnormal wiring design recognition result based on the R abnormal wiring design submodels.
4. The method of claim 3, wherein the processing the building electrical BIM model according to the abnormal wiring design category based on the R first target spatial structure representation arrays to determine R abnormal wiring design sub-models corresponding to the building electrical BIM model includes: loading the R first target space structure representation arrays to a BIM model analysis algorithm, and determining the R abnormal wiring design sub-models based on the BIM model analysis algorithm and the R first target space structure representation arrays by processing the building electrical BIM model according to the abnormal wiring design types.
5. The method of claim 3, wherein the processing the building electrical BIM model according to the abnormal wiring design category based on the R first target spatial structure representation arrays to determine R abnormal wiring design sub-models corresponding to the building electrical BIM model includes: for an R first target space structure representation array in the R first target space structure representation arrays, determining an R abnormal wiring design sub-model in the R abnormal wiring design sub-models corresponding to the building electrical BIM based on the R first target space structure representation array, wherein the R abnormal wiring design sub-model comprises building electrical model data of which the abnormal wiring design category in the building electrical BIM is the R abnormal wiring design category in the R abnormal wiring design categories.
6. The method of claim 1, wherein the intelligent building information analysis method applied to artificial intelligence is implemented using a depth residual network, a network training set of the depth residual network including a first building electrical BIM model sample to be processed, an abnormal wiring design identification sample annotation of the first building electrical BIM model sample to be processed, and the first building information analysis template, the first building electrical BIM model sample to be processed including at least two of the R abnormal wiring design categories;
The method further comprises the steps of:
performing spatial structure characterization analysis on the first building electrical BIM model sample to be processed through the depth residual error network to obtain a fifth spatial structure characterization array of the first building electrical BIM model sample to be processed, and performing spatial structure characterization analysis on target building electrical BIM model samples corresponding to different wiring design categories in the R abnormal wiring design categories through the depth residual error network to obtain R fifth spatial structure characterization arrays, wherein the R fifth spatial structure characterization array corresponds to the R abnormal wiring design categories one by one, and the target building electrical BIM model sample corresponding to each abnormal wiring design category is one of at least one building electrical BIM model sample corresponding to each abnormal wiring design category;
determining R sixth spatial structure characterization arrays based on sample annotations of target building electrical BIM model samples corresponding to different wiring design categories in the R fifth spatial structure characterization arrays and the R abnormal wiring design categories, and sorting the fifth spatial structure characterization arrays and the R sixth spatial structure characterization arrays to obtain R second target spatial structure characterization arrays, wherein the R sixth spatial structure characterization arrays and the R second target spatial structure characterization arrays are corresponding to the R abnormal wiring design categories one by one;
Based on the R second target space structure characterization arrays, carrying out abnormal wiring design identification processing on the first to-be-processed building electrical BIM model sample to obtain an abnormal wiring design identification result of the first to-be-processed building electrical BIM model sample;
determining an abnormal wiring design recognition offset based on the abnormal wiring design recognition result of the first to-be-processed building electrical BIM model sample and the abnormal wiring design recognition sample annotation;
and optimizing the depth residual error network based on the abnormal wiring design identification offset to obtain an optimized depth residual error network.
7. The method of claim 6, wherein the sample annotation of the target building electrical BIM model sample for each of the R abnormal wiring design categories is a set of salient visual features;
the determining R sixth spatial structure characterization arrays based on the R fifth spatial structure characterization arrays and the sample annotations of the target building electrical BIM model samples corresponding to the respective abnormal wiring design categories of the R abnormal wiring design categories includes:
and extracting features of the R fifth spatial structure characterization arrays based on the R fifth spatial structure characterization arrays and the salient visual feature sets of the target building electrical BIM model samples corresponding to the R abnormal wiring design types in the R abnormal wiring design types to obtain R sixth spatial structure characterization arrays in the R sixth spatial structure characterization arrays, wherein the R fifth spatial structure characterization arrays and the R sixth spatial structure characterization arrays are spatial structure characterization arrays corresponding to the R abnormal wiring design types in the R abnormal wiring design types.
8. The method of claim 6, wherein prior to optimizing the depth residual network based on the first building electrical BIM model to be processed, the abnormal wiring design identification sample annotation of the first building electrical BIM model to be processed, and the first building information analysis template, the method further comprises:
the method comprises the steps of combining a second building electrical BIM model sample to be processed, abnormal wiring design identification sample notes of the second building electrical BIM model sample to be processed, and a second building information analysis template, pre-optimizing the depth residual error network, wherein the second building information analysis template comprises a plurality of building electrical BIM model samples corresponding to each abnormal wiring design category in T abnormal wiring design categories and sample notes of each building electrical BIM model sample, the R abnormal wiring design categories are derived abnormal wiring design categories outside the T abnormal wiring design categories, and the second building electrical BIM model sample to be processed comprises at least two abnormal wiring design categories in the T abnormal wiring design categories.
9. The method of claim 6, wherein the method further comprises: determining the R second spatial structure characterization arrays based on the first building information analysis template and the optimized depth residual error network;
The building electrical BIM model sample corresponding to each abnormal wiring design category in the R abnormal wiring design categories is annotated as a significant visual feature set; the determining the R second spatial structure characterization arrays based on the first building information analysis template and the optimized depth residual network includes: carrying out space structure characterization analysis on building electrical BIM model samples corresponding to each abnormal wiring design category in the R abnormal wiring design categories through the optimized depth residual error network to obtain R eighth space structure characterization arrays; performing feature extraction on an R eighth spatial structure representation array in the R eighth spatial structure representation arrays based on the R eighth spatial structure representation array and a salient visual feature set of a building electrical BIM model sample corresponding to an R abnormal wiring design category in the R abnormal wiring design categories to obtain an R second spatial structure representation array in the R second spatial structure representation arrays; the eighth and second space structure characterization arrays are space structure characterization arrays corresponding to the R-th abnormal wiring design category of the R abnormal wiring design categories.
10. A smart building information analysis system comprising a processing engine, a network module and a memory, the processing engine and the memory in communication via the network module, the processing engine to read a computer program from the memory and to run the computer program to implement the method of any of claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211629569.5A CN117540509B (en) | 2022-12-19 | 2022-12-19 | Intelligent building information analysis method and system applied to artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211629569.5A CN117540509B (en) | 2022-12-19 | 2022-12-19 | Intelligent building information analysis method and system applied to artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117540509A true CN117540509A (en) | 2024-02-09 |
CN117540509B CN117540509B (en) | 2024-07-23 |
Family
ID=89786749
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211629569.5A Active CN117540509B (en) | 2022-12-19 | 2022-12-19 | Intelligent building information analysis method and system applied to artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117540509B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140039845A1 (en) * | 2012-08-02 | 2014-02-06 | Honeywell International Inc. | Determining a layout and wiring estimation for a heating, ventilation, and air conditioning system of a building |
CN110427961A (en) * | 2019-06-19 | 2019-11-08 | 华南农业大学 | A kind of rule-based and samples fusion architecture information extracting method and system |
CN110502803A (en) * | 2019-07-29 | 2019-11-26 | 兰州容大信息科技有限公司 | Wiring method and device based on BIM technology |
KR102302149B1 (en) * | 2021-03-04 | 2021-09-14 | 한방유비스 주식회사 | Method, apparatus and coumputer-readable medium for providing design solution of fire electric facility field |
CN113743727A (en) * | 2021-08-04 | 2021-12-03 | 苏州上应科技有限公司 | Building monitoring method based on BIM |
CN113807797A (en) * | 2020-06-11 | 2021-12-17 | 中国矿业大学(北京) | Underground engineering construction management and monitoring system integrated with BIM and intelligent algorithm |
CN114329724A (en) * | 2021-12-31 | 2022-04-12 | 北京泰豪智能工程有限公司 | Building information model BIM updating method and system based on vision |
CN114707282A (en) * | 2022-03-18 | 2022-07-05 | 中国能源建设集团江苏省电力设计院有限公司 | Intelligent monitoring method, system and medium for underground pipeline construction |
CN115163515A (en) * | 2022-07-15 | 2022-10-11 | 郑宇祺 | Building electrical equipment intelligent analysis monitoring system based on BIM |
-
2022
- 2022-12-19 CN CN202211629569.5A patent/CN117540509B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140039845A1 (en) * | 2012-08-02 | 2014-02-06 | Honeywell International Inc. | Determining a layout and wiring estimation for a heating, ventilation, and air conditioning system of a building |
CN110427961A (en) * | 2019-06-19 | 2019-11-08 | 华南农业大学 | A kind of rule-based and samples fusion architecture information extracting method and system |
CN110502803A (en) * | 2019-07-29 | 2019-11-26 | 兰州容大信息科技有限公司 | Wiring method and device based on BIM technology |
CN113807797A (en) * | 2020-06-11 | 2021-12-17 | 中国矿业大学(北京) | Underground engineering construction management and monitoring system integrated with BIM and intelligent algorithm |
KR102302149B1 (en) * | 2021-03-04 | 2021-09-14 | 한방유비스 주식회사 | Method, apparatus and coumputer-readable medium for providing design solution of fire electric facility field |
CN113743727A (en) * | 2021-08-04 | 2021-12-03 | 苏州上应科技有限公司 | Building monitoring method based on BIM |
CN114329724A (en) * | 2021-12-31 | 2022-04-12 | 北京泰豪智能工程有限公司 | Building information model BIM updating method and system based on vision |
CN114707282A (en) * | 2022-03-18 | 2022-07-05 | 中国能源建设集团江苏省电力设计院有限公司 | Intelligent monitoring method, system and medium for underground pipeline construction |
CN115163515A (en) * | 2022-07-15 | 2022-10-11 | 郑宇祺 | Building electrical equipment intelligent analysis monitoring system based on BIM |
Non-Patent Citations (1)
Title |
---|
岳丽雪;: "BIM在建筑电气设计中的应用情况及探讨", 信息化建设, no. 06, 15 June 2016 (2016-06-15) * |
Also Published As
Publication number | Publication date |
---|---|
CN117540509B (en) | 2024-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110263780B (en) | Method, device and equipment for realizing identification of properties of special composition picture and molecular space structure | |
CN110287104A (en) | Method for generating test case, device, terminal and computer readable storage medium | |
CN110826789A (en) | Power load prediction method and device based on power system and terminal equipment | |
CN110879776A (en) | Test case generation method and device | |
CN115204536A (en) | Building equipment fault prediction method, device, equipment and storage medium | |
CN114048468A (en) | Intrusion detection method, intrusion detection model training method, device and medium | |
CN113010671B (en) | App classification system | |
CN114462040A (en) | Malicious software detection model training method, malicious software detection method and malicious software detection device | |
CN110457207A (en) | Test method and relevant device based on machine learning model | |
CN117540509B (en) | Intelligent building information analysis method and system applied to artificial intelligence | |
US20200279148A1 (en) | Material structure analysis method and material structure analyzer | |
CN116740900B (en) | SVM-based power construction early warning method and system | |
Zhang et al. | Af-dndf: Asynchronous federated learning of deep neural decision forests | |
CN113110961A (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
CN117110794A (en) | Intelligent diagnosis system and method for cable faults | |
CN116431522A (en) | Automatic test method and system for low-code object storage gateway | |
JP7251955B2 (en) | Detection device and machine learning method | |
CN116449092A (en) | Automobile power detection method, system, computer and readable storage medium | |
US11003825B1 (en) | System, method, and computer program product for optimization in an electronic design | |
CN115358473A (en) | Power load prediction method and prediction system based on deep learning | |
CN107679478A (en) | The extracting method and system of transmission line of electricity space load state | |
CN114462127A (en) | Structural damage identification method and system based on deep extreme learning machine | |
CN109492707B (en) | Method, device and equipment for constructing spectral analysis model and storage medium | |
CN111859370A (en) | Method, apparatus, electronic device and computer-readable storage medium for identifying service | |
CN115237606B (en) | Edge calculation control system |
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 | ||
GR01 | Patent grant |