Method and device for creating and rendering standardized three-dimensional field layout models for enterprises

Abstract

The present application provides a method and device for creating and rendering standardized three-dimensional field layout models of an enterprise, and the method includes: obtaining a CAD site plan layout; using modeling software, inserting the enterprise's standard family library into a specified position in the CAD site plan layout to obtain a field layout model; adding an environmental landscape model to the field layout model through a plug-in to obtain a two-dimensional panoramic view; rendering the two-dimensional panoramic view to obtain a three-dimensional panoramic view; and displaying the three-dimensional panoramic view through BIM software. According to the pre-built simulated construction site layout, a series of processing is performed on the CAD site plan layout to obtain a two-dimensional panoramic view that can truly reflect the on-site situation. By rendering the two-dimensional panoramic view, a three-dimensional rendering effect diagram can be directly rendered without manual drawing, which not only saves labor costs, but also improves drawing efficiency. By using the enterprise's standard family library, it is possible to save a lot of modeling time when establishing the field layout model, and the model results are more standardized.

Description

Technical Field

[0001] The present application relates to the field of engineering technology, and in particular to a method and device for creating and rendering a standardized three-dimensional field model for an enterprise. Background Art

[0002] In the engineering field, for a certain project or project, the CAD site layout drawing is an indispensable construction reference drawing for the project or project. However, in addition to the CAD site layout, companies usually also need a 3D rendering of the project or project after completion to facilitate promotion and application.

[0003] However, current renderings usually need to be drawn manually, which is labor-intensive, time-consuming and labor-intensive. Summary of the invention

[0004] The embodiment of the present application provides a method and device for creating an enterprise standardized three-dimensional field layout model and rendering effects, so as to achieve low-cost and efficient drawing of three-dimensional rendering effect diagrams.

[0005] In order to achieve the above purpose, this application adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for creating and rendering a standardized three-dimensional site layout model of an enterprise, the method comprising: obtaining a CAD site plan layout; using modeling software, placing the enterprise's standard family library at a designated location in the CAD site plan layout to obtain a site layout model; adding an environmental landscape model to the site layout model through a plug-in to obtain a two-dimensional panoramic view; rendering the two-dimensional panoramic view to obtain a three-dimensional panoramic view; and displaying the three-dimensional panoramic view through BIM software.

[0007] Based on the method of the first aspect, it can be known that according to the pre-built simulated construction site layout, a series of processing is performed on the CAD site plan layout to obtain a two-dimensional panoramic view that can truly reflect the on-site situation. By rendering the two-dimensional panoramic view, a three-dimensional panoramic view, that is, a three-dimensional rendering effect map, can be directly obtained without manual drawing, which not only saves labor costs, but also greatly improves the drawing efficiency of the three-dimensional rendering effect map. In addition, in the above series of processing, by using the company's standard family library, it can save a lot of modeling time when establishing the on-site layout model, and the model results are more standardized.

[0008] In a possible design scheme, the elements in the CAD site plan include at least one of the following: temporary buildings, main body outlines, tower cranes, construction elevators, site roads, or various material processing plants and yards; the elements in the standard family library include at least one of the following: gates, walls, standardized protection, various processing sheds, dormitories, canteens, offices, conference rooms, activity rooms, toilets, basketball courts, or corporate logos and signs; the elements in the environmental landscape model include at least one of the following: flowers, trees, people, or cars.

[0009] In a possible design scheme, the rendering of the two-dimensional panoramic image to obtain a three-dimensional panoramic image includes: using an unsupervised neural network model to perform clustering processing on the two-dimensional panoramic image to obtain N types of two-dimensional feature vector sets, the two-dimensional panoramic image includes N elements, and the i-th type of two-dimensional feature vector set is the feature vector set of the i-th element of the N elements in the two-dimensional plane, N is an integer greater than 1, and i is an arbitrary integer from 1 to N; using a feature reconstruction neural network model to perform dimensionality upgrading processing on the i-th type of two-dimensional feature vector set to obtain the i-th type of three-dimensional feature vector set, the i-th type of three-dimensional feature vector set is the feature vector set of the i-th element in three-dimensional space; and constructing a three-dimensional panoramic image based on the i-th type of three-dimensional feature vector set.

[0010] It can be understood that by clustering the two-dimensional panorama using an unsupervised neural network model, the two-dimensional features of each element in the two-dimensional panorama can be extracted, that is, a set of two-dimensional feature vectors. In this way, by using the two-dimensional features of each element of the feature reconstruction neural network model to upgrade the dimension, the three-dimensional features of each element can be obtained, that is, a set of three-dimensional feature vectors, so that a three-dimensional model, that is, a three-dimensional panorama, can be constructed based on the three-dimensional features of the elements, so that through unsupervised learning, a three-dimensional model can be constructed based on a two-dimensional image, thereby realizing how to apply unsupervised learning to more fields.

[0011] In a possible design scheme, the unsupervised neural network model includes a feature extraction layer and a feature classification layer, and the unsupervised neural network model is used to perform clustering processing on the two-dimensional panoramic image to obtain a set of N two-dimensional feature vectors, including: using the feature extraction layer of the unsupervised neural network model to perform convolution and pooling processing on the two-dimensional panoramic image to obtain a two-dimensional feature sequence of the two-dimensional panoramic image; using the feature classification layer of the unsupervised neural network model to perform clustering processing on the two-dimensional feature sequence to obtain a set of N two-dimensional feature vectors. In this way, by dividing the unsupervised neural network model into a feature extraction layer and a feature classification layer, decoupling is achieved, which facilitates updating or upgrading the model.

[0012] In a possible design, the feature classification layer includes M classifiers, M is an integer greater than N, and the feature classification layer of the unsupervised neural network model is used to cluster the two-dimensional feature sequence to obtain a set of N types of two-dimensional feature vectors, including: using each classifier in the M classifiers to cluster the two-dimensional feature sequence to obtain N types of two-dimensional feature vectors, wherein N classifiers in the M classifiers each output a corresponding type of two-dimensional feature vector, and the other MN classifiers in the M classifiers do not output a two-dimensional feature vector. It can be seen that the M classifiers are set for the type of element, and the two-dimensional features of each element can be extracted by a special classifier, so that the accuracy of feature extraction can be improved to improve the accuracy of building a three-dimensional model.

[0013] In a possible design scheme, the i-th classifier among N classifiers outputs the i-th type of two-dimensional feature vector, and the i-th classifier outputs the i-th type of two-dimensional feature vector means that the i-th classifier processes the two-dimensional feature sequence to obtain multiple two-dimensional feature vectors clustered in the feature space and multiple two-dimensional feature vectors discrete in the feature space, and the i-th classifier determines the multiple two-dimensional feature vectors clustered in the feature space as the i-th type of two-dimensional feature vector. It can be seen that the classifier can cluster features by their positions in the feature space, so that a class of features can be extracted more accurately.

[0014] In a possible design, the feature classification layer includes M classifiers, M is an integer greater than N, and the M classifiers classify two types of classifiers, one type of classifier includes N main classifiers, and the other type of classifier includes MN auxiliary classifiers, each auxiliary classifier is intertwined with the N auxiliary classifiers, and the feature classification layer of the unsupervised neural network model is used to cluster the two-dimensional feature sequence to obtain a set of N types of two-dimensional feature vectors, including: clustering the two-dimensional feature sequence using the i-th main classifier and the MN auxiliary classifiers intertwined with the main classifier to obtain the i-th two-dimensional feature vector. In other words, the classification of each main classifier can be assisted by all auxiliary classifiers to further improve the accuracy of feature extraction.

[0015] In a possible design scheme, each auxiliary classifier is interwoven with N auxiliary classifiers, which means: the classification neural network of each auxiliary classifier is coupled with the classification neural network of each of the N auxiliary classifiers, the i-th main classifier performs clustering processing on the two-dimensional feature sequence to obtain the first clustered feature and the first discrete feature, the first clustered feature refers to multiple two-dimensional feature vectors clustered in the feature space, the first discrete feature refers to multiple two-dimensional feature vectors discrete in the feature space, MN auxiliary classifiers perform clustering processing on the first clustered feature and the first discrete feature to obtain the second clustered feature from the first clustered feature, and the third clustered feature from the first discrete feature, the second clustered feature and the third clustered feature both refer to multiple two-dimensional feature vectors clustered in the feature space, and the second clustered feature and the third clustered feature obtain the i-th two-dimensional feature vector. It can be seen that the auxiliary classifier can check and fill in the gaps in the feature extraction results of the main classifier to ensure the accuracy of feature extraction.

[0016] In a possible design scheme, the i-th two-dimensional feature vector set is processed by using a feature reconstruction neural network model to increase the dimension, and obtain the i-th three-dimensional feature vector set, including: using the feature reconstruction neural network model to analyze the i-th two-dimensional feature vector set to derive the i-th third-dimensional feature vector set of the i-th element, wherein the i-th three-dimensional feature vector set includes the i-th two-dimensional feature vector set and the i-th third-dimensional feature vector set, the i-th two-dimensional feature vector set is specifically the feature vector set of the i-th element on the x-axis and y-axis, and the i-th third-dimensional feature vector set is specifically the feature vector set of the i-th element on the z-axis. It can be seen that the dimension-upgrading processing of the feature is not to reconstruct the feature, but to supplement the third-dimensional feature on the basis of the two-dimensional feature, which can improve the processing efficiency and reduce the computing overhead.

[0017] In a possible design, the feature reconstruction neural network model includes S feature derivation layers, S is an integer greater than 1, and the sth feature derivation layer among the S feature derivation layers is used to derive a partial third-dimensional feature vector set based on the input parameters, and output the input parameters and the partial third-dimensional feature vector set, wherein s takes any integer from 1 to S, if s is 1, the input parameter is the i-th type of two-dimensional feature vector set, if s is not 1, the input parameter is the output parameter of the s-1th feature derivation layer. It can be seen that the next feature derivation layer can continue to derive the remaining third-dimensional features based on the third-dimensional features derived by the previous feature derivation layer, that is, recursive derivation, which can improve the robustness and accuracy of the derivation compared to directly deriving all the third-dimensional features.

[0018] In the second aspect, an embodiment of the present application provides a device for creating and rendering standardized three-dimensional field layout models of an enterprise, and the device includes: a transceiver module for obtaining a CAD site plan layout; a processing module for placing the enterprise's standard family library at a specified location in the CAD site plan layout through modeling software to obtain a field layout model; adding an environmental landscape model to the field layout model through a plug-in to obtain a two-dimensional panoramic view; rendering the two-dimensional panoramic view to obtain a three-dimensional panoramic view; and displaying the three-dimensional panoramic view through BIM software.

[0019] In a possible design scheme, the elements in the CAD site plan include at least one of the following: temporary buildings, main body outlines, tower cranes, construction elevators, site roads, or various material processing plants and yards; the elements in the standard family library include at least one of the following: gates, walls, standardized protection, various processing sheds, dormitories, canteens, offices, conference rooms, activity rooms, toilets, basketball courts, or corporate logos and signs; the elements in the environmental landscape model include at least one of the following: flowers, trees, people, or cars.

[0020] In a possible design scheme, the processing module is also used to use an unsupervised neural network model to perform clustering processing on the two-dimensional panoramic image to obtain N types of two-dimensional feature vector sets, where the two-dimensional panoramic image includes N elements, and the i-th type of two-dimensional feature vector set is the feature vector set of the i-th element among the N elements in the two-dimensional plane, where N is an integer greater than 1, and i is an arbitrary integer from 1 to N; use a feature reconstruction neural network model to perform dimensionality upgrade processing on the i-th type of two-dimensional feature vector set to obtain the i-th type of three-dimensional feature vector set, where the i-th type of three-dimensional feature vector set is the feature vector set of the i-th element in three-dimensional space; and construct a three-dimensional panoramic image based on the i-th type of three-dimensional feature vector set.

[0021] In a possible design scheme, the processing module is also used to use the feature extraction layer of the unsupervised neural network model to perform convolution and pooling processing on the two-dimensional panoramic image to obtain a two-dimensional feature sequence of the two-dimensional panoramic image; and use the feature classification layer of the unsupervised neural network model to cluster the two-dimensional feature sequence to obtain a set of N types of two-dimensional feature vectors.

[0022] In one possible design scheme, the feature classification layer includes M classifiers, M is an integer greater than N, and the processing module is also used to use each of the M classifiers to cluster the two-dimensional feature sequence to obtain N types of two-dimensional feature vectors, among which N classifiers among the M classifiers each output a corresponding type of two-dimensional feature vector, and the other MN classifiers among the M classifiers do not output a two-dimensional feature vector.

[0023] In a possible design scheme, the i-th classifier among N classifiers outputs the i-th two-dimensional feature vector, and the i-th classifier outputs the i-th two-dimensional feature vector means: the i-th classifier processes the two-dimensional feature sequence to obtain multiple two-dimensional feature vectors clustered in the feature space, and multiple two-dimensional feature vectors discrete in the feature space, and the i-th classifier determines the multiple two-dimensional feature vectors clustered in the feature space as the i-th two-dimensional feature vector.

[0024] In a possible design scheme, the feature classification layer includes M classifiers, M is an integer greater than N, and the M classifiers classify two types of classifiers. One type of classifier includes N main classifiers, and the other type of classifier includes MN auxiliary classifiers. Each auxiliary classifier is interleaved with the N auxiliary classifiers. The processing module is also used to use the i-th main classifier and the MN auxiliary classifiers interleaved with the main classifier to perform clustering processing on the two-dimensional feature sequence to obtain the i-th two-dimensional feature vector.

[0025] In a possible design scheme, each auxiliary classifier is interwoven with N auxiliary classifiers, which means that: the classification neural network of each auxiliary classifier is coupled with the classification neural networks of the N auxiliary classifiers respectively, the i-th main classifier clusters the two-dimensional feature sequence to obtain a first clustered feature and a first discrete feature, the first clustered feature refers to a plurality of two-dimensional feature vectors clustered in the feature space, the first discrete feature refers to a plurality of two-dimensional feature vectors discrete in the feature space, MN auxiliary classifiers cluster the first clustered feature and the first discrete feature to obtain a second clustered feature from the first clustered feature and a third clustered feature from the first discrete feature, the second clustered feature and the third clustered feature both refer to a plurality of two-dimensional feature vectors clustered in the feature space, and the second clustered feature and the third clustered feature obtain the i-th two-dimensional feature vector.

[0026] In a possible design scheme, the processing module is also used to analyze the i-th two-dimensional feature vector set using a feature reconstruction neural network model to derive the i-th third-dimensional feature vector set of the i-th element, wherein the i-th three-dimensional feature vector set includes the i-th two-dimensional feature vector set and the i-th third-dimensional feature vector set, the i-th two-dimensional feature vector set is specifically the feature vector set of the i-th element on the x-axis and the y-axis, and the i-th third-dimensional feature vector set is specifically the feature vector set of the i-th element on the z-axis.

[0027] In one possible design scheme, the feature reconstruction neural network model includes S feature derivation layers, S is an integer greater than 1, and the sth feature derivation layer among the S feature derivation layers is used to derive a partial third-dimensional feature vector set based on input parameters, and output the input parameters and the partial third-dimensional feature vector set, where s takes any integer from 1 to S. If s is 1, the input parameter is the i-th two-dimensional feature vector set, and if s is not 1, the input parameter is the output parameter of the s-1th feature derivation layer.

[0028] Optionally, the transceiver module may include a receiving module and a sending module, wherein the receiving module is used to implement the receiving function of the device described in the second aspect, and the sending module is used to implement the sending function of the device described in the second aspect.

[0029] Optionally, the device described in the second aspect may further include a storage module, wherein the storage module stores a program or instruction. When the processing module executes the program or instruction, the device may execute the method described in the first aspect.

[0030] It should be noted that the device described in the second aspect can be a terminal or a network device, or a chip (system) or other parts or components that can be set in a terminal or a network device, or a device that includes a network device, which is not limited in this application.

[0031] In addition, the technical effects of the device described in the second aspect can refer to the technical effects of the above-mentioned method, which will not be repeated here.

[0032] In a third aspect, an embodiment of the present application provides a device for creating a standardized three-dimensional field layout model and rendering effects for an enterprise, and the device for creating a standardized three-dimensional field layout model and rendering effects for an enterprise comprises: a processor and a memory; the memory is used to store computer instructions, and when the processor executes the instructions, the device for creating a standardized three-dimensional field layout model and rendering effects for an enterprise executes the method described in the first aspect.

[0033] In a possible design solution, the device for creating a standardized three-dimensional field model and rendering effects of an enterprise described in the third aspect may include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the device for creating a standardized three-dimensional field model and rendering effects of an enterprise described in the third aspect to communicate with other devices.

[0034] In addition, the technical effects of the device for creating an enterprise standardized three-dimensional field layout model and rendering effects described in the third aspect can refer to the technical effects of the method described in the first aspect, and will not be repeated here.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a program code stored thereon. When the program code is executed by the computer, the method described in the first aspect is executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of a method for creating a standardized three-dimensional field model and rendering effects for an enterprise provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of a device for creating a standardized three-dimensional field model and rendering effects provided in an embodiment of the present application Figure 1 ;

[0038] Figure 3 A schematic diagram of a device for creating a standardized three-dimensional field model and rendering effects provided in an embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0039] The technical solution in this application will be described below in conjunction with the accompanying drawings.

[0040] The present application will present various aspects, embodiments or features around a system that may include multiple devices, components, modules, etc. It should be understood and appreciated that each system may include additional devices, components, modules, etc., and / or may not include all of the devices, components, modules, etc. discussed in conjunction with the figures. In addition, combinations of these schemes may also be used.

[0041] In addition, in the embodiments of the present application, words such as "exemplary" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present concepts in a concrete way.

[0042] It should be noted that when the distinction is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the distinction is not emphasized, the meanings they intend to express are the same.

[0043] In the embodiments of the present application, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0044] The network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. A person of ordinary skill in the art can appreciate that with the evolution of the network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0045] The method for creating an enterprise standardized three-dimensional field layout model and rendering effects provided in the embodiment of the present application can be applied to an apparatus for creating an enterprise standardized three-dimensional field layout model and rendering effects, and the apparatus for creating an enterprise standardized three-dimensional field layout model and rendering effects can be a terminal or a network device.

[0046] The above-mentioned terminal is a terminal with a transceiver function or a chip or chip system that can be set in the terminal. The terminal device can also be called a user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user device. The terminal device in the embodiment of the present application can be a mobile phone, a tablet computer (Pad), a computer with a wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control (industrial control), a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid (smart grid), a wireless terminal in transportation safety (transportation safety), a wireless terminal in a smart city (smart city), a wireless terminal in a smart home (smarthome), a vehicle-mounted terminal, an RSU with a terminal function, etc. The terminal device of the present application may also be a vehicle-mounted module, vehicle-mounted module, vehicle-mounted component, vehicle-mounted chip or vehicle-mounted unit that is built into the vehicle as one or more components or units. The vehicle can implement the method provided by the present application through the built-in vehicle-mounted module, vehicle-mounted module, vehicle-mounted component, vehicle-mounted chip or vehicle-mounted unit.

[0047] The above-mentioned network device may be a server, such as a data server, a network server, or may be a server cluster composed of a single server, and this application does not make any specific limitation on this.

[0048] It should be noted that the solutions in the embodiments of the present application can also be applied to other device systems, and the corresponding names can also be replaced by the names of corresponding functions in other devices.

[0049] See also Figure 1 The embodiment of the present application provides a method for creating a standardized three-dimensional field model and rendering effects for an enterprise. The method can be applied to the above-mentioned device for creating a standardized three-dimensional field model and rendering effects for an enterprise, which is referred to as the first device for convenience of description. The process of the method includes:

[0050] S101, obtaining a CAD site plan layout drawing.

[0051] Among them, the first device can obtain the CAD site plan layout by any possible means or ways, such as user input, transmission by other devices, etc., without specific limitation. Among them, the CAD site plan layout can be drawn in the following way: according to relevant technical information, combined with the construction site conditions, it is drawn in stages, and then the drawing drawings are processed, such as block unlocking, Z-axis zeroing, cleaning drawings and exporting drawings, etc., so as to obtain the CAD site plan layout. The elements in the CAD site plan layout include at least one of the following: temporary construction, main body outline, tower crane, construction elevator, site road, or various material processing plants and yards. These elements are designed according to actual conditions and conform to actual conditions. Among them, the stages include construction preparation stage, earth excavation stage, structure construction stage, decoration construction stage, outdoor landscape construction stage, etc.

[0052] S102, using modeling software, inserting the enterprise's standard family library into a designated location in the CAD site plan layout to obtain a site layout model.

[0053] The elements in the standard family library include at least one of the following: gates, walls, standardized protection, various processing sheds, dormitories, canteens, offices, conference rooms, activity rooms, toilets, basketball courts, or corporate logos and signs. These elements are designed according to actual conditions and conform to actual conditions. The modeling software can be Revit or any other possible software, and there is no specific limitation on this.

[0054] S103, adding an environmental landscape model to the field model through a plug-in to obtain a two-dimensional panoramic image.

[0055] The elements in the environment landscape model include at least one of the following: flowers, trees, people, or cars. These elements are designed according to the actual situation and conform to the actual situation. The plug-in can be Enscape or any other possible plug-in, and there is no specific limitation on this.

[0056] S104, rendering the two-dimensional panoramic image to obtain a three-dimensional panoramic image.

[0057] Among them, the specific implementation of S104 may include: step 1, clustering the two-dimensional panoramic image using an unsupervised neural network model to obtain a set of N two-dimensional feature vectors. Step 2, using a feature reconstruction neural network model to perform dimension-upgrading processing on the i-th two-dimensional feature vector set to obtain the i-th three-dimensional feature vector set. Step 3, constructing a three-dimensional panoramic image based on the i-th three-dimensional feature vector set. It can be understood that by clustering the two-dimensional panoramic image using an unsupervised neural network model, the two-dimensional features of each element in the two-dimensional panoramic image can be extracted, that is, a set of two-dimensional feature vectors. In this way, by using the two-dimensional features of each element of the feature reconstruction neural network model to perform dimension-upgrading, the three-dimensional features of each element can be obtained, that is, a set of three-dimensional feature vectors, so that according to the three-dimensional features of the elements, a three-dimensional model, that is, a three-dimensional panoramic image, is constructed, so that through unsupervised learning, a three-dimensional model is constructed based on a two-dimensional image, so as to realize how to apply unsupervised learning to more fields. The following is a detailed introduction to S104.

[0058] For step 1, the two-dimensional panoramic image includes N elements referred to in S101-S103 above, where N is an integer greater than 1. The i-th type of two-dimensional feature vector set is the feature vector set of the i-th element in the N elements in the two-dimensional plane, where i is any integer from 1 to N.

[0059] Specifically, the unsupervised neural network model includes a feature extraction layer and a feature classification layer. The first device can use the feature extraction layer of the unsupervised neural network model to perform convolution and pooling processing on the two-dimensional panoramic image, thereby obtaining a two-dimensional feature sequence of the two-dimensional panoramic image. The first device can use the feature classification layer of the unsupervised neural network model to perform clustering processing on the two-dimensional feature sequence to obtain a set of N types of two-dimensional feature vectors. In this way, by dividing the unsupervised neural network model into a feature extraction layer and a feature classification layer, decoupling is achieved, which facilitates updating or upgrading the model. The clustering process is described in detail below.

[0060] In a possible implementation, the feature classification layer includes M classifiers, where M is an integer greater than N. In this way, the first device can use each of the M classifiers to perform clustering processing on the two-dimensional feature sequence to obtain N types of two-dimensional feature vectors. Among them, N classifiers in the M classifiers each output a corresponding type of two-dimensional feature vector, and the other MN classifiers in the M classifiers do not output a two-dimensional feature vector. It can be seen that the M classifiers are set for the type of element, and the two-dimensional features of each element can be extracted by a special classifier, which can improve the accuracy of feature extraction and improve the accuracy of building a three-dimensional model.

[0061] Optionally, the i-th classifier among the N classifiers outputs the i-th two-dimensional feature vector, and the i-th classifier outputs the i-th two-dimensional feature vector means that the i-th classifier processes the two-dimensional feature sequence to obtain multiple two-dimensional feature vectors clustered in the feature space and multiple two-dimensional feature vectors discrete in the feature space, and the i-th classifier determines the multiple two-dimensional feature vectors clustered in the feature space as the i-th two-dimensional feature vector. It can be seen that the classifier can cluster features by their positions in the feature space, so that a class of features can be extracted more accurately.

[0062] Alternatively, in a possible implementation, the feature classification layer includes M classifiers, where M is an integer greater than N, and the M classifiers classify two types of classifiers, one type of classifier includes N main classifiers, and the other type of classifier includes MN auxiliary classifiers, and each auxiliary classifier is intertwined with the N auxiliary classifiers. In this way, the first device can use the i-th main classifier and the MN auxiliary classifiers intertwined with the main classifier to perform clustering processing on the two-dimensional feature sequence to obtain the i-th two-dimensional feature vector. In other words, the classification of each main classifier can be assisted by all auxiliary classifiers to further improve the accuracy of feature extraction.

[0063] Optionally, each auxiliary classifier is interwoven with N auxiliary classifiers, which means that the classification neural network of each auxiliary classifier is coupled with the classification neural network of each of the N auxiliary classifiers, the i-th main classifier performs clustering processing on the two-dimensional feature sequence to obtain the first clustered feature and the first discrete feature, the first clustered feature refers to multiple two-dimensional feature vectors clustered in the feature space, the first discrete feature refers to multiple two-dimensional feature vectors discrete in the feature space, MN auxiliary classifiers perform clustering processing on the first clustered feature and the first discrete feature to obtain the second clustered feature from the first clustered feature, and the third clustered feature from the first discrete feature, the second clustered feature and the third clustered feature both refer to multiple two-dimensional feature vectors clustered in the feature space, and the second clustered feature and the third clustered feature obtain the i-th two-dimensional feature vector. It can be seen that the auxiliary classifier can check and fill in the gaps in the feature extraction results of the main classifier to ensure the accuracy of feature extraction.

[0064] For step 2, the i-th three-dimensional feature vector set is the feature vector set of the i-th element in three-dimensional space. The first device can use the feature reconstruction neural network model to analyze the i-th two-dimensional feature vector set to derive the i-th third-dimensional feature vector set of the i-th element. Among them, the i-th three-dimensional feature vector set includes the i-th two-dimensional feature vector set and the i-th third-dimensional feature vector set. The i-th two-dimensional feature vector set is specifically the feature vector set of the i-th element on the x-axis and y-axis, and the i-th third-dimensional feature vector set is specifically the feature vector set of the i-th element on the z-axis. It can be seen that the dimensionality increase processing of the features is not to reconstruct the features, but to supplement the third-dimensional features on the basis of the two-dimensional features, which can improve the processing efficiency and reduce the computing overhead.

[0065] Optionally, the feature reconstruction neural network model includes S feature derivation layers, S is an integer greater than 1, and the sth feature derivation layer among the S feature derivation layers is used to derive a partial third-dimensional feature vector set according to the input parameters, and output the input parameters and the partial third-dimensional feature vector set, wherein s takes any integer from 1 to S, if s is 1, the input parameter is the i-th type of two-dimensional feature vector set, and if s is not 1, the input parameter is the output parameter of the s-1th feature derivation layer. It can be seen that the next feature derivation layer can continue to derive the remaining third-dimensional features based on the third-dimensional features derived by the previous feature derivation layer, that is, recursive derivation, which can improve the robustness and accuracy of the derivation compared to directly deriving all third-dimensional features.

[0066] For step 3, the first device can map the i-th type of three-dimensional feature vector set to the three-dimensional space to obtain the discrete coordinate points of the i-th element in the three-dimensional space. The first device can make these discrete coordinate points continuous to obtain the model of the i-th element in the three-dimensional space.

[0067] S105, displaying a three-dimensional panoramic view through BIM software.

[0068] Among them, BIM software can transmit information through WeChat links, QR codes, etc., that is, the three-dimensional panoramic view can be displayed by clicking WeChat links, scanning QR codes, etc.

[0069] In summary, based on the above method, it can be seen that according to the pre-built simulated construction site layout, a series of processing is performed on the CAD site plan to obtain a two-dimensional panoramic view that can truly reflect the on-site situation. By rendering the two-dimensional panoramic view, a three-dimensional panoramic view, that is, a three-dimensional rendering effect map, can be directly obtained without manual drawing, which not only saves labor costs, but also greatly improves the drawing efficiency of the three-dimensional rendering effect map. In addition, in the above series of processing, by using the company's standard family library, it can save a lot of modeling time when establishing the on-site layout model, and the model results are more standardized.

[0070] See also Figure 3 In this embodiment, a device 200 for creating an enterprise standardized three-dimensional field model and rendering effects is also provided. The device 200 includes:

[0071] The transceiver module 201 is used to obtain the CAD site plan layout; the processing module 202 is used to put the enterprise's standard family library into the specified position in the CAD site plan layout through the modeling software to obtain the site layout model; add the environmental landscape model to the site layout model through the plug-in to obtain a two-dimensional panoramic view; render the two-dimensional panoramic view to obtain a three-dimensional panoramic view; and display the three-dimensional panoramic view through the BIM software.

[0072] In a possible design scheme, the processing module 202 is also used to use an unsupervised neural network model to perform clustering processing on the two-dimensional panoramic image to obtain N types of two-dimensional feature vector sets, where the two-dimensional panoramic image includes N elements, and the i-th type of two-dimensional feature vector set is the feature vector set of the i-th element of the N elements in the two-dimensional plane, where N is an integer greater than 1, and i is an arbitrary integer from 1 to N; use a feature reconstruction neural network model to perform dimensionality upgrade processing on the i-th type of two-dimensional feature vector set to obtain the i-th type of three-dimensional feature vector set, where the i-th type of three-dimensional feature vector set is the feature vector set of the i-th element in three-dimensional space; and construct a three-dimensional panoramic image based on the i-th type of three-dimensional feature vector set.

[0073] In one possible design scheme, the processing module 202 is also used to use the feature extraction layer of the unsupervised neural network model to perform convolution and pooling processing on the two-dimensional panoramic image to obtain a two-dimensional feature sequence of the two-dimensional panoramic image; and use the feature classification layer of the unsupervised neural network model to cluster the two-dimensional feature sequence to obtain a set of N types of two-dimensional feature vectors.

[0074] In one possible design scheme, the feature classification layer includes M classifiers, where M is an integer greater than N. The processing module 202 is also used to use each of the M classifiers to perform clustering processing on the two-dimensional feature sequence to obtain N types of two-dimensional feature vectors, wherein N of the M classifiers each output a corresponding type of two-dimensional feature vector, and the other MN of the M classifiers do not output a two-dimensional feature vector.

[0075] In a possible design scheme, the i-th classifier among N classifiers outputs the i-th two-dimensional feature vector, and the i-th classifier outputs the i-th two-dimensional feature vector means: the i-th classifier processes the two-dimensional feature sequence to obtain multiple two-dimensional feature vectors clustered in the feature space, and multiple two-dimensional feature vectors discrete in the feature space, and the i-th classifier determines the multiple two-dimensional feature vectors clustered in the feature space as the i-th two-dimensional feature vector.

[0076] In a possible design scheme, the feature classification layer includes M classifiers, where M is an integer greater than N. The M classifiers classify two types of classifiers, one type of classifier includes N main classifiers, and the other type of classifier includes MN auxiliary classifiers. Each auxiliary classifier is interleaved with the N auxiliary classifiers. The processing module 202 is also used to use the i-th main classifier and the MN auxiliary classifiers interleaved with the main classifier to perform clustering processing on the two-dimensional feature sequence to obtain the i-th two-dimensional feature vector.

[0077] In a possible design scheme, each auxiliary classifier is interwoven with N auxiliary classifiers, which means that: the classification neural network of each auxiliary classifier is coupled with the classification neural networks of the N auxiliary classifiers respectively, the i-th main classifier clusters the two-dimensional feature sequence to obtain a first clustered feature and a first discrete feature, the first clustered feature refers to a plurality of two-dimensional feature vectors clustered in the feature space, the first discrete feature refers to a plurality of two-dimensional feature vectors discrete in the feature space, MN auxiliary classifiers cluster the first clustered feature and the first discrete feature to obtain a second clustered feature from the first clustered feature and a third clustered feature from the first discrete feature, the second clustered feature and the third clustered feature both refer to a plurality of two-dimensional feature vectors clustered in the feature space, and the second clustered feature and the third clustered feature obtain the i-th two-dimensional feature vector.

[0078] In a possible design scheme, the processing module 202 is also used to analyze the i-th two-dimensional feature vector set using a feature reconstruction neural network model to derive the i-th third-dimensional feature vector set of the i-th element, wherein the i-th three-dimensional feature vector set includes the i-th two-dimensional feature vector set and the i-th third-dimensional feature vector set, the i-th two-dimensional feature vector set is specifically the feature vector set of the i-th element on the x-axis and the y-axis, and the i-th third-dimensional feature vector set is specifically the feature vector set of the i-th element on the z-axis.

[0079] In one possible design scheme, the feature reconstruction neural network model includes S feature derivation layers, S is an integer greater than 1, and the sth feature derivation layer among the S feature derivation layers is used to derive a partial third-dimensional feature vector set based on input parameters, and output the input parameters and the partial third-dimensional feature vector set, where s takes any integer from 1 to S. If s is 1, the input parameter is the i-th two-dimensional feature vector set, and if s is not 1, the input parameter is the output parameter of the s-1th feature derivation layer.

[0080] In a possible design scheme, the transceiver module 201 may include a receiving module and a sending module. The receiving module is used to implement the receiving function of the device 200 for creating a standardized three-dimensional field cloth model and rendering effects of an enterprise. The sending module is used to implement the sending function of the device 200 for creating a standardized three-dimensional field cloth model and rendering effects of an enterprise.

[0081] In a possible design solution, the device 200 for creating a standardized three-dimensional field model and rendering effects for an enterprise may further include a storage module, which stores a program or instruction. When the processing module 202 executes the program or instruction, the device 200 for creating a standardized three-dimensional field model and rendering effects for an enterprise may perform the above Figure 1 The method shown.

[0082] It should be noted that the device 200 for creating a standardized enterprise three-dimensional layout model and rendering effects can be a terminal or a network device, or a chip (system) or other parts or components that can be set in a terminal or a network device, or a device including a terminal or a network device, and this application does not limit this.

[0083] In addition, the technical effects of the device 200 for creating a standardized three-dimensional field layout model and rendering effects for an enterprise can refer to the technical effects of the above-mentioned method, which will not be repeated here.

[0084] Combine the following Figure 3 , the various components of the device 300 for creating a standardized three-dimensional field model and rendering effects are specifically introduced:

[0085] Specifically, the processor 301 is the control center of the device 300 for creating a standardized three-dimensional field model and rendering effects for an enterprise, and can be a processor or a general term for multiple processing elements. For example, the processor 301 is one or more central processing units (CPUs), or can be an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0086] Optionally, the processor 301 can execute various functions of the device 300 for creating an enterprise standardized three-dimensional layout model and rendering effects by running or executing a software program stored in the memory 302 and calling data stored in the memory 302 .

[0087] In a specific implementation, as an embodiment, the processor 301 may include one or more CPUs, such as CPU0 and CPU1.

[0088] In a specific implementation, as an embodiment, the device 300 for creating a standardized three-dimensional field model and rendering effects of an enterprise may also include multiple processors, such as Figure 3 301 and processor 304 are shown in FIG. Each of these processors may be a single-CPU or a multi-CPU. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0089] The memory 302 is used to store the software program for executing the solution of the present application, and the execution is controlled by the processor 301. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0090] Optionally, the memory 302 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 302 may be integrated with the processor 301, or may exist independently, and may be accessed through the interface circuit ( Figure 3 (not shown) is coupled to the processor 301, which is not specifically limited in the embodiment of the present application.

[0091] The transceiver 303 is used for communication with other devices. For example, the device 300 for creating a standardized three-dimensional scene model and rendering effects of an enterprise is a network device, and the transceiver 303 can be used for communication with a terminal device or another network device.

[0092] Optionally, the transceiver 303 may include a receiver and a transmitter ( Figure 3 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0093] Optionally, the transceiver 303 may be integrated with the processor 301, or may exist independently, and may be connected to the processor 301 through the interface circuit ( Figure 3 (not shown) is coupled to the processor 301, which is not specifically limited in the embodiment of the present application.

[0094] It should be noted that Figure 3 The structure of the device 300 shown in the figure does not constitute a limitation on the device 300 for creating a standardized three-dimensional field layout model and rendering effects of the enterprise. The actual device 300 for creating a standardized three-dimensional field layout model and rendering effects of the enterprise may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0095] In addition, the technical effects of the device 300 can refer to the technical effects of the method in the above method embodiment, which will not be repeated here.

[0096] It should be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0097] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0098] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0099] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated elements, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated elements before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0100] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0101] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0102] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0104] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some feature fields can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0107] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., and other media that can store program codes.

[0108] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for creating a standardized three-dimensional field model and rendering effects for an enterprise, characterized in that: The method comprises: Get the CAD site layout; By using modeling software, the enterprise's standard family library is placed in the designated position of the CAD site plan to obtain a site layout model; Adding an environmental landscape model to the field model through a plug-in to obtain a two-dimensional panoramic image; Rendering the two-dimensional panoramic image to obtain a three-dimensional panoramic image; Displaying the three-dimensional panoramic view through BIM software; The elements in the CAD site layout drawing include at least one of the following: temporary buildings, main body outlines, tower cranes, construction elevators, site roads, or various material processing plants and yards; the elements in the standard family library include at least one of the following: gates, walls, standardized protection, various processing sheds, dormitories, canteens, offices, conference rooms, activity rooms, toilets, basketball courts, or corporate logos and signs; the elements in the environmental landscape model include at least one of the following: flowers, trees, people, or cars; The rendering of the two-dimensional panoramic image to obtain a three-dimensional panoramic image includes: Using an unsupervised neural network model to perform clustering processing on the two-dimensional panoramic image, obtaining N types of two-dimensional feature vector sets, wherein the two-dimensional panoramic image includes N elements, and the i-th type of the two-dimensional feature vector set is a feature vector set of the i-th element of the N elements in a two-dimensional plane, where N is an integer greater than 1, and i is an arbitrary integer from 1 to N; Using a feature reconstruction neural network model, the two-dimensional feature vector set of the i-th category is subjected to dimensionality-increasing processing to obtain a three-dimensional feature vector set of the i-th category, wherein the three-dimensional feature vector set of the i-th category is a feature vector set of the i-th element in three-dimensional space; The three-dimensional panoramic image is constructed according to the three-dimensional feature vector set of the i-th category.

2. The method according to claim 1, characterized in that The unsupervised neural network model includes a feature extraction layer and a feature classification layer. The unsupervised neural network model is used to perform clustering processing on the two-dimensional panoramic image to obtain a set of N two-dimensional feature vectors, including: Using the feature extraction layer of the unsupervised neural network model to perform convolution and pooling processing on the two-dimensional panoramic image, so as to obtain a two-dimensional feature sequence of the two-dimensional panoramic image; The two-dimensional feature sequence is clustered using the feature classification layer of the unsupervised neural network model to obtain the N types of two-dimensional feature vector sets.

3. The method according to claim 2, characterized in that The feature classification layer includes M classifiers, where M is an integer greater than N. The feature classification layer using the unsupervised neural network model performs clustering processing on the two-dimensional feature sequence to obtain the N types of two-dimensional feature vector sets, including: Each of the M classifiers is used to perform clustering processing on the two-dimensional feature sequence to obtain the N types of two-dimensional feature vectors, wherein N of the M classifiers each output a corresponding type of the two-dimensional feature vector, and the other MN of the M classifiers do not output the two-dimensional feature vector.

4. The method according to claim 2, characterized in that: The feature classification layer includes M classifiers, where M is an integer greater than N. The M classifiers classify two types of classifiers, one type of classifier includes N main classifiers, and the other type of classifier includes MN auxiliary classifiers. Each of the auxiliary classifiers is intertwined with the N main classifiers. The feature classification layer using the unsupervised neural network model performs clustering processing on the two-dimensional feature sequence to obtain the N types of two-dimensional feature vector sets, including: The two-dimensional feature sequence is clustered using the i-th main classifier and the MN auxiliary classifiers interwoven with the main classifier to obtain the i-th two-dimensional feature vector.

5. The method according to claim 4, characterized in that Each of the auxiliary classifiers is interwoven with the N main classifiers, which means that the classification neural network of each auxiliary classifier is coupled with the classification neural network of each of the N main classifiers; the i-th main classifier performs clustering processing on the two-dimensional feature sequence to obtain a first clustered feature and a first discrete feature, the first clustered feature refers to a plurality of two-dimensional feature vectors clustered in the feature space, the first discrete feature refers to a plurality of two-dimensional feature vectors discrete in the feature space, MN auxiliary classifiers perform clustering processing on the first clustered feature and the first discrete feature to obtain a second clustered feature from the first clustered feature and a third clustered feature from the first discrete feature, the second clustered feature and the third clustered feature both refer to a plurality of two-dimensional feature vectors clustered in the feature space, and the second clustered feature and the third clustered feature obtain the i-th two-dimensional feature vector.

6. The method according to claim 1, characterized in that The method of using the feature reconstruction neural network model to perform dimension-upgrading processing on the two-dimensional feature vector set of the i-th category to obtain the three-dimensional feature vector set of the i-th category includes: The feature reconstruction neural network model is used to analyze the two-dimensional feature vector set of the i-th category to derive the i-th third-dimensional feature vector set of the i-th element, wherein the i-th three-dimensional feature vector set includes the i-th two-dimensional feature vector set and the i-th third-dimensional feature vector set, the i-th two-dimensional feature vector set is specifically the feature vector set of the i-th element on the x-axis and the y-axis, and the i-th third-dimensional feature vector set is specifically the feature vector set of the i-th element on the z-axis.

7. The method according to claim 6, characterized in that The feature reconstruction neural network model includes S feature derivation layers, S is an integer greater than 1, and the sth feature derivation layer among the S feature derivation layers is used to derive part of the third-dimensional feature vector set based on input parameters, and output the input parameters and part of the third-dimensional feature vector set, wherein s takes any integer from 1 to S, if s is 1, then the input parameter is the two-dimensional feature vector set of the i-th category, and if s is not 1, then the input parameter is the output parameter of the s-1th feature derivation layer.

8. A device for creating a standardized three-dimensional field model and rendering effects for an enterprise, characterized in that: The device comprises: A transceiver module is used to obtain the CAD site layout; The processing module is used to put the enterprise's standard family library in the designated position of the CAD site plan through the modeling software to obtain a site layout model; add the environmental landscape model to the site layout model through the plug-in to obtain a two-dimensional panoramic view; render the two-dimensional panoramic view to obtain a three-dimensional panoramic view; and display the three-dimensional panoramic view through the BIM software; The elements in the CAD site layout drawing include at least one of the following: temporary buildings, main body outlines, tower cranes, construction elevators, site roads, or various material processing plants and yards; the elements in the standard family library include at least one of the following: gates, walls, standardized protection, various processing sheds, dormitories, canteens, offices, conference rooms, activity rooms, toilets, basketball courts, or corporate logos and signs; the elements in the environmental landscape model include at least one of the following: flowers, trees, people, or cars; The rendering of the two-dimensional panoramic image to obtain a three-dimensional panoramic image includes: Using an unsupervised neural network model to perform clustering processing on the two-dimensional panoramic image, obtaining N types of two-dimensional feature vector sets, wherein the two-dimensional panoramic image includes N elements, and the i-th type of the two-dimensional feature vector set is a feature vector set of the i-th element of the N elements in a two-dimensional plane, where N is an integer greater than 1, and i is an arbitrary integer from 1 to N; Using a feature reconstruction neural network model, the two-dimensional feature vector set of the i-th category is subjected to dimensionality-increasing processing to obtain a three-dimensional feature vector set of the i-th category, wherein the three-dimensional feature vector set of the i-th category is a feature vector set of the i-th element in three-dimensional space; The three-dimensional panoramic image is constructed according to the three-dimensional feature vector set of the i-th category.

Images