Hotel installation project pipeline layout optimization system and method based on BIM technology
Through BIM technology and deep learning artificial intelligence technology, intelligent collision detection of hotel installation engineering pipelines is achieved, solving the problem that manual design is difficult to detect pipeline conflicts in traditional methods, and improving the degree of automation and design efficiency of pipeline layout.
Patent Information
- Application Number
- CN202411179648.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-08-27
AI Technical Summary
The traditional hotel installation engineering pipeline layout design method relies on manual drawing, making it difficult to display complex pipeline systems comprehensively and intuitively, resulting in potential conflicts that are difficult to detect, affecting the progress and quality of the project. In addition, intelligent detection methods cannot eliminate reasonable collisions, and require manual judgment and consume time. .
The pipeline layout optimization system based on BIM technology uses the artificial intelligence technology of deep learning to extract pipeline layout features and realize intelligentization through local feature correlation analysis of pixel particle size Pipe collision detection.
It significantly improves the degree of automation of pipeline layout, optimizes pipeline layout, effectively avoids pipeline collision rework, and improves design quality and efficiency.
Smart Images

Figure CN118709341B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of hotel installation engineering, and specifically to a hotel installation engineering pipeline layout optimization system and method based on BIM technology. Background Art
[0002] In the complex ecosystem of the modern construction industry, hotel installation projects are undoubtedly a puzzle that requires delicate operation and efficient management. Among them, pipeline layout design, as the core link of the project, is of self-evident importance. This process involves the layout of multiple pipelines such as electricity, communications, water supply and drainage, and air conditioning. Its increasing complexity poses a severe challenge to the professional skills and patience of designers.
[0003] The traditional pipeline layout design method mainly relies on manual drawing and repeated adjustments by designers, which not only consumes a lot of manpower and time, but also the traditional two-dimensional design drawings are difficult to fully and intuitively display the complex pipeline system, resulting in difficulty in discovering potential pipeline conflicts and collisions during the design process, which may cause pipeline collision rework, thus seriously affecting the progress and quality of the project and increasing the difficulty and cost of later construction.
[0004] With the development of Building Information Modeling (BIM) technology, new possibilities have been provided for optimizing pipeline layout. BIM technology can realize three-dimensional visual design, facilitate the discovery and resolution of conflicts between pipelines, and improve design quality and efficiency. However, in related technologies, intelligent pipeline collision detection methods are usually based on simple geometric collision detection, which may not be able to exclude reasonable collisions such as components that should be connected or with adjacent components, resulting in the need for manual judgment item by item, which is time-consuming.
[0005] Therefore, an optimized pipeline layout optimization method for hotel installation projects based on BIM technology is expected. Summary of the invention
[0006] This application is made in view of the above problems. One purpose of this application is to provide a hotel installation project pipeline layout optimization system and method based on BIM technology.
[0007] The embodiment of the present application provides a hotel installation project pipeline layout optimization method based on BIM technology, which includes:
[0008] The hotel installation engineering pipelines are classified based on usage requirements, where functional pipelines are set as Class I pipelines, supply pipelines are set as Class II pipelines, and sewage pipelines are set as Class III pipelines;
[0009] Using IBM to perform three-dimensional modeling on the hotel installation engineering pipeline to obtain a three-dimensional model of the hotel installation engineering pipeline, and color-labeling the hotel installation engineering pipeline in the three-dimensional model of the hotel installation engineering pipeline based on the pipeline function;
[0010] A collision detection is performed on the three-dimensional model of the hotel installation project pipeline to obtain a collision detection result, and the collision detection result is used to indicate whether there is a pipeline collision phenomenon.
[0011] For example, according to the BIM-based hotel installation project pipeline layout optimization method of an embodiment of the present application, a collision detection is performed on the hotel installation project pipeline three-dimensional model to obtain a collision detection result, and the collision detection result is used to indicate whether there is a pipeline collision phenomenon, including:
[0012] Extract pipeline layout features based on the hotel installation project pipeline three-dimensional model to obtain a local layout feature map of the hotel installation project pipeline;
[0013] Performing autocorrelation attention enhancement on the local layout feature map of the hotel installation project pipeline to obtain a spatially significant feature map of the local layout of the hotel installation project pipeline;
[0014] Performing pixel-level feature energy level correlation analysis on the spatially significant feature map of the local layout of the hotel installation project pipeline to obtain a feature energy level guided pipeline distribution aggregation representation vector;
[0015] The pipeline distribution aggregation representation vector is guided based on the characteristic energy level to generate the collision detection result.
[0016] For example, according to the BIM technology-based hotel installation project pipeline layout optimization method of an embodiment of the present application, the pipeline layout features are extracted based on the hotel installation project pipeline three-dimensional model to obtain a local layout feature map of the hotel installation project pipeline, including:
[0017] The three-dimensional model of the hotel installation project pipeline is input into a pipeline layout feature extractor based on a three-dimensional convolutional neural network model to obtain a local layout feature map of the hotel installation project pipeline.
[0018] For example, according to the BIM-based hotel installation project pipeline layout optimization method of an embodiment of the present application, the hotel installation project pipeline local layout feature map is autocorrelatedly enhanced to obtain a hotel installation project pipeline local layout spatially significant feature map, including:
[0019] The local layout feature map of the hotel installation engineering pipeline is input into a feature space structure-preserving self-attention enhancement module based on cross-channel intersection to obtain a spatially significant feature map of the local layout of the hotel installation engineering pipeline.
[0020] For example, according to the BIM-based hotel installation project pipeline layout optimization method of an embodiment of the present application, the local layout feature map of the hotel installation project pipeline is input into a feature space structure-maintaining self-attention enhancement module based on cross-channel intersection to obtain a spatially significant feature map of the local layout of the hotel installation project pipeline, including:
[0021] Performing layer normalization on the hotel installation project pipeline local layout feature map to obtain a normalized hotel installation project pipeline local layout feature map;
[0022] Performing point convolution processing on the normalized hotel installation project pipeline local layout feature map to obtain a pipeline local layout channel context association representation feature map;
[0023] Convolutionally encoding the pipeline local layout channel context association representation feature map to obtain a pipeline local layout space context association representation feature map;
[0024] Copying the pipeline local layout space context association representation feature map to obtain a backup pipeline local layout space context association representation feature map;
[0025] Reshaping the pipeline local layout channel context association representation feature map, the pipeline local layout space context association representation feature map and the backup pipeline local layout space context association representation feature map to obtain a pipeline local layout channel context association representation feature matrix, a pipeline local layout space context association representation feature matrix and a backup pipeline local layout space context association representation feature matrix;
[0026] Calculating a cross-channel cross covariance matrix between the pipeline local layout channel context association representation feature matrix and the pipeline local layout spatial context association representation feature matrix;
[0027] Using a Softmax function to activate the cross-channel cross covariance matrix to obtain a pipeline local layout feature global interaction attention matrix;
[0028] Calculate the product of the backup pipeline local layout spatial context association representation feature matrix and the pipeline local layout feature global interaction attention matrix to obtain an attention-enhanced pipeline local layout feature representation matrix;
[0029] The feature shape of the attention-enhanced pipeline local layout feature representation matrix is reshaped to obtain a spatially significant feature map of the hotel installation project pipeline local layout.
[0030] For example, according to the BIM-based hotel installation project pipeline layout optimization method of an embodiment of the present application, a pixel-level feature energy level correlation analysis is performed on the significant feature map of the local layout space of the hotel installation project pipeline to obtain a feature energy level guided pipeline distribution aggregation representation vector, including:
[0031] Performing feature dispersion on the spatially significant feature map of the local layout of the hotel installation project pipeline to obtain a set of pixel granularity feature vectors of the hotel installation project pipeline layout;
[0032] The set of pixel granularity feature vectors of the hotel installation project pipeline layout is input into a feature aggregation network based on feature local energy distribution gating to obtain the feature energy level guided pipeline distribution aggregation representation vector.
[0033] For example, according to the BIM-based hotel installation project pipeline layout optimization method of an embodiment of the present application, a set of pixel granularity feature vectors of the hotel installation project pipeline layout is input into a feature aggregation network based on feature local energy distribution gating to obtain the feature energy level guided pipeline distribution aggregation representation vector, including:
[0034] Based on the maximum value, minimum value, mean value and variance of each hotel installation project pipeline layout pixel granularity feature vector in the set of hotel installation project pipeline layout pixel granularity feature vectors, determining the characteristic energy level coefficient of each hotel installation project pipeline layout pixel granularity feature vector to obtain a set of pipeline layout pixel granularity feature energy level coefficients;
[0035] Determine the scale of the local neighborhood, calculate the local neighborhood significance descriptor of each pipeline layout pixel granularity feature energy level coefficient in the pipeline layout pixel granularity feature energy level coefficient to obtain a set of pipeline layout pixel granularity feature energy level significance descriptors;
[0036] Inputting the set of pipeline layout pixel granularity feature energy level significance descriptors into a mask module based on a gating function to obtain a set of mask-gated probabilistic pipeline layout pixel granularity feature energy level significance descriptors;
[0037] Taking the set of mask-gated probabilistic pipeline layout pixel granularity feature energy level significance descriptors as a set of weights, the position-weighted sum of the set of pixel granularity feature vectors of the hotel installation project pipeline layout is calculated to obtain the feature energy level guided pipeline distribution aggregation representation vector.
[0038] For example, according to the BIM technology-based hotel installation project pipeline layout optimization method of an embodiment of the present application, based on the maximum value, minimum value, mean value and variance of each hotel installation project pipeline layout pixel granularity feature vector in the set of the hotel installation project pipeline layout pixel granularity feature vector, the characteristic energy level coefficient of each hotel installation project pipeline layout pixel granularity feature vector is determined to obtain a set of pipeline layout pixel granularity feature energy level coefficients, including:
[0039] Calculate the sum of the variance and the bias term of the pixel granularity feature vector of the hotel installation project pipeline layout to obtain a first intermediate term, and calculate the square of the difference between the maximum feature value and the mean value of the pixel granularity feature vector of the hotel installation project pipeline layout, the square of the difference between the minimum feature value and the mean value of the pixel granularity feature vector of the hotel installation project pipeline layout, and the sum of the bias term to obtain a second intermediate term;
[0040] The first intermediate term is divided by the second intermediate term to obtain the pipeline layout pixel granularity feature energy level coefficient.
[0041] For example, according to the BIM technology-based hotel installation project pipeline layout optimization method of an embodiment of the present application, the pipeline distribution aggregation representation vector is guided based on the characteristic energy level to generate the collision detection result, including:
[0042] The characteristic energy level guided pipeline distribution aggregation representation vector is input into a classifier-based collision detector to obtain the collision detection result.
[0043] The embodiment of the present application also provides a hotel installation project pipeline layout optimization system based on BIM technology, which includes:
[0044] The pipeline classification module is used to classify the hotel installation engineering pipelines based on usage requirements, wherein the functional pipelines are set as Class I pipelines, the supply pipelines are set as Class II pipelines, and the sewage pipelines are set as Class III pipelines;
[0045] A modeling and marking module is used to perform three-dimensional modeling on the hotel installation engineering pipeline using IBM to obtain a three-dimensional model of the hotel installation engineering pipeline, and to perform color marking based on pipeline functions on the hotel installation engineering pipeline in the three-dimensional model of the hotel installation engineering pipeline;
[0046] A collision analysis module, used for performing collision detection on the three-dimensional model of the hotel installation project pipeline to obtain a collision detection result, wherein the collision detection result is used to indicate whether there is a pipeline collision phenomenon;
[0047] Wherein, the collision analysis module includes:
[0048] Extract pipeline layout features based on the hotel installation project pipeline three-dimensional model to obtain a local layout feature map of the hotel installation project pipeline;
[0049] Inputting the local layout feature map of the hotel installation project pipeline into a feature space structure-maintaining self-attention enhancement module based on cross-channel intersection to obtain a spatially significant feature map of the local layout of the hotel installation project pipeline;
[0050] Performing pixel-level feature energy level correlation analysis on the spatially significant feature map of the local layout of the hotel installation project pipeline to obtain a feature energy level guided pipeline distribution aggregation representation vector;
[0051] The pipeline distribution aggregation representation vector is guided based on the characteristic energy level to generate the collision detection result.
[0052] According to the BIM technology-based hotel installation project pipeline layout optimization system and method of the embodiment of the present application, the hotel installation project pipelines are classified based on usage requirements, and color-labeled in the three-dimensional model of the pipelines. At the same time, the pipeline layout features of the three-dimensional model of the pipelines are extracted using artificial intelligence technology based on deep learning, and potential conflicts in the pipeline layout are mined through local feature correlation analysis at the pixel granularity, thereby realizing intelligent pipeline collision detection. In this way, the automation degree of pipeline layout can be significantly improved, the pipeline layout can be optimized, and the phenomenon of pipeline collision rework can be effectively avoided. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.
[0054] Figure 1 A schematic diagram of the application architecture of a hotel installation project pipeline arrangement optimization method based on BIM technology in an embodiment of the present application is shown;
[0055] Figure 2 A flow chart of a hotel installation project pipeline arrangement optimization method based on BIM technology in an embodiment of the present application is shown;
[0056] Figure 3 A flowchart of sub-step S530 of the hotel installation project pipeline arrangement optimization method based on BIM technology in an embodiment of the present application is shown;
[0057] Figure 4 A schematic diagram of the structure of a hotel installation project pipeline layout optimization system based on BIM technology in an embodiment of the present application is shown;
[0058] Figure 5An application scenario diagram of the hotel installation project pipeline layout optimization method based on BIM technology in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0059] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.
[0060] The terms used in this specification are those common terms currently widely used in the art in consideration of the functions of the present application, but these terms may vary according to the intentions of those skilled in the art, precedents, or new technologies in the art. In addition, specific terms may be selected, and in this case, their detailed meanings will be described in the detailed description of the present application. Therefore, the terms used in the specification should not be understood as simple names, but rather as a general description based on the meaning of the terms and the present application.
[0061] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.
[0062] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.
[0063] Figure 1 A schematic diagram of the application architecture of a hotel installation project pipeline layout optimization method based on BIM technology in an embodiment of the present application is shown, including a server 100 and a terminal device 200.
[0064] The terminal device 200 and the server 100 can be connected via the Internet to achieve mutual communication. Optionally, the above-mentioned Internet uses standard communication technology and / or protocol. The Internet is usually the Internet, but it can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or a virtual private network. In some embodiments, the data exchanged through the network can be represented by technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec), etc. can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.
[0065] The server 100 can provide various network services for the terminal device 200, wherein the server 100 can be a single server, a server cluster consisting of several servers, or a cloud computing center. Specifically, the server 100 may include a processor 110 (Center Processing Unit, CPU), a memory 120, an input device 130, and an output device 140, etc. The input device 130 may include a keyboard, a mouse, a touch screen, etc., and the output device 140 may include a display device, such as a liquid crystal display (Liquid Crystal Display, LCD), a cathode ray tube (Cathode Ray Tube, CRT), etc.
[0066] The memory 120 may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor 110 with program instructions and data stored in the memory 120. In the embodiment of the present application, the memory 120 may be used to store the program of the hotel installation engineering pipeline arrangement optimization method based on BIM technology in the embodiment of the present application.
[0067] The processor 110 calls the program instructions stored in the memory 120, and the processor 110 is used to execute the steps of any one of the hotel installation project pipeline layout optimization methods based on BIM technology in the embodiments of the present application according to the obtained program instructions.
[0068] In addition, the application architecture diagram in the embodiment of the present application is intended to more clearly illustrate the technical solution in the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present application is also applicable to similar problems.
[0069] The following is a non-restrictive description of the hotel installation project pipeline layout optimization method based on BIM technology provided according to at least one embodiment of the present application through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also belong to the scope of protection of this application.
[0070] In response to the above technical problems, the technical concept of this application is to classify hotel installation engineering pipelines based on usage requirements, and color-label them in the three-dimensional model of the pipelines. At the same time, artificial intelligence technology based on deep learning is used to extract pipeline layout features from the three-dimensional model of the pipelines, and through local feature correlation analysis at the pixel granularity, potential conflicts in pipeline layout are discovered, thereby realizing intelligent pipeline collision detection. In this way, the automation level of pipeline layout can be significantly improved, pipeline layout can be optimized, and pipeline collision rework can be effectively avoided.
[0071] Based on this, in the technical solution of this application, a hotel installation project pipeline layout optimization method based on BIM technology is proposed, such as Figure 2 As shown, it includes: S510, classifying hotel installation engineering pipelines based on usage requirements, wherein functional pipelines are set as Class I pipelines, supply pipelines are set as Class II pipelines, and sewage pipelines are set as Class III pipelines; S520, using IBM to perform three-dimensional modeling on the hotel installation engineering pipelines to obtain a three-dimensional model of the hotel installation engineering pipelines, and color-labeling the hotel installation engineering pipelines in the three-dimensional model of the hotel installation engineering pipelines based on pipeline functions; S530, performing collision detection on the three-dimensional model of the hotel installation engineering pipelines to obtain a collision detection result, and the collision detection result is used to indicate whether there is a pipeline collision phenomenon.
[0072] Among them, in step S530, if Figure 3As shown, collision detection is performed on the three-dimensional model of the hotel installation project pipeline to obtain a collision detection result, and the collision detection result is used to indicate whether there is a pipeline collision phenomenon, including: S531, extracting pipeline layout features based on the three-dimensional model of the hotel installation project pipeline to obtain a local layout feature map of the hotel installation project pipeline; S532, performing autocorrelation attention enhancement on the local layout feature map of the hotel installation project pipeline to obtain a spatially significant feature map of the local layout of the hotel installation project pipeline; S533, performing pixel-level feature energy level correlation analysis on the spatially significant feature map of the local layout of the hotel installation project pipeline to obtain a feature energy level-guided pipeline distribution aggregation representation vector; S534, generating the collision detection result based on the feature energy level-guided pipeline distribution aggregation representation vector.
[0073] Specifically, in the process of performing collision detection on the three-dimensional model of the hotel installation project pipeline, first, the three-dimensional model of the hotel installation project pipeline is input into the pipeline layout feature extractor based on the three-dimensional convolutional neural network model to obtain the local layout feature map of the hotel installation project pipeline. It should be understood that the three-dimensional convolutional neural network model can perform a convolution operation on each voxel (or "voxel block") in the three-dimensional model of the pipeline by using a three-dimensional convolution kernel, and extract the local detail features such as the direction, curvature, and intersection of the pipeline in the three-dimensional model of the hotel installation project pipeline, thereby achieving a deep understanding of the layout and structural information of the pipeline, and effectively improving the accuracy of pipeline conflict detection.
[0074] In one embodiment of the present application, the pipeline layout feature extractor based on the three-dimensional convolutional neural network model includes multiple three-dimensional convolutional layers, activation layers based on ReLU functions, and maximum pooling layers. Among them, the three-dimensional convolutional layer is used to perform sliding convolution operations in the height, width, and depth directions of the three-dimensional model data to extract the local features of the pipeline; the activation layer based on the ReLU function is used to introduce nonlinear transformations to enhance the expression ability of the model; the maximum pooling layer is used to reduce the dimension of the feature map, reduce the amount of calculation, and retain important feature information. More specifically, in the training process of the three-dimensional convolutional neural network model, first, a large number of hotel installation engineering pipeline three-dimensional models are collected and divided into local feature samples. Then, local detail features such as direction, curvature, and intersections are marked for each local feature sample. Then, the three-dimensional convolutional neural network model is trained using the labeled data so that the model can extract corresponding local detail features from the local feature samples. After the training is completed, the model is verified and optimized using unlabeled hotel installation engineering pipeline three-dimensional model data to ensure that it can accurately extract the local detail features of the pipeline layout.
[0075] In a specific example, on the PyCharm platform, combined with the TensorFlow2.0 toolkit, a pipeline layout feature extractor based on the three-dimensional convolutional neural network model was constructed. The parameters of the three-dimensional convolutional neural network model were set as follows: the size of the 3D convolution kernel of the first convolutional layer is [3×3×6], the convolution step is [1,1,4], and the pooling function is the sigmoid function. The size of the first pooling layer is [3×3×3], the size of the 3D convolution kernel of the second convolution layer is [3×3×6], the convolution step is [1,1,2], the size of the second pooling layer is [3×3×3], and the pooling function is the sigmoid function. It can be understood that the use of 3D convolutional layers can automatically learn the feature representation of the pipeline, and the convolution kernel slides in the voxelized data to capture local detail features.
[0076] Correspondingly, in step S531, pipeline layout features are extracted based on the three-dimensional model of the hotel installation project pipeline to obtain a local layout feature map of the hotel installation project pipeline, including: inputting the three-dimensional model of the hotel installation project pipeline into a pipeline layout feature extractor based on a three-dimensional convolutional neural network model to obtain the local layout feature map of the hotel installation project pipeline.
[0077] Since the three-dimensional model of the hotel installation engineering pipeline is three-dimensional structure data, there are complex cross-correlations between the channel features of the local layout feature map of the hotel installation engineering pipeline. In order to effectively mine the channel context association information in the local layout feature map of the hotel installation engineering pipeline, so as to better identify potential pipeline conflicts, the present application introduces a feature space structure-maintaining self-attention enhancement module based on cross-channel intersection to process the local layout feature map of the hotel installation engineering pipeline. Among them, the feature space structure-maintaining self-attention enhancement module can utilize the feature channel interaction of the local layout feature map of the hotel installation engineering pipeline to capture its channel context association information, and at the same time retain the spatial structure of the feature map, so as to take into account the robustness and richness of the feature expression. Specifically, the local layout feature map of the hotel installation engineering pipeline is firstly subjected to layer normalization to eliminate the scale differences between layers and ensure the stability of feature processing. Then, a multi-layer convolution operation is used to capture the channel context association and spatial structure information of the local layout feature map of the hotel installation engineering pipeline, and the channel context association information is used as the query, and the spatial structure information is used as the key and value. Based on the self-attention mechanism, the feature cross-channel global association interaction is performed. While retaining the spatial structure of the local layout feature map of the hotel installation engineering pipeline, the channel association information between feature structures is fused in units of feature spatial structure to enhance the expressiveness of the feature map, thereby obtaining the spatially significant feature map of the local layout of the hotel installation engineering pipeline.
[0078] Accordingly, in step S532, the local layout feature map of the hotel installation engineering pipeline is subjected to autocorrelation attention enhancement to obtain a spatially significant feature map of the local layout of the hotel installation engineering pipeline, including: inputting the local layout feature map of the hotel installation engineering pipeline into a self-attention enhancement module based on a feature space structure maintained across channel intersections to obtain a spatially significant feature map of the local layout of the hotel installation engineering pipeline.
[0079] Specifically, the local layout feature map of the hotel installation project pipeline is input into a feature space structure-maintaining self-attention enhancement module based on cross-channel intersection to obtain a spatially significant feature map of the local layout of the hotel installation project pipeline, including: layer normalization of the local layout feature map of the hotel installation project pipeline to obtain a normalized local layout feature map of the hotel installation project pipeline; point convolution processing of the normalized local layout feature map of the hotel installation project pipeline to obtain a pipeline local layout channel context association representation feature map; convolution encoding of the pipeline local layout channel context association representation feature map to obtain a pipeline local layout space context association representation feature map; copying the pipeline local layout space context association representation feature map to obtain a backup pipeline local layout space context association representation feature map; encoding the pipeline local layout channel context association representation feature map, the pipeline local layout space context association representation feature map and the backup pipeline local layout The local space context association representation feature map is reshaped to obtain the pipeline local layout channel context association representation feature matrix, the pipeline local layout space context association representation feature matrix and the backup pipeline local layout space context association representation feature matrix; the cross-channel cross covariance matrix between the pipeline local layout channel context association representation feature matrix and the pipeline local layout space context association representation feature matrix is calculated; the cross-channel cross covariance matrix is activated using the Softmax function to obtain the pipeline local layout feature global interaction attention matrix; the product between the backup pipeline local layout space context association representation feature matrix and the pipeline local layout feature global interaction attention matrix is calculated to obtain the attention-enhanced pipeline local layout feature representation matrix; the attention-enhanced pipeline local layout feature representation matrix is reshaped to obtain the hotel installation project pipeline local layout space salient feature map.
[0080] In a specific example, the local layout feature map of the hotel installation engineering pipeline is input into a feature space structure-maintaining self-attention enhancement module based on cross-channel intersection to obtain a spatially significant feature map of the local layout of the hotel installation engineering pipeline, including: processing the local layout feature map of the hotel installation engineering pipeline with the following autocorrelation attention enhancement formula to obtain the spatially significant feature map of the local layout of the hotel installation engineering pipeline, wherein the autocorrelation attention enhancement formula is:
[0081]
[0082]
[0083]
[0084]
[0085]
[0086]
[0087]
[0088]
[0089]
[0090] in, The characteristic diagram of the local layout of the hotel installation project pipeline is shown. Representation layer normalization operation, represents the normalized hotel installation project pipeline local layout characteristic diagram, represents point convolution, A context-related representation feature map representing the pipeline local layout channel, Represents convolution processing based on 3×3 convolution kernel, A spatial contextual representation feature graph representing the local layout of the pipeline, Indicates a copy operation. A spatial context-related representation feature graph representing the backup pipeline local layout, represents the feature shape reshaping, , and They respectively represent the pipeline local layout channel context association representation feature matrix, the pipeline local layout space context association representation feature matrix and the backup pipeline local layout space context association representation feature matrix, represents the cross-channel cross covariance matrix, is the scaling factor, represents the normalized exponential function, represents the matrix multiplication operation, A diagram showing the significant features of the local layout space of the hotel installation project pipeline.
[0091] Furthermore, in order to capture the subtle differences and potential conflicts between pipelines, a fine-grained local feature association analysis is further performed on the spatially significant feature map of the local layout of the hotel installation project pipelines. Specifically, in the technical solution of the present application, first, feature dispersion processing is performed on the spatially significant feature map of the local layout of the hotel installation project pipelines to refine the feature information therein to the pixel level, and obtain a set of pixel-granular feature vectors of the hotel installation project pipeline layout, thereby enhancing the sensitivity to local feature differences in the feature map.
[0092] Next, in order to capture the correlation dependency between the pixel granularity features of the pipeline layout, the present application introduces a feature aggregation network based on the feature local energy distribution gating to perform refined feature association analysis and aggregation processing on the set of pixel granularity feature vectors of the hotel installation project pipeline layout. Specifically, the feature aggregation network calculates its feature energy level coefficient based on the statistical characteristics of the pixel granularity feature vectors of the hotel installation project pipeline layout, and quantifies its energy distribution and energy level. Then, by calculating the mean of the feature energy level coefficients in the local neighborhood, the local neighborhood significance of the pixel granularity feature vectors of the hotel installation project pipeline layout is quantitatively described, and the weights are screened and allocated according to their feature significance through the gated mask technology, and the set of pixel granularity feature vectors of the hotel installation project pipeline layout is adaptively weighted and fused to enhance the correlation and discrimination of local features, and obtain the feature energy level-guided pipeline distribution aggregation representation vector. In this way, the tiny local feature differences and potential conflict points in the local layout feature map of the hotel installation project pipeline can be effectively mined, thereby improving the accuracy of collision detection.
[0093] Correspondingly, in step S533, a pixel-level feature energy level correlation analysis is performed on the spatially significant feature map of the local layout of the hotel installation engineering pipelines to obtain a feature energy level-guided pipeline distribution aggregation representation vector, including: feature dispersion of the spatially significant feature map of the local layout of the hotel installation engineering pipelines to obtain a set of pixel-granularity feature vectors of the hotel installation engineering pipeline layout; and inputting the set of pixel-granularity feature vectors of the hotel installation engineering pipeline layout into a feature aggregation network based on feature local energy distribution gating to obtain the feature energy level-guided pipeline distribution aggregation representation vector.
[0094] Among them, the set of pixel granularity feature vectors of the hotel installation project pipeline layout is input into the feature aggregation network based on the characteristic local energy distribution gating to obtain the characteristic energy level guided pipeline distribution aggregation representation vector, including: based on the maximum value, minimum value, mean value and variance of each hotel installation project pipeline layout pixel granularity feature vector in the set of the hotel installation project pipeline layout pixel granularity feature vector, the characteristic energy level coefficient of each hotel installation project pipeline layout pixel granularity feature vector is determined to obtain a set of pipeline layout pixel granularity feature energy level coefficients; the scale of the local neighborhood is determined, and the pipeline layout pixel granularity feature energy level coefficients are calculated. The local neighborhood significance descriptors of each pipeline layout pixel granularity feature energy level coefficient are obtained to obtain a set of pipeline layout pixel granularity feature energy level significance descriptors; the set of pipeline layout pixel granularity feature energy level significance descriptors is input into a mask module based on a gating function to obtain a set of mask-gated probabilistic pipeline layout pixel granularity feature energy level significance descriptors; the set of mask-gated probabilistic pipeline layout pixel granularity feature energy level significance descriptors is used as a set of weights, and the position-weighted sum of the set of hotel installation project pipeline layout pixel granularity feature vectors is calculated to obtain the feature energy level guided pipeline distribution aggregation representation vector.
[0095] Specifically, based on the maximum value, minimum value, mean value and variance of each hotel installation engineering pipeline layout pixel granularity feature vector in the set of the hotel installation engineering pipeline layout pixel granularity feature vector, the characteristic energy level coefficient of each hotel installation engineering pipeline layout pixel granularity feature vector is determined to obtain a set of pipeline layout pixel granularity feature energy level coefficients, including: calculating the variance and the sum of the bias term of the hotel installation engineering pipeline layout pixel granularity feature vector to obtain a first intermediate term, and calculating the square of the difference between the characteristic maximum value and the mean of the hotel installation engineering pipeline layout pixel granularity feature vector, the square of the difference between the characteristic minimum value and the mean of the hotel installation engineering pipeline layout pixel granularity feature vector, and the sum of the bias term to obtain a second intermediate term; calculating the first intermediate term divided by the second intermediate term to obtain the pipeline layout pixel granularity feature energy level coefficient.
[0096] In a specific example, the set of pixel granularity feature vectors of the hotel installation project pipeline layout is input into a feature aggregation network based on feature local energy distribution gating to obtain the feature energy level guided pipeline distribution aggregation representation vector, including: processing the set of pixel granularity feature vectors of the hotel installation project pipeline layout with the following feature aggregation formula to obtain the feature energy level guided pipeline distribution aggregation representation vector, wherein the feature aggregation formula is:
[0097]
[0098]
[0099]
[0100]
[0101]
[0102]
[0103]
[0104] in, represents the set of pixel granularity feature vectors of the pipeline layout of the hotel installation project, The value of is the number of feature vectors in the set of pixel granularity feature vectors of the hotel installation project pipeline layout, , , and They represent the first, second, and third pixel granularity feature vectors of the hotel installation project pipeline layout. and The pixel-level feature vector of the hotel installation project pipeline layout, For the The feature mean of the pixel-level feature vector of the hotel installation project pipeline layout, For the The feature variance of the pixel-level feature vector of the pipeline layout of the hotel installation project is and Respectively represent the The maximum and minimum values of each eigenvalue of the pixel granularity feature vector of the pipeline layout of the hotel installation project, is the bias term, Indicates the The pipeline layout pixel granularity feature energy level coefficient of the hotel installation project pipeline layout pixel granularity feature vector, Indicates The local neighborhood centered at The pixel granularity feature energy level coefficient of the pipeline layout, represents the number of pixel granularity feature energy level coefficients of the pipeline layout in the local neighborhood, For the pipeline layout pixel-granular feature energy-level saliency descriptors, Indicates A probabilistic pipeline layout pixel-granular feature energy-level saliency descriptor, Indicates mask processing, Indicates the preset mask threshold, Indicates mask-gated probabilistic pipeline layout pixel-level feature energy-level saliency descriptors, A pipeline distribution aggregate representation vector is directed for the characteristic energy level.
[0105] Next, the characteristic energy level-guided pipeline distribution aggregation representation vector is input into a classifier-based collision detector to obtain the collision detection result. That is, the characteristic energy level-guided pipeline distribution aggregation representation vector is subjected to feature pattern learning using a pre-trained classifier model, and at the same time, the characteristic energy level-guided pipeline distribution aggregation representation vector is subjected to classification mapping in combination with the classification decision boundary learned during the training process to output a binary classification result for indicating whether there is a pipeline collision phenomenon in the three-dimensional model of the hotel installation project pipeline. In this way, refined and intelligent collision detection of the three-dimensional model of the hotel installation project pipeline can be achieved, effectively avoiding rework caused by unreasonable pipeline layout, and improving engineering efficiency and quality.
[0106] Accordingly, in step S534, the collision detection result is generated based on the characteristic energy level guided pipeline distribution aggregation representation vector, including: inputting the characteristic energy level guided pipeline distribution aggregation representation vector into a classifier-based collision detector to obtain the collision detection result.
[0107] It should be understood that the role of the classifier is to use the given categories and known training data to learn classification rules and classifiers, and then classify (or predict) unknown data. Logistic regression, SVM, etc. are often used to solve binary classification problems. For multi-class classification problems, logistic regression or SVM can also be used, but multiple binary classifications are required to form a multi-classification, but this is prone to errors and inefficient. Commonly used multi-classification methods include the Softmax classification function.
[0108] In the technical solution of the present application, the local layout feature map of the hotel installation engineering pipeline is used to represent the local semantic features of the three-dimensional modeling of the hotel installation engineering pipeline three-dimensional model. After the local layout feature map of the hotel installation engineering pipeline is input into the feature space structure-maintaining self-attention enhancement module based on cross-channel intersection, and the spatial significant feature map of the local layout of the hotel installation engineering pipeline is feature dispersed, the obtained set of pixel granularity feature vectors of the hotel installation engineering pipeline layout is used to represent the feature distribution set of the spatial dimension enhanced expression of the local semantic features of the three-dimensional modeling. However, because feature enhancement occurs in the spatial dimension and feature dispersion acts on the channel dimension, this will make the feature manifold heterogeneity between the elements in the set of pixel granularity feature vectors of the hotel installation engineering pipeline layout more significant. In this way, when the set of pixel-granularity feature vectors of the hotel installation project pipeline layout is input into the feature aggregation network based on feature local energy distribution gating, the obtained feature energy level guided pipeline distribution aggregation representation vector will also cause insufficient feature aggregation coverage due to the energy difference of semantically associated nodes between local three-dimensional modeling semantic feature distributions, thereby leading to outlier class reasoning mapping deviation, affecting the accuracy of the collision detection result obtained by inputting the feature energy level guided pipeline distribution aggregation representation vector into the collision detector based on the classifier.
[0109] Based on this, in a preferred example, the characteristic energy level guided pipeline distribution aggregation representation vector is input into a classifier-based collision detector to obtain the collision detection result, including: calculating the characteristic mean of the characteristic energy level guided pipeline distribution aggregation representation vector, and dividing the characteristic mean by the difference between the maximum eigenvalue and the minimum eigenvalue of the characteristic energy level guided pipeline distribution aggregation representation vector to obtain a characteristic energy level guided pipeline distribution aggregation representation distribution characterization value; subtracting the characteristic energy level guided pipeline distribution aggregation representation distribution characterization value and dividing it by the characteristic energy level guided pipeline distribution aggregation representation distribution characterization value to obtain a characteristic energy level guided pipeline distribution aggregation representation distribution modulation value; activating the characteristic energy level guided pipeline distribution aggregation representation vector through a probabilistic function to obtain a probabilistic characteristic energy level guided pipeline distribution aggregation representation vector; performing point subtraction between the probabilistic characteristic energy level guided pipeline distribution aggregation representation vector and the characteristic energy level guided pipeline distribution aggregation representation distribution modulation value, taking the absolute value and performing the sum operation. Calculate the negative of the logarithmic value with base 2 to obtain a probabilistic feature energy level guided pipeline distribution aggregation representation distribution modulation information vector; divide the feature energy level guided pipeline distribution aggregation representation distribution characterization value by one minus the difference of each eigenvalue of the probabilistic feature energy level guided pipeline distribution aggregation representation vector, sum all eigenvalues of the probabilistic feature energy level guided pipeline distribution aggregation representation vector, and divide it by the length of the feature energy level guided pipeline distribution aggregation representation vector to obtain a probabilistic feature energy level guided pipeline distribution aggregation representation distribution modulation bias value; perform dot addition on the probabilistic feature energy level guided pipeline distribution aggregation representation distribution modulation information vector and the probabilistic feature energy level guided pipeline distribution aggregation representation distribution modulation bias value multiplied by a weight as a hyperparameter to obtain an optimized feature energy level guided pipeline distribution aggregation representation vector; input the optimized feature energy level guided pipeline distribution aggregation representation vector into a classifier-based collision detector to obtain a collision detection result to obtain a control result.
[0110] The calculation process of the optimized characteristic energy level guided pipeline distribution aggregation representation vector is expressed by the following optimization formula:
[0111]
[0112] And among them:
[0113]
[0114] in, represents the characteristic mean of the characteristic energy level guiding pipeline distribution aggregation representation vector, and They respectively represent the maximum eigenvalue and the minimum eigenvalue in the characteristic energy level guiding pipeline distribution aggregation representation vector, 𝑝 represents the distribution representation value of the characteristic energy level guiding pipeline distribution aggregation representation, represents the probabilistic feature energy level guided pipeline distribution aggregation representation vector obtained after the feature energy level guided pipeline distribution aggregation representation vector is activated by a probabilistic function, The first representation vector of the probabilistic feature energy level guide pipeline distribution aggregation representation vector eigenvalues, represents the logarithmic function with base 2, 𝜀 is the weight as a hyperparameter, The value of is the length of the probabilistic feature energy level guide pipeline distribution aggregation representation vector, It means to subtract by position point. Indicates adding by position point. The optimized feature energy level guide pipeline distribution aggregation representation vector is represented.
[0115] That is, in the above preferred example, the eigenvalue-based probability information distribution planning of the feature energy level guided pipeline distribution aggregation representation vector is performed by using the Bernoulli probability modulation distribution of the feature energy level guided pipeline distribution aggregation representation vector relative to the eigenvalue distribution, and the probability reverse mapping of the probability feature of the feature energy level guided pipeline distribution aggregation representation vector as a whole is used as an extended coverage of the set mapping space of the feature energy level guided pipeline distribution aggregation representation vector to independently understand the interaction path between the intuitive probability information distribution and the abstract probability space mapping of the feature energy level guided pipeline distribution aggregation representation vector, so as to improve the accuracy of the collision detection result obtained by inputting the optimized feature energy level guided pipeline distribution aggregation representation vector into the classifier-based collision detector by avoiding the counterfactual reasoning mapping of the outlier feature distribution of the feature energy level guided pipeline distribution aggregation representation vector to the class probability.
[0116] Furthermore, it should be known to those skilled in the art that neural networks need to be trained before application inference, and the goal of neural network training is to minimize the loss function of the entire network. This process is end-to-end, meaning that the input data passes through each layer of the network and eventually generates an output, and then the difference between the predicted output and the true label is calculated through the loss function.
[0117] Therefore, in one embodiment of the present application, the hotel installation project pipeline layout optimization based on BIM technology also includes a training process. During the training process, a three-dimensional model of the hotel installation project pipeline for training is obtained, and it is sequentially passed through the pipeline layout feature extractor based on the three-dimensional convolutional neural network model, the feature space structure based on cross-channel intersection to maintain self-attention reinforcement module, the feature aggregation network based on feature local energy distribution gating, and the collision detector based on the classifier to obtain the predicted collision detection result, and then the cross entropy between the predicted collision detection result and the real collision detection result is calculated as the loss function. During the training process, the back propagation algorithm is used to calculate the gradient of the loss relative to the network parameters. These gradients indicate how to adjust the weights and biases in the network to reduce the loss. Based on the calculated gradients, an optimization algorithm (such as SGD, Adam, etc.) is used to update all parameters in the pipeline layout feature extractor based on the three-dimensional convolutional neural network model, the feature space structure based on cross-channel intersection to maintain self-attention reinforcement module, the feature aggregation network based on feature local energy distribution gating, and the collision detector based on the classifier.
[0118] Based on the above embodiments, see Figure 4 As shown, it is a structural schematic diagram of a hotel installation engineering pipeline arrangement optimization system 800 based on BIM technology in an embodiment of the present application. The hotel installation engineering pipeline arrangement optimization system 800 based on BIM technology includes: a pipeline classification module 810, which is used to classify hotel installation engineering pipelines based on usage requirements, wherein functional pipelines are set as Class I pipelines, supply pipelines are set as Class II pipelines, and sewage pipelines are set as Class III pipelines; a modeling and marking module 820, which is used to use IBM to perform three-dimensional modeling on the hotel installation engineering pipelines to obtain a three-dimensional model of the hotel installation engineering pipelines, and to perform color marking on the hotel installation engineering pipelines in the three-dimensional model of the hotel installation engineering pipelines based on the pipeline functions; a collision analysis module 830, which is used to perform collision detection on the three-dimensional model of the hotel installation engineering pipelines to obtain a collision detection result, and the collision detection result is used to indicate whether there is a pipeline collision phenomenon.
[0119] Here, those skilled in the art can understand that the specific functions and operations of each module in the above-mentioned hotel installation engineering pipeline arrangement optimization system 800 based on BIM technology have been referred to above. Figure 2 to Figure 3 The description of the pipeline layout optimization method for hotel installation projects based on BIM technology has been introduced in detail, and therefore, its repeated description will be omitted.
[0120] Figure 5 This is an application scenario diagram of the hotel installation project pipeline layout optimization method based on BIM technology according to an embodiment of the present application. Figure 5As shown, in this application scenario, first, obtain the hotel installation project pipeline 3D model (for example, Figure 5 Then, the hotel installation project pipeline three-dimensional model is input to a server (for example, Figure 5 In S) shown in , the server can use the hotel installation project pipeline layout optimization algorithm based on BIM technology to process the hotel installation project pipeline three-dimensional model to obtain a collision detection result for indicating whether there is a pipeline collision phenomenon.
[0121] Based on the above embodiments, another exemplary embodiment of an electronic device is also provided in the embodiments of the present application. In some possible implementations, the electronic device in the embodiments of the present application may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the hotel installation project pipeline layout optimization method based on BIM technology in the above embodiments when executing the program.
[0122] For example, in the case of electronic equipment Figure 1 Taking the server 100 in the example as an example, the processor in the electronic device is the processor 110 in the server 100, and the memory in the electronic device is the memory 120 in the server 100.
[0123] The embodiment of the present application also provides a computer-readable storage medium, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the hotel installation engineering pipeline arrangement optimization method based on BIM technology according to the embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may, for example, include a read-only memory (ROM), a hard disk, a flash memory, etc.
[0124] The embodiment of the present application also provides a computer program product or computer program, which includes computer executable instructions, and the computer executable instructions are stored in a computer readable storage medium. The processor of the computer device reads the computer executable instructions from the computer readable storage medium, and the processor executes the computer executable instructions, so that the computer device executes the hotel installation engineering pipeline layout optimization method based on BIM technology according to the embodiment of the present application.
[0125] Those skilled in the art will appreciate that the contents disclosed in this application may be subject to various variations and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.
[0126] In addition, although the present application makes various references to certain units in the system according to embodiments of the present application, any number of different units can be used and run on the client and / or server. The units are only illustrative, and different aspects of the system and method can use different units.
[0127] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present application is not limited to any particular form of combination of hardware and software.
[0128] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.
[0129] The above is an explanation of the present application and should not be considered as limiting thereof. Although several exemplary embodiments of the present application have been described, those skilled in the art will readily appreciate that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present application.
Claims
1. A hotel installation project pipeline layout optimization method based on BIM technology, characterized in that: include: The hotel installation engineering pipelines are classified based on usage requirements, where functional pipelines are set as Class I pipelines, supply pipelines are set as Class II pipelines, and sewage pipelines are set as Class III pipelines; Using IBM to perform three-dimensional modeling on the hotel installation engineering pipeline to obtain a three-dimensional model of the hotel installation engineering pipeline, and color-labeling the hotel installation engineering pipeline in the three-dimensional model of the hotel installation engineering pipeline based on the pipeline function; Performing collision detection on the three-dimensional model of the hotel installation project pipeline to obtain a collision detection result, wherein the collision detection result is used to indicate whether there is a pipeline collision phenomenon; The three-dimensional model of the hotel installation project pipeline is subjected to collision detection to obtain a collision detection result, and the collision detection result is used to indicate whether there is a pipeline collision phenomenon, including: Extract pipeline layout features based on the hotel installation project pipeline three-dimensional model to obtain a local layout feature map of the hotel installation project pipeline; Inputting the local layout feature map of the hotel installation project pipeline into a feature space structure-maintaining self-attention enhancement module based on cross-channel intersection to obtain a spatially significant feature map of the local layout of the hotel installation project pipeline; Performing pixel-level feature energy level correlation analysis on the spatially significant feature map of the local layout of the hotel installation project pipeline to obtain a feature energy level guided pipeline distribution aggregation representation vector; Based on the characteristic energy level, the pipeline distribution aggregation representation vector is guided to generate the collision detection result; The local layout feature map of the hotel installation project pipeline is input into a feature space structure-maintaining self-attention enhancement module based on cross-channel intersection to obtain a spatially significant feature map of the local layout of the hotel installation project pipeline, including: Performing layer normalization on the hotel installation project pipeline local layout feature map to obtain a normalized hotel installation project pipeline local layout feature map; Performing point convolution processing on the normalized hotel installation project pipeline local layout feature map to obtain a pipeline local layout channel context association representation feature map; Convolutionally encoding the pipeline local layout channel context association representation feature map to obtain a pipeline local layout space context association representation feature map; Copying the pipeline local layout space context association representation feature map to obtain a backup pipeline local layout space context association representation feature map; Reshaping the pipeline local layout channel context association representation feature map, the pipeline local layout space context association representation feature map and the backup pipeline local layout space context association representation feature map to obtain a pipeline local layout channel context association representation feature matrix, a pipeline local layout space context association representation feature matrix and a backup pipeline local layout space context association representation feature matrix; Calculating a cross-channel cross covariance matrix between the pipeline local layout channel context association representation feature matrix and the pipeline local layout spatial context association representation feature matrix; Using a Softmax function to activate the cross-channel cross covariance matrix to obtain a pipeline local layout feature global interaction attention matrix; Calculate the product of the backup pipeline local layout spatial context association representation feature matrix and the pipeline local layout feature global interaction attention matrix to obtain an attention-enhanced pipeline local layout feature representation matrix; The feature shape of the attention-enhanced pipeline local layout feature representation matrix is reshaped to obtain a spatially significant feature map of the hotel installation project pipeline local layout.
2. The hotel installation project pipeline layout optimization method based on BIM technology according to claim 1 is characterized in that: Extracting pipeline layout features based on the hotel installation project pipeline three-dimensional model to obtain a local layout feature map of the hotel installation project pipeline includes: The three-dimensional model of the hotel installation project pipeline is input into a pipeline layout feature extractor based on a three-dimensional convolutional neural network model to obtain a local layout feature map of the hotel installation project pipeline.
3. The hotel installation project pipeline layout optimization method based on BIM technology according to claim 2 is characterized in that: Performing pixel-level feature energy level correlation analysis on the spatial significant feature map of the local layout of the hotel installation project pipeline to obtain a feature energy level guided pipeline distribution aggregation representation vector, including: Performing feature dispersion on the spatially significant feature map of the local layout of the hotel installation project pipeline to obtain a set of pixel granularity feature vectors of the hotel installation project pipeline layout; The set of pixel granularity feature vectors of the hotel installation project pipeline layout is input into a feature aggregation network based on feature local energy distribution gating to obtain the feature energy level guided pipeline distribution aggregation representation vector.
4. The hotel installation project pipeline layout optimization method based on BIM technology according to claim 3 is characterized in that: Inputting the set of pixel granularity feature vectors of the hotel installation project pipeline layout into a feature aggregation network based on feature local energy distribution gating to obtain the feature energy level guided pipeline distribution aggregation representation vector, including: Based on the maximum value, minimum value, mean value and variance of each hotel installation project pipeline layout pixel granularity feature vector in the set of hotel installation project pipeline layout pixel granularity feature vectors, determining the characteristic energy level coefficient of each hotel installation project pipeline layout pixel granularity feature vector to obtain a set of pipeline layout pixel granularity feature energy level coefficients; Determine the scale of the local neighborhood, calculate the local neighborhood significance descriptor of each pipeline layout pixel granularity feature energy level coefficient in the pipeline layout pixel granularity feature energy level coefficient to obtain a set of pipeline layout pixel granularity feature energy level significance descriptors; Inputting the set of pipeline layout pixel granularity feature energy level significance descriptors into a mask module based on a gating function to obtain a set of mask-gated probabilistic pipeline layout pixel granularity feature energy level significance descriptors; Taking the set of mask-gated probabilistic pipeline layout pixel granularity feature energy level significance descriptors as a set of weights, the position-weighted sum of the set of pixel granularity feature vectors of the hotel installation project pipeline layout is calculated to obtain the feature energy level guided pipeline distribution aggregation representation vector.
5. The hotel installation project pipeline layout optimization method based on BIM technology according to claim 4 is characterized in that: Based on the maximum value, minimum value, mean value and variance of each hotel installation project pipeline layout pixel granularity feature vector in the set of hotel installation project pipeline layout pixel granularity feature vectors, determining the characteristic energy level coefficient of each hotel installation project pipeline layout pixel granularity feature vector to obtain a set of pipeline layout pixel granularity feature energy level coefficients, including: Calculate the sum of the variance and the bias term of the pixel granularity feature vector of the hotel installation project pipeline layout to obtain a first intermediate term, and calculate the square of the difference between the maximum feature value and the mean value of the pixel granularity feature vector of the hotel installation project pipeline layout, the square of the difference between the minimum feature value and the mean value of the pixel granularity feature vector of the hotel installation project pipeline layout, and the sum of the bias term to obtain a second intermediate term; The first intermediate term is divided by the second intermediate term to obtain the pipeline layout pixel granularity feature energy level coefficient.
6. The hotel installation project pipeline layout optimization method based on BIM technology according to claim 5 is characterized in that: Based on the characteristic energy level guiding pipeline distribution aggregation representation vector, generating the collision detection result includes: The characteristic energy level guided pipeline distribution aggregation representation vector is input into a classifier-based collision detector to obtain the collision detection result.
7. A hotel installation project pipeline layout optimization system based on BIM technology, characterized in that: include: The pipeline classification module is used to classify the hotel installation engineering pipelines based on usage requirements, wherein the functional pipelines are set as Class I pipelines, the supply pipelines are set as Class II pipelines, and the sewage pipelines are set as Class III pipelines; A modeling and marking module is used to perform three-dimensional modeling on the hotel installation engineering pipeline using IBM to obtain a three-dimensional model of the hotel installation engineering pipeline, and to perform color marking based on pipeline functions on the hotel installation engineering pipeline in the three-dimensional model of the hotel installation engineering pipeline; A collision analysis module, used for performing collision detection on the three-dimensional model of the hotel installation project pipeline to obtain a collision detection result, wherein the collision detection result is used to indicate whether there is a pipeline collision phenomenon; Wherein, the collision analysis module includes: Extract pipeline layout features based on the hotel installation project pipeline three-dimensional model to obtain a local layout feature map of the hotel installation project pipeline; Inputting the local layout feature map of the hotel installation project pipeline into a feature space structure-maintaining self-attention enhancement module based on cross-channel intersection to obtain a spatially significant feature map of the local layout of the hotel installation project pipeline; Performing pixel-level feature energy level correlation analysis on the spatially significant feature map of the local layout of the hotel installation project pipeline to obtain a feature energy level guided pipeline distribution aggregation representation vector; Based on the characteristic energy level, the pipeline distribution aggregation representation vector is guided to generate the collision detection result; The local layout feature map of the hotel installation project pipeline is input into a feature space structure-maintaining self-attention enhancement module based on cross-channel intersection to obtain a spatially significant feature map of the local layout of the hotel installation project pipeline, including: Performing layer normalization on the hotel installation project pipeline local layout feature map to obtain a normalized hotel installation project pipeline local layout feature map; Performing point convolution processing on the normalized hotel installation project pipeline local layout feature map to obtain a pipeline local layout channel context association representation feature map; Convolutionally encoding the pipeline local layout channel context association representation feature map to obtain a pipeline local layout space context association representation feature map; Copying the pipeline local layout space context association representation feature map to obtain a backup pipeline local layout space context association representation feature map; Reshaping the pipeline local layout channel context association representation feature map, the pipeline local layout space context association representation feature map and the backup pipeline local layout space context association representation feature map to obtain a pipeline local layout channel context association representation feature matrix, a pipeline local layout space context association representation feature matrix and a backup pipeline local layout space context association representation feature matrix; Calculating a cross-channel cross covariance matrix between the pipeline local layout channel context association representation feature matrix and the pipeline local layout spatial context association representation feature matrix; Using a Softmax function to activate the cross-channel cross covariance matrix to obtain a pipeline local layout feature global interaction attention matrix; Calculate the product of the backup pipeline local layout spatial context association representation feature matrix and the pipeline local layout feature global interaction attention matrix to obtain an attention-enhanced pipeline local layout feature representation matrix; The feature shape of the attention-enhanced pipeline local layout feature representation matrix is reshaped to obtain a spatially significant feature map of the hotel installation project pipeline local layout.
