A management method and system for high-rise building construction sites based on BIM technology
Through the progress dual twin detection network of BIM technology, the feature extraction and purification of real-time BIM models and reference models at high-rise building construction sites has been solved, and the construction progress monitoring problem has been achieved, real-time monitoring and deviation adjustment have been achieved to ensure that the project is completed on time.
Patent Information
- Application Number
- CN202410516506.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-28
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-04-28
AI Technical Summary
At high-rise building construction sites, it is difficult for existing technology to monitor construction progress in real time, resulting in difficult time to detect and adjust construction deviations in a timely manner, affecting the project completion time.
Using a management method based on BIM technology, the real-time BIM model and reference BIM model are featured through a progress dual twin detection network, and the similarity of the feature map is calculated to determine whether there is a deviation in the construction progress, and real-time monitoring and adjustment measures are provided.
Real-time monitoring of construction progress is achieved, deviations are discovered in a timely manner and corresponding measures are taken to ensure that the project is completed on time and improve construction efficiency and quality.
Smart Images

Figure CN118445882B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of building information modeling, and in particular to a management method and system for a high-rise building construction site based on BIM technology. Background Art
[0002] Building Information Modeling (BIM) is a digital building design and management tool that can create, manage and maintain building information throughout the building life cycle. With the support of Building Information Modeling (BIM) technology, high-rise building construction site management has entered a new stage of development. In the field of high-rise building construction, the application of BIM technology has become an important means to improve efficiency, reduce costs and ensure quality. BIM technology can not only provide a three-dimensional digital representation of the physical and functional characteristics of the building, but also realize real-time monitoring and analysis during the construction process, so as to timely discover deviations in the construction progress and take corresponding adjustment measures.
[0003] Therefore, a management solution for high-rise building construction sites based on BIM technology is desired. Summary of the invention
[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.
[0005] In a first aspect, the present disclosure provides a management method for a high-rise building construction site based on BIM technology, the method comprising:
[0006] Get real-time BIM models of high-rise building construction sites;
[0007] Extract the reference BIM model of the scheduled progress from the backend database;
[0008] The real-time BIM model and the reference BIM model are respectively subjected to feature extraction by a progress dual twin detection network to obtain a real-time progress BIM model feature graph and a reference BIM model feature graph;
[0009] The real-time progress BIM model feature graph and the reference BIM model feature graph are respectively passed through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph;
[0010] The similarity between the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph is calculated, and it is determined whether there is a deviation in the construction progress.
[0011] Optionally, the progress dual twin detection network includes a first three-dimensional convolutional neural network model and a second three-dimensional convolutional neural network model, wherein the first three-dimensional convolutional neural network model and the second three-dimensional convolutional neural network model have convolution kernels of different scales.
[0012] Optionally, the real-time progress BIM model feature graph and the reference BIM model feature graph are respectively passed through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph, including: the real-time progress BIM model feature graph is processed by the feature purifier based on the essential feature extraction network with the following feature purification formula to obtain the purified real-time progress BIM model feature graph; wherein the feature purification formula is:
[0013]
[0014]
[0015] Among them, v i (x) and v j (x) are respectively the time series reinforcement association feature vectors of the i-th and j-th ice-making machine operating parameters in the sequence of the real-time progress BIM model feature vectors obtained by quantizing the feature matrices along the channel dimension in the real-time progress BIM model feature graph, V k is the sequence of the real-time progress BIM model feature vectors, log represents the logarithmic function value with base 2, L is the length of each real-time progress BIM model feature vector, M is the number of vectors in the sequence of the real-time progress BIM model feature vectors - 1, D i is the eigenvalue of each position in the differential eigenvector of the real-time progress BIM model, N s is the length of the differentiated feature vector of the real-time progress BIM model, exp(·) is an exponential operation, and V is a purified real-time progress BIM model feature vector obtained by quantizing the feature matrices along the channel dimension in the purified real-time progress BIM model feature graph.
[0016] Optionally, the similarity between the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph is calculated, and whether there is a deviation in the construction progress is determined, including: calculating the hash similarity between the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph; and, based on the hash similarity, determining whether there is a deviation in the construction progress.
[0017] Optionally, calculating the hash similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph includes: optimizing the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph respectively to obtain an optimized purified real-time progress BIM model feature graph and an optimized purified reference BIM model feature graph; calculating the hash similarity between the optimized purified real-time progress BIM model feature graph and the optimized purified reference BIM model feature graph.
[0018] Optionally, the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph are optimized respectively to obtain an optimized purified real-time progress BIM model characteristic graph and an optimized purified reference BIM model characteristic graph, including: respectively calculating the weighting coefficients of the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph to obtain a first weighting coefficient and a second weighting coefficient; weighting the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph with the first weighting coefficient and the second weighting coefficient to optimize the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph to obtain the optimized purified real-time progress BIM model characteristic graph and the optimized purified reference BIM model characteristic graph.
[0019] Optionally, in response to the hash similarity being less than a predetermined threshold, it is determined that there is a deviation in the construction progress.
[0020] In a second aspect, the present disclosure provides a management system for a high-rise building construction site based on BIM technology, the system comprising:
[0021] Real-time BIM model acquisition module, used to obtain the real-time BIM model of the high-rise building construction site;
[0022] A reference BIM model acquisition module is used to extract a reference BIM model of a scheduled progress from a background database;
[0023] A progress dual twin detection module, used to extract features of the real-time BIM model and the reference BIM model respectively through a progress dual twin detection network to obtain a real-time progress BIM model feature graph and a reference BIM model feature graph;
[0024] A feature purification module, used for respectively passing the real-time progress BIM model feature graph and the reference BIM model feature graph through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph;
[0025] The similarity calculation module is used to calculate the similarity between the purified real-time progress BIM model characteristic diagram and the purified reference BIM model characteristic diagram, and determine whether there is a deviation in the construction progress.
[0026] Optionally, the progress dual twin detection network includes a first three-dimensional convolutional neural network model and a second three-dimensional convolutional neural network model, wherein the first three-dimensional convolutional neural network model and the second three-dimensional convolutional neural network model have convolution kernels of different scales.
[0027] Optionally, the feature purification module is used to: process the real-time progress BIM model feature graph through the feature purifier based on the essential feature extraction network with the following feature purification formula to obtain the purified real-time progress BIM model feature graph; wherein the feature purification formula is:
[0028]
[0029]
[0030] Among them, v i (x) and v j (x) are respectively the time series reinforcement association feature vectors of the i-th and j-th ice-making machine operating parameters in the sequence of the real-time progress BIM model feature vectors obtained by quantizing the feature matrices along the channel dimension in the real-time progress BIM model feature graph, V k is the sequence of the real-time progress BIM model feature vectors, log represents a logarithmic function with base 2, L is the length of each of the real-time progress BIM model feature vectors, M is the number of vectors in the sequence of the real-time progress BIM model feature vectors - 1, D i is the eigenvalue of each position in the differential eigenvector of the real-time progress BIM model, N s is the length of the differentiated feature vector of the real-time progress BIM model, exp(·) is an exponential operation, and V is a purified real-time progress BIM model feature vector obtained by quantizing the feature matrices along the channel dimension in the purified real-time progress BIM model feature graph.
[0031] By adopting the above technical scheme, the real-time BIM model obtained from the construction site of the high-rise building and the reference BIM model extracted from the background database are respectively feature extracted through the progress double twin detection network to obtain the real-time progress BIM model feature graph and the reference BIM model feature graph; the real-time progress BIM model feature graph and the reference BIM model feature graph are respectively passed through the feature purifier based on the essential feature extraction network to obtain the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph; the similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph is calculated, and it is determined whether there is a deviation in the construction progress. In this way, the project management team can monitor the construction progress in real time, which helps to timely discover the deviation of the construction progress and take corresponding measures to adjust it to ensure that the project is completed on time.
[0032] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:
[0034] Figure 1 The present invention is a flowchart of a method for managing a high-rise building construction site based on BIM technology according to an exemplary embodiment.
[0035] Figure 2 It is a block diagram of a management system for a high-rise building construction site based on BIM technology according to an exemplary embodiment.
[0036] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.
[0037] Figure 4 It is an application scenario diagram of a management method for a high-rise building construction site based on BIM technology according to an exemplary embodiment. DETAILED DESCRIPTION
[0038] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0039] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.
[0040] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.
[0041] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0042] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0043] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0044] First of all, it should be understood that real-time monitoring of construction progress is a crucial part of high-rise building construction management. Specifically, in the process of real-time monitoring of construction progress, the technical concept of this application is that by analyzing and comparing the real-time BIM model with the reference BIM model of the predetermined progress, the project management team can monitor the construction progress in real time, thereby helping to timely discover construction progress deviations and take corresponding measures to make adjustments to ensure that the project is completed on time.
[0045] In order to solve the above problems, the present disclosure provides a management method and system for a high-rise building construction site based on BIM technology, which uses a progress dual twin detection network to extract features from the real-time BIM model obtained from the high-rise building construction site and the reference BIM model extracted from the background database to obtain a real-time progress BIM model feature graph and a reference BIM model feature graph; the real-time progress BIM model feature graph and the reference BIM model feature graph are respectively passed through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph; the similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph is calculated, and it is determined whether there is a deviation in the construction progress. In this way, the project management team can monitor the construction progress in real time, which helps to timely discover the deviation in the construction progress and take corresponding measures to adjust it to ensure that the project is completed on time.
[0046] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
[0047] Figure 1 is a flow chart of a management method for a high-rise building construction site based on BIM technology according to an exemplary embodiment. Figure 1 As shown, the method includes:
[0048] Step 101: Obtain a real-time BIM model of a high-rise building construction site;
[0049] Step 102: extracting a reference BIM model of a scheduled progress from a backend database;
[0050] Step 103: extracting features of the real-time BIM model and the reference BIM model respectively through a progress dual twin detection network to obtain a real-time progress BIM model feature graph and a reference BIM model feature graph;
[0051] Step 104: The real-time progress BIM model feature graph and the reference BIM model feature graph are respectively passed through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph;
[0052] Step 105: Calculate the similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph, and determine whether there is a deviation in the construction progress.
[0053] Among them, the progress dual twin detection network includes a first three-dimensional convolutional neural network model and a second three-dimensional convolutional neural network model, wherein the first three-dimensional convolutional neural network model and the second three-dimensional convolutional neural network model have convolution kernels of different scales.
[0054] Specifically, in the technical solution of the present application, first, a real-time BIM model of a high-rise building construction site is obtained, and a reference BIM model of a predetermined progress is extracted from a background database. Next, considering that both the real-time BIM model and the reference BIM model are three-dimensional models, and a three-dimensional convolutional neural network is a neural network model specifically used to process three-dimensional data, it can extract effective feature information from three-dimensional data. In particular, it is also considered that in the process of monitoring the construction progress by extracting the features of the BIM model, whether it is a real-time BIM model or a reference BIM model, there are feature information of different scales and levels about the semantics of the construction progress. Therefore, in order to be able to more fully and accurately extract representative construction semantic features from the real-time BIM model and the reference BIM model, respectively, in the technical solution of the present application, the real-time BIM model and the reference BIM model need to be passed through a progress dual twin detection network including a first three-dimensional convolutional neural network model and a second three-dimensional convolutional neural network model to obtain a real-time progress BIM model feature map and a reference BIM model feature map. Here, the first three-dimensional convolutional neural network model and the second three-dimensional convolutional neural network model have convolution kernels of different scales, which are used to capture important feature information such as the geometric shape, spatial relationship and construction progress semantic information of the high-rise building in the BIM model.
[0055] Furthermore, considering that there are many noises and interference features unrelated to the construction progress in the real-time progress BIM model feature graph and the reference BIM model feature graph, this may affect the subsequent analysis and judgment. Therefore, in order to remove the noise and irrelevant information in the feature graph, thereby extracting more essential and robust construction semantic features, so as to more accurately judge whether there is a deviation in the construction progress, in the technical solution of the present application, the real-time progress BIM model feature graph and the reference BIM model feature graph are further passed through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph. It should be understood that the feature purifier based on the essential feature extraction network can remove redundant information and enhance the characterization ability of the features by learning the essential features between different aspects of the features in the BIM model feature graph. The purified real-time progress BIM model feature graph and the purified reference BIM model feature graph after such processing can more accurately reflect the actual characteristics and progress of the building, and help managers to find deviations in time and take corresponding measures.
[0056] In one embodiment of the present disclosure, the real-time progress BIM model feature graph and the reference BIM model feature graph are respectively processed by a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph, including: processing the real-time progress BIM model feature graph by the feature purifier based on the essential feature extraction network with the following feature purification formula to obtain the purified real-time progress BIM model feature graph; wherein the feature purification formula is:
[0057]
[0058]
[0059] Among them, v i (x) and v j (x) are respectively the time series reinforcement association feature vectors of the i-th and j-th ice-making machine operating parameters in the sequence of the real-time progress BIM model feature vectors obtained by quantizing the feature matrices along the channel dimension in the real-time progress BIM model feature graph, V k is the sequence of the real-time progress BIM model feature vectors, log represents the logarithmic function value with base 2, L is the length of each real-time progress BIM model feature vector, M is the number of vectors in the sequence of the real-time progress BIM model feature vectors - 1, D i is the eigenvalue of each position in the differential eigenvector of the real-time progress BIM model, N s is the length of the differentiated feature vector of the real-time progress BIM model, exp(·) is an exponential operation, and V is a purified real-time progress BIM model feature vector obtained by quantizing the feature matrices along the channel dimension in the purified real-time progress BIM model feature graph.
[0060] In one embodiment of the present disclosure, the similarity between the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph is calculated, and it is determined whether there is a deviation in the construction progress, including: calculating the hash similarity between the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph; and, based on the hash similarity, determining whether there is a deviation in the construction progress.
[0061] Then, in order to quantify the semantic similarity between the real-time progress BIM model and the reference BIM model, so as to determine whether there is a deviation in the construction progress, in the technical solution of the present application, the hash similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph is further calculated. By calculating the hash similarity between the real-time progress and the reference BIM model features, the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph can be embedded and mapped into the hash space, and the hash semantic similarity between the two can be captured.
[0062] In one embodiment of the present disclosure, the hash similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph is calculated, including: optimizing the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph respectively to obtain an optimized purified real-time progress BIM model feature graph and an optimized purified reference BIM model feature graph; and calculating the hash similarity between the optimized purified real-time progress BIM model feature graph and the optimized purified reference BIM model feature graph.
[0063] Furthermore, the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph are optimized respectively to obtain an optimized purified real-time progress BIM model characteristic graph and an optimized purified reference BIM model characteristic graph, including: respectively calculating the weighting coefficients of the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph to obtain a first weighting coefficient and a second weighting coefficient; weighting the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph with the first weighting coefficient and the second weighting coefficient to optimize the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph to obtain the optimized purified real-time progress BIM model characteristic graph and the optimized purified reference BIM model characteristic graph.
[0064] By calculating the similarity between the two BIM models in the hash space, the similarity between the feature graphs of the two BIM models can be quickly and efficiently evaluated. If the hash similarity is high, it means that the two feature graphs have a high similarity in the feature space, that is, the real-time progress is consistent with the scheduled progress, and the construction progress is normal. On the contrary, if the hash similarity is low, it means that there is a large difference between the two feature graphs, which may mean that there is a deviation or problem in the construction progress. Then, based on the hash similarity, it is determined whether there is a deviation in the construction progress. That is, in response to the hash similarity being less than a predetermined threshold, it is determined that there is a deviation in the construction progress. In this way, the construction progress deviation can be more accurately and timely discovered based on the hash similarity between the real-time BIM model and the reference BIM model of the scheduled progress, and corresponding measures can be taken to make adjustments to ensure that the project is completed on time.
[0065] In one embodiment of the present disclosure, in response to the hash similarity being less than a predetermined threshold, it is determined that there is a deviation in the construction progress.
[0066] In the above technical solution, in the above technical solution, considering the difference in the semantic space distribution of the source model between the real-time BIM model of the high-rise building construction site and the reference BIM model, this difference exists not only in the substantial content part but also in the difference in content expression form and BIM model noise level, so that the real-time progress BIM model feature graph obtained by the twin feature extraction of the progress double twin detection network including the first three-dimensional convolutional neural network model and the second three-dimensional convolutional neural network model and the reference BIM model feature graph will have inconsistent image semantic feature distribution in the spatial distribution dimension. After the real-time progress BIM model feature graph and the reference BIM model feature graph are respectively passed through the feature purifier based on the essential feature extraction network, the inconsistency of the image semantic feature distribution between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph will be further amplified, that is, there is a semantic feature expression distinction between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph, thereby affecting the calculation accuracy of the hash similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph.
[0067] In this way, when calculating the hash similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph, and thereby mapping the hash similarity probability space of the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph respectively, it is expected to improve the probability mapping certainty of the distinguishable feature distributions of the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph, so as to improve the calculation accuracy of the hash similarity. Based on this, the present application first calculates the weighting coefficients of the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph respectively. Specifically, the weighting coefficients of the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph are calculated respectively using the following coefficient calculation formula to obtain the first weighting coefficient and the second weighting coefficient; wherein, the coefficient calculation formula is:
[0068]
[0069]
[0070] Among them, f 1-max and f 2-max are the maximum eigenvalues of the purified real-time progress BIM model feature graph F1 and the purified reference BIM model feature graph F2, respectively, 1-j and f 2-j is the eigenvalue of the j-th position of the purified real-time progress BIM model feature graph F1 and the purified reference BIM model feature graph F2, N is the scale of the feature graph, log represents the logarithm with base 2, and α is the weight hyperparameter, ω1 and ω2 are the first weighting coefficient and the second weighting coefficient respectively.
[0071] Specifically, the image semantic features of the purified real-time progress BIM model feature graph F1 and the purified reference BIM model feature graph F2 are respectively represented by majority voting in the form of text semantic crowdsourcing. A voting) mechanism is used to seek the maximization of the individual information expectation of each feature vector under the distribution subordinate probability model of the purified real-time progress BIM model feature graph F1 and the purified reference BIM model feature graph F2 relative to the hash similarity probability space. In this way, the purified real-time progress BIM model feature graph F1 and the purified reference BIM model feature graph F2 are weighted by the first weighting coefficient ω1 and the second weighting coefficient ω2 to optimize the purified real-time progress BIM model feature graph F1 and the purified reference BIM model feature graph F2. Based on the average information confidence of the eigenvalues of the purified real-time progress BIM model feature graph F1 and the purified reference BIM model feature graph F2, a joint distribution estimation relative to the hash similarity probability space can be performed, so as to improve the certainty of the probability mapping to the hash similarity probability space while maintaining the distinguishability of the feature distribution of the purified real-time progress BIM model feature graph F1 and the purified reference BIM model feature graph F2, so as to improve the calculation accuracy of the hash similarity. In this way, construction progress deviations can be discovered more accurately and timely based on the hash comparison between the real-time BIM model and the reference BIM model of the scheduled progress, so that corresponding measures can be taken to make adjustments to ensure that the project is completed on time.
[0072] In summary, by adopting the above scheme, by analyzing and comparing the real-time BIM model with the reference BIM model of the scheduled progress, the project management team can monitor the construction progress in real time, which helps to promptly detect construction progress deviations and take corresponding measures to make adjustments to ensure that the project is completed on time.
[0073] Figure 2 FIG. 1 is a block diagram of a management system for a high-rise building construction site based on BIM technology according to an exemplary embodiment. Figure 2 As shown, the management system 200 includes:
[0074] A real-time BIM model acquisition module 201 is used to acquire a real-time BIM model of a high-rise building construction site;
[0075] A reference BIM model acquisition module 202 is used to extract a reference BIM model of a predetermined schedule from a background database;
[0076] A progress dual twin detection module 203 is used to extract features of the real-time BIM model and the reference BIM model through a progress dual twin detection network to obtain a real-time progress BIM model feature graph and a reference BIM model feature graph;
[0077] A feature purification module 204 is used to pass the real-time progress BIM model feature graph and the reference BIM model feature graph through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph;
[0078] The similarity calculation module 205 is used to calculate the similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph, and determine whether there is a deviation in the construction progress.
[0079] Optionally, the progress dual twin detection network includes a first three-dimensional convolutional neural network model and a second three-dimensional convolutional neural network model, wherein the first three-dimensional convolutional neural network model and the second three-dimensional convolutional neural network model have convolution kernels of different scales.
[0080] Optionally, the feature purification module is used to: process the real-time progress BIM model feature graph through the feature purifier based on the essential feature extraction network with the following feature purification formula to obtain the purified real-time progress BIM model feature graph; wherein the feature purification formula is:
[0081]
[0082]
[0083] Among them, v i (x) and v j (x) are respectively the time series reinforcement association feature vectors of the i-th and j-th ice-making machine operating parameters in the sequence of the real-time progress BIM model feature vectors obtained by quantizing the feature matrices along the channel dimension in the real-time progress BIM model feature graph, V k is the sequence of the real-time progress BIM model feature vectors, log represents a logarithmic function with base 2, L is the length of each of the real-time progress BIM model feature vectors, M is the number of vectors in the sequence of the real-time progress BIM model feature vectors - 1, D i is the eigenvalue of each position in the differential eigenvector of the real-time progress BIM model, N s is the length of the differentiated feature vector of the real-time progress BIM model, exp(·) is an exponential operation, and V is a purified real-time progress BIM model feature vector obtained by quantizing the feature matrices along the channel dimension in the purified real-time progress BIM model feature graph.
[0084] Reference below Figure 3, which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0085] like Figure 3 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0086] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.
[0087] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
[0088] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0089] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0090] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0091] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0092] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0093] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device".
[0094] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.
[0095] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0096] According to one or more embodiments of the present disclosure, Example 1 provides a management method for a high-rise building construction site based on BIM technology, the method comprising:
[0097] Get real-time BIM models of high-rise building construction sites;
[0098] Extract the reference BIM model of the scheduled progress from the backend database;
[0099] The real-time BIM model and the reference BIM model are respectively subjected to feature extraction by a progress dual twin detection network to obtain a real-time progress BIM model feature graph and a reference BIM model feature graph;
[0100] The real-time progress BIM model feature graph and the reference BIM model feature graph are respectively passed through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph;
[0101] The similarity between the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph is calculated, and it is determined whether there is a deviation in the construction progress.
[0102] According to one or more embodiments of the present disclosure, Example 2 provides the method of Example 1, wherein the progress dual twin detection network includes a first three-dimensional convolutional neural network model and a second three-dimensional convolutional neural network model, wherein the first three-dimensional convolutional neural network model and the second three-dimensional convolutional neural network model have convolution kernels of different scales.
[0103] According to one or more embodiments of the present disclosure, Example 3 provides the method of Example 2, wherein the real-time progress BIM model feature graph and the reference BIM model feature graph are respectively passed through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph, including: passing the real-time progress BIM model feature graph through the feature purifier based on the essential feature extraction network to process the feature purifier with the following feature purification formula to obtain the purified real-time progress BIM model feature graph;
[0104] Wherein, the characteristic purification formula is:
[0105]
[0106]
[0107] Among them, v i (x) and v j (x) are respectively the time series reinforcement association feature vectors of the i-th and j-th ice-making machine operating parameters in the sequence of the real-time progress BIM model feature vectors obtained by quantizing the feature matrices along the channel dimension in the real-time progress BIM model feature graph, V k is the sequence of the real-time progress BIM model feature vectors, log represents the logarithmic function value with base 2, L is the length of each real-time progress BIM model feature vector, M is the number of vectors in the sequence of the real-time progress BIM model feature vectors - 1, D i is the eigenvalue of each position in the differential eigenvector of the real-time progress BIM model, N s is the length of the differentiated feature vector of the real-time progress BIM model, exp(·) is an exponential operation, and V is a purified real-time progress BIM model feature vector obtained by quantizing the feature matrices along the channel dimension in the purified real-time progress BIM model feature graph.
[0108] According to one or more embodiments of the present disclosure, Example 4 provides the method of Example 3, calculating the similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph, and determining whether there is a deviation in the construction progress, including:
[0109] Calculating the hash similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph; and
[0110] Based on the hash similarity, determine whether there is a deviation in the construction progress.
[0111] According to one or more embodiments of the present disclosure, Example 5 provides the method of Example 4, calculating the hash similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph, including:
[0112] The purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph are respectively optimized to obtain an optimized purified real-time progress BIM model characteristic graph and an optimized purified reference BIM model characteristic graph;
[0113] Calculate the hash similarity between the optimized purified real-time progress BIM model feature graph and the optimized purified reference BIM model feature graph.
[0114] According to one or more embodiments of the present disclosure, Example 6 provides the method of Example 5, wherein the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph are optimized respectively to obtain an optimized purified real-time progress BIM model feature graph and an optimized purified reference BIM model feature graph, including:
[0115] Respectively calculating weighting coefficients of the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph to obtain a first weighting coefficient and a second weighting coefficient;
[0116] The purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph are weighted by the first weighting coefficient and the second weighting coefficient to optimize the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph to obtain the optimized purified real-time progress BIM model characteristic graph and the optimized purified reference BIM model characteristic graph.
[0117] According to one or more embodiments of the present disclosure, Example 7 provides the method of Example 6, and in response to the hash similarity being less than a predetermined threshold, it is determined that there is a deviation in the construction progress.
[0118] According to one or more embodiments of the present disclosure, Example 8 provides a management system for a high-rise building construction site based on BIM technology, the system comprising:
[0119] Real-time BIM model acquisition module, used to obtain the real-time BIM model of the high-rise building construction site;
[0120] A reference BIM model acquisition module is used to extract a reference BIM model of a scheduled progress from a background database;
[0121] A progress dual twin detection module, used to extract features of the real-time BIM model and the reference BIM model respectively through a progress dual twin detection network to obtain a real-time progress BIM model feature graph and a reference BIM model feature graph;
[0122] A feature purification module, used for respectively passing the real-time progress BIM model feature graph and the reference BIM model feature graph through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph;
[0123] The similarity calculation module is used to calculate the similarity between the purified real-time progress BIM model characteristic diagram and the purified reference BIM model characteristic diagram, and determine whether there is a deviation in the construction progress.
[0124] According to one or more embodiments of the present disclosure, Example 9 provides the method of Example 8, wherein the progress dual twin detection network includes a first three-dimensional convolutional neural network model and a second three-dimensional convolutional neural network model, wherein the first three-dimensional convolutional neural network model and the second three-dimensional convolutional neural network model have convolution kernels of different scales.
[0125] According to one or more embodiments of the present disclosure, Example 10 provides the method of Example 9, wherein the feature purification module is used to: process the real-time progress BIM model feature graph through the feature purifier based on the essential feature extraction network with the following feature purification formula to obtain the purified real-time progress BIM model feature graph;
[0126] Wherein, the characteristic purification formula is:
[0127]
[0128]
[0129] Among them, v i (x) and v j (x) are respectively the time series reinforcement association feature vectors of the i-th and j-th ice-making machine operating parameters in the sequence of the real-time progress BIM model feature vectors obtained by quantizing the feature matrices along the channel dimension in the real-time progress BIM model feature graph, V k is the sequence of the real-time progress BIM model feature vectors, log represents a logarithmic function with base 2, L is the length of each of the real-time progress BIM model feature vectors, M is the number of vectors in the sequence of the real-time progress BIM model feature vectors - 1, D i is the eigenvalue of each position in the differential eigenvector of the real-time progress BIM model, N sis the length of the differentiated feature vector of the real-time progress BIM model, exp(·) is an exponential operation, and V is a purified real-time progress BIM model feature vector obtained by quantizing the feature matrices along the channel dimension in the purified real-time progress BIM model feature graph.
[0130] Figure 4 FIG. 1 is an application scenario diagram of a method for managing a high-rise building construction site based on BIM technology according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, a real-time BIM model of a high-rise building construction site is obtained (for example, Figure 4 C1 shown in FIG); extracting a reference BIM model of the scheduled progress from the backend database (e.g., Figure 4 Then, the acquired real-time BIM model and the reference BIM model are input to a server (for example, Figure 4 In S) shown in , the server is capable of processing the real-time BIM model and the reference BIM model based on the management algorithm of the high-rise building construction site based on BIM technology to determine whether there is a deviation in the construction progress.
[0131] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.
[0132] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.
[0133] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Claims
1. A management method for a high-rise building construction site based on BIM technology, characterized in that: include: Get real-time BIM models of high-rise building construction sites; Extract the reference BIM model of the scheduled progress from the backend database; The real-time BIM model and the reference BIM model are respectively subjected to feature extraction by a progress dual twin detection network to obtain a real-time progress BIM model feature graph and a reference BIM model feature graph; The real-time progress BIM model feature graph and the reference BIM model feature graph are respectively passed through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph; Calculating the similarity between the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph, and determining whether there is a deviation in the construction progress; The real-time progress BIM model feature graph and the reference BIM model feature graph are respectively passed through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph, including: the real-time progress BIM model feature graph is processed by the feature purifier based on the essential feature extraction network with the following feature purification formula to obtain the purified real-time progress BIM model feature graph; Wherein, the characteristic purification formula is: Among them, v i (x) and v j (x) are respectively the time series reinforcement association feature vectors of the i-th and j-th ice-making machine operating parameters in the sequence of the real-time progress BIM model feature vectors obtained by quantizing the feature matrices along the channel dimension in the real-time progress BIM model feature graph, V k is the sequence of the real-time progress BIM model feature vectors, log represents the logarithmic function value with base 2, L is the length of each real-time progress BIM model feature vector, M is the number of vectors in the sequence of the real-time progress BIM model feature vectors - 1, D i is the eigenvalue of each position in the differential eigenvector of the real-time progress BIM model, N s is the length of the differentiated feature vector of the real-time progress BIM model, exp(·) is an exponential operation, and V is a purified real-time progress BIM model feature vector obtained by quantizing the feature matrices along the channel dimension in the purified real-time progress BIM model feature graph.
2. The management method of high-rise building construction site based on BIM technology according to claim 1 is characterized in that: The progress dual twin detection network includes a first three-dimensional convolutional neural network model and a second three-dimensional convolutional neural network model, wherein the first three-dimensional convolutional neural network model and the second three-dimensional convolutional neural network model have convolution kernels of different scales.
3. The management method of high-rise building construction site based on BIM technology according to claim 2 is characterized in that: Calculating the similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph, and determining whether there is a deviation in the construction progress, including: Calculating the hash similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph; and Based on the hash similarity, determine whether there is a deviation in the construction progress.
4. The method for managing a high-rise building construction site based on BIM technology according to claim 3 is characterized in that: Calculating the hash similarity between the purified real-time progress BIM model feature graph and the purified reference BIM model feature graph includes: The purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph are respectively optimized to obtain an optimized purified real-time progress BIM model characteristic graph and an optimized purified reference BIM model characteristic graph; Calculate the hash similarity between the optimized purified real-time progress BIM model feature graph and the optimized purified reference BIM model feature graph.
5. The method for managing a high-rise building construction site based on BIM technology according to claim 4 is characterized in that: The purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph are respectively optimized to obtain an optimized purified real-time progress BIM model characteristic graph and an optimized purified reference BIM model characteristic graph, including: Respectively calculating weighting coefficients of the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph to obtain a first weighting coefficient and a second weighting coefficient; The purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph are weighted by the first weighting coefficient and the second weighting coefficient to optimize the purified real-time progress BIM model characteristic graph and the purified reference BIM model characteristic graph to obtain the optimized purified real-time progress BIM model characteristic graph and the optimized purified reference BIM model characteristic graph.
6. The method for managing a high-rise building construction site based on BIM technology according to claim 5 is characterized in that: In response to the hash similarity being less than a predetermined threshold, it is determined that there is a deviation in the construction progress.
7. A management system for a high-rise building construction site based on BIM technology, characterized in that: include: Real-time BIM model acquisition module, used to obtain the real-time BIM model of the high-rise building construction site; A reference BIM model acquisition module is used to extract a reference BIM model of a scheduled progress from a background database; A progress dual twin detection module, used to extract features of the real-time BIM model and the reference BIM model respectively through a progress dual twin detection network to obtain a real-time progress BIM model feature graph and a reference BIM model feature graph; A feature purification module, used for respectively passing the real-time progress BIM model feature graph and the reference BIM model feature graph through a feature purifier based on an essential feature extraction network to obtain a purified real-time progress BIM model feature graph and a purified reference BIM model feature graph; A similarity calculation module is used to calculate the similarity between the purified real-time progress BIM model characteristic diagram and the purified reference BIM model characteristic diagram, and determine whether there is a deviation in the construction progress; Wherein, the feature purification module is used to: process the real-time progress BIM model feature graph through the feature purifier based on the essential feature extraction network with the following feature purification formula to obtain the purified real-time progress BIM model feature graph; Wherein, the characteristic purification formula is: Among them, v i (x) and v j (x) are respectively the time series reinforcement association feature vectors of the i-th and j-th ice-making machine operating parameters in the sequence of the real-time progress BIM model feature vectors obtained by quantizing the feature matrices along the channel dimension in the real-time progress BIM model feature graph, V k is the sequence of the real-time progress BIM model feature vectors, log represents a logarithmic function with base 2, L is the length of each of the real-time progress BIM model feature vectors, M is the number of vectors in the sequence of the real-time progress BIM model feature vectors - 1, D i is the eigenvalue of each position in the differential eigenvector of the real-time progress BIM model, N s is the length of the differentiated feature vector of the real-time progress BIM model, exp(·) is an exponential operation, and V is a purified real-time progress BIM model feature vector obtained by quantizing the feature matrices along the channel dimension in the purified real-time progress BIM model feature graph.
8. The management system for high-rise building construction sites based on BIM technology according to claim 7 is characterized in that: The progress dual twin detection network includes a first three-dimensional convolutional neural network model and a second three-dimensional convolutional neural network model, wherein the first three-dimensional convolutional neural network model and the second three-dimensional convolutional neural network model have convolution kernels of different scales.
