Method for installation and monitoring of electromechanical equipment applied to building areas and computer device

Abstract

Embodiments of the present application relate to the field of electromechanical equipment installation and monitoring, and particularly to an electromechanical equipment installation and monitoring method applied to a building area and a computer device. A specific implementation of the method includes: performing image stitching on each optimized building wide-angle image in an optimized building wide-angle image set; generating an original building area model corresponding to the building area according to a building area stitched image and a pre-trained building information generation model; obtaining electromechanical equipment model information corresponding to each electromechanical equipment coding identifier in an electromechanical equipment coding identifier group; filling the original building area model according to the electromechanical equipment model information group and the electromechanical equipment coding identifier group to obtain a target building area model; and controlling an associated installation device to perform installation processing on each electromechanical equipment to be installed according to the target building area model. The implementation can install each electromechanical equipment according to the target building area model, thereby avoiding installation errors of the electromechanical equipment.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of electromechanical equipment installation and monitoring, and in particular to an electromechanical equipment installation and monitoring method and computer device applied to a building area. BACKGROUND

[0002] Electromechanical equipment generally refers to mechanical, electrical and electrical automation equipment, and in the building, it refers to the general term of mechanical, piping equipment other than earthwork, woodworking, reinforcing steel, and mud water. It is different from hardware, and refers to finished products that can achieve a certain function. At present, in the construction industry, the installation of electromechanical equipment in the building area needs the operating workers to install and place each electromechanical equipment according to the installation drawing. However, the operating workers install and place each electromechanical equipment according to the installation drawing, which is low in efficiency and easy to cause equipment installation error. After the equipment installation error, it is also difficult for the operating workers to find it in time. SUMMARY

[0003] The summary part of the present application is used to introduce the concept in a brief form, which will be described in detail in the specific embodiment part. The summary part of the present application is not intended to identify the key features or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0004] Some embodiments of the present application propose an electromechanical equipment installation and monitoring method, a computer device and a computer readable storage medium applied to a building area, to solve one or more of the technical problems mentioned in the background part.

[0005] In a first aspect, some embodiments of the present application provide a method for installation and monitoring of mechanical and electrical equipment applied to a building area, the method comprising: collecting, by a mechanical and electrical equipment installation and monitoring device, building data in a building area where mechanical and electrical equipment is to be installed, wherein the building data comprises: a set of building wide-angle images corresponding to the building area; encoding each mechanical and electrical equipment to be installed in the building area to generate a mechanical and electrical equipment encoding identifier, thereby obtaining a set of mechanical and electrical equipment encoding identifiers; generating an optimized set of building wide-angle images from the set of building wide-angle images, wherein the optimized building wide-angle image is an image obtained by locally fusing and optimizing a plurality of building wide-angle images; image stitching each optimized building wide-angle image in the set of optimized building wide-angle images to obtain a building area stitching image; generating an original building area model corresponding to the building area according to the building area stitching image and a pre-trained building information generation model; obtaining mechanical and electrical equipment model information corresponding to each mechanical and electrical equipment encoding identifier in the set of mechanical and electrical equipment encoding identifiers, thereby obtaining a set of mechanical and electrical equipment model information, wherein the mechanical and electrical equipment model information comprises: a mechanical and electrical equipment model, installation location information, and equipment size information; filling the original building area model according to the set of mechanical and electrical equipment model information and the set of mechanical and electrical equipment encoding identifiers, thereby obtaining a target building area model; controlling an associated installation device to install each mechanical and electrical equipment to be installed according to the target building area model; in response to determining that each mechanical and electrical equipment is installed, controlling the mechanical and electrical equipment installation and monitoring device to collect building data of the building area after installation is completed as target building data, and performing position verification on each installed mechanical and electrical equipment according to the target building data.

[0006] In a second aspect, the present application further provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the method described in any of the implementations of the first aspect.

[0007] In a third aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the method described in any of the implementations of the first aspect.

[0008] The above various embodiments of the present application have the following beneficial effects: through the mechanical and electrical equipment installation and monitoring method applied to the building area by some embodiments of the present application, a three-dimensional model of the building area can be established, and through the three-dimensional model and the mechanical and electrical equipment model, a target building area model after the mechanical and electrical equipment installation is completed can be simulated. Thus, each mechanical and electrical equipment can be installed according to the target building area model. Further, installation errors of the mechanical and electrical equipment are avoided. First, through the mechanical and electrical equipment installation monitoring device, building data in the building area of the mechanical and electrical equipment to be installed is collected, wherein the above building data includes: a building wide-angle image set corresponding to the building area. Each mechanical and electrical equipment to be installed in the above building area is coded to generate a mechanical and electrical equipment coded identifier, and a mechanical and electrical equipment coded identifier group is obtained. Thus, it is convenient to construct a building area model. Second, through the above building wide-angle image set, an optimized building wide-angle image set is generated, wherein the optimized building wide-angle image is an image after local fusion optimization of multiple building wide-angle images. Each optimized building wide-angle image in the above optimized building wide-angle image set is image stitched to obtain a building area stitching image. Thus, through the image optimization method, the model precision of the building area model generated subsequently is improved. Third, according to the above building area stitching image and a pre-trained building information generation model, an original building area model corresponding to the above building area is generated. Thus, a three-dimensional model of the building area can be established. Fourth, the mechanical and electrical equipment model information corresponding to each mechanical and electrical equipment coded identifier in the above mechanical and electrical equipment coded identifier group is obtained to obtain a mechanical and electrical equipment model information group, wherein the mechanical and electrical equipment model information includes: a mechanical and electrical equipment model, installation position information, and equipment size information. Fifth, according to the above mechanical and electrical equipment model information group and the above mechanical and electrical equipment coded identifier group, the above original building area model is filled to obtain a target building area model. Thus, through the three-dimensional model and the mechanical and electrical equipment model, a target building area model after the mechanical and electrical equipment installation is completed can be simulated. Sixth, according to the above target building area model, the associated installation equipment is controlled to install each mechanical and electrical equipment to be installed. In response to determining that each mechanical and electrical equipment is installed, the above mechanical and electrical equipment installation monitoring device is controlled to collect building data of the building area after installation as target building data, and each installed mechanical and electrical equipment is position verified according to the above target building data. Thus, each mechanical and electrical equipment can be installed according to the target building area model. Further, installation errors of the mechanical and electrical equipment are avoided. In addition, the building area after the mechanical and electrical equipment is installed can be collected again to verify whether there is an error in the installation of each mechanical and electrical equipment, so as to be corrected in time. BRIEF DESCRIPTION OF DRAWINGS

[0009] The above and other features, aspects and advantages of the present embodiments will become more apparent with reference to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, similar or same reference numerals are used to denote similar or same elements. It is to be understood that the drawings are schematic, and elements and features are not necessarily to scale.

[0010] Figure 1 is a flowchart of some embodiments of a method for installation and monitoring of electromechanical equipment applied to a building area according to the present application;

[0011] Figure 2 is a structural schematic diagram of a computer device suitable for use to implement some embodiments of the present application. DETAILED DESCRIPTION

[0012] Embodiments of the present application will be described in more detail with reference to the drawings. Although certain embodiments of the present application are shown in the drawings, it is understood that the present application can be embodied in various forms and should not be interpreted as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present application will be more thoroughly understood. It is to be understood that the drawings and embodiments of the present application are for illustrative purposes only and should not be construed as limiting the scope of the present application.

[0013] It should also be noted that, for the sake of brevity, the figures herein only show portions of an apparatus that are related to the relevant application. Embodiments of the present application and features in embodiments can be combined with each other in cases of no conflict.

[0014] It should be noted that the terms "first", "second", and the like in the present application are only used to distinguish different devices, modules or units, and do not imply the order or interdependence of the functions performed by these devices, modules or units.

[0015] It should be noted that the terms "one", "multiple" in the present application are illustrative and not restrictive, and those skilled in the art should understand that, unless otherwise explicitly stated in the context, it should be understood as "one or more".

[0016] The names of the messages or information exchanged between the devices in the embodiments of the present application are only used for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0017] The present application will be described in detail below with reference to the drawings and in conjunction with embodiments.

[0018] Figure 1 Flowchart 100 of some embodiments of a method for installation and monitoring of electromechanical equipment applied to a building area according to the present application is shown. The method for installation and monitoring of electromechanical equipment applied to a building area includes the following steps:

[0019] In step 101, the building data in the building area where the electromechanical equipment is to be installed is collected by the electromechanical equipment installation monitoring device.

[0020] In some embodiments, the execution subject (e.g., computer equipment) of the electromechanical equipment installation and monitoring method applied to the building area can collect the building data in the building area where the electromechanical equipment is to be installed through the electromechanical equipment installation monitoring device. The above-mentioned building data includes: a set of building wide-angle images corresponding to the building area. The electromechanical equipment installation monitoring device can be a monitoring device with a wide-angle lens set in the building area, which can include a wide-angle lens camera, various sensors. The set of building wide-angle images is a wide-angle image in the building area. The set of building wide-angle images is a set of images containing a panorama in the building area collected by a camera with a wide-angle lens. The building area can be an area where various electromechanical equipment is to be installed. For example, the building area can be a laboratory, an exhibition hall, etc. For example, various electromechanical equipment can include but is not limited to: household appliances, automotive electronic products, fitness exercise machines, computers, printers, copiers, communication equipment, office automation equipment, etc.

[0021] In an actual scenario, the execution subject can collect the building data in the building area where the electromechanical equipment is to be installed by the following steps:

[0022] First, a set of building wide-angle images in the building area where the electromechanical equipment is to be installed is collected. For example, the associated wide-angle lens camera can be controlled to collect each building wide-angle image in the building area where the electromechanical equipment is to be installed.

[0023] Second, each building wide-angle image in the set of building wide-angle images with time sequence is converted to obtain a sequence of converted building wide-angle image information. For example, for each building wide-angle image in the set of building wide-angle images, first, the building wide-angle image can be subjected to image size conversion; then, the building wide-angle image can be subjected to standardization processing; then, the building wide-angle image can be converted into a building wide-angle image tensor. The converted building wide-angle image tensor is the converted building wide-angle image information. The image size conversion can be a conversion to a preset image size. The building wide-angle image tensor can be a PyTorch tensor.

[0024] Third, for each converted building wide-angle image information in the sequence of converted building wide-angle image information, the following steps are performed:

[0025] 1. The converted wide-angle architectural image information is input into the encoding network of a pre-trained depth image construction model to obtain a converted wide-angle architectural image feature map. The depth image construction model includes an encoding network, an image memory network, and a decoding network. The image memory network includes an attention layer. This depth image construction model can be a neural network model that takes the converted wide-angle architectural image as input and outputs a corresponding wide-angle architectural depth image. The encoding network can be used for image feature extraction. For example, the encoding network can be the encoder of a Vision Transformer. The image memory network can be used to store image features and depth information from historical frames, and can also fuse this historical information with the feature map of the current image to enhance the feature map of the current frame. The decoding network can be used to decode the enhanced attention operation feature map to obtain the wide-angle architectural depth image. For example, the decoding network can be the decoder of a DPT (Dense Prediction Transformer) Header. The attention layer can be used for attention operations. The encoding network can include sequential feature extraction layers.

[0026] 2. The transformed wide-angle architectural image feature map is input into the attention layer to perform attention operations on the transformed wide-angle architectural image feature map and the memory features stored in the image memory network, resulting in an attention operation feature map. For example, the execution entity can process the transformed wide-angle architectural image feature map and the memory features using an attention mechanism to obtain a weighted feature representation as the attention operation feature map. The memory features are initially empty. The attention layer may include various attention network layers. In each attention network layer, the current feature map is first processed through a self-attention mechanism, and then processed together with the memory features through a cross-attention mechanism to capture the dependency between the current feature map and the memory features. Each attention network layer may also include a feedforward network for further data processing.

[0027] 3. Input the attention operation feature map described above into the decoding network to obtain the building wide-angle depth image. The decoding network may include feature decoding layers corresponding to the feature extraction layers described above. The number of feature decoding layers may be the same as the number of feature extraction layers described above. Each feature decoding layer corresponds to one feature extraction layer. The feature decoding layers correspond to the feature extraction layers in reverse order.

[0028] 4. Merge the building wide-angle image corresponding to the above converted building wide-angle image information with the above building wide-angle depth image to form building image data.

[0029] The fourth step is to merge the individual building image data into building data.

[0030] Therefore, the accuracy of each depth image generated from the time-series image sequence is improved, thereby facilitating subsequent position verification of the installed electromechanical equipment.

[0031] At step 102, each electromechanical equipment to be installed in the building area is coded to generate an electromechanical equipment coded identifier, thereby obtaining a set of electromechanical equipment coded identifiers.

[0032] In some embodiments, the execution subject can code each electromechanical equipment to be installed in the building area to generate an electromechanical equipment coded identifier, thereby obtaining a set of electromechanical equipment coded identifiers. For example, each electromechanical equipment to be installed can be coded according to a pre-set coding rule to generate an electromechanical equipment coded identifier. For example, the coding rule can be a serial number coding, a device name coding, or a device placement position coding. The electromechanical equipment coded identifier can uniquely identify an electromechanical equipment.

[0033] At step 103, the optimized building wide-angle image set is generated from the building wide-angle image set.

[0034] In some embodiments, the execution subject can generate an optimized building wide-angle image set from the building wide-angle image set. The optimized building wide-angle image is an image obtained by locally fusing and optimizing multiple building wide-angle images. For example, the building wide-angle image set can include a first building wide-angle image, a second building wide-angle image, and a third building wide-angle image. The first building wide-angle image and the second building wide-angle image have an overlapping area 1. The second building wide-angle image and the third building wide-angle image have an overlapping area 2. Therefore, the first building wide-angle image and the second building wide-angle image can be spliced, and the pixel values of the pixel points in the overlapping area 1 of the first building wide-angle image and the second building wide-angle image can be averaged to obtain a first optimized building wide-angle image. The execution subject can splice the second building wide-angle image and the third building wide-angle image, and average the pixel values of the pixel points in the overlapping area 2 of the second building wide-angle image and the third building wide-angle image to obtain a second optimized building wide-angle image.

[0035] In an actual scenario, the execution subject can generate an optimized building wide-angle image set by the following steps:

[0036] First, for each building wide-angle image in the building wide-angle image set, the following processing steps are performed:

[0037] 1. The building wide-angle image is subjected to distortion calibration processing to obtain a distortion calibrated building wide-angle image. For example, the building wide-angle image can be subjected to distortion calibration processing by geometric correction to obtain a distortion calibrated building wide-angle image.

[0038] 2. Perform target detection processing on the distortion-corrected building wide-angle image to obtain a target description information set. The target description information includes a target feature point set. For example, the detected target can be an air conditioner, a television, or a computer. The accuracy of target modeling affects the usability of the generated updated building area model. Based on the target-based image alignment method, the alignment speed is faster than the full-pixel comparison method. The NanoDet model can be used to perform target detection processing on the distortion-corrected building wide-angle image to obtain a target description information set.

[0039] Second, according to the target description information set corresponding to the building wide-angle image, perform image similarity matching on the building wide-angle images in the building wide-angle image set to generate a building wide-angle image group set. The feature point matching method can be used to determine the feature point matching degree of the target feature point set included in the target description information corresponding to the building wide-angle image, and the matching building wide-angle image is used as the building wide-angle image group.

[0040] Third, for each building wide-angle image group in the building wide-angle image group set, the following optimization steps are performed:

[0041] 1. Randomly select a building wide-angle image from the building wide-angle image group as a base building wide-angle image.

[0042] 2. Perform local image quality optimization on the base building wide-angle image according to each building wide-angle image in the building wide-angle image group except the base building wide-angle image to generate an optimized building wide-angle image. The local area where the target feature point is located in each building wide-angle image in the building wide-angle image group except the base building wide-angle image can be superimposed on the base building wide-angle image, and the pixel value mean value is obtained to obtain the optimized building wide-angle image.

[0043] Step 104, perform image stitching on each optimized building wide-angle image in the optimized building wide-angle image set to obtain a building area stitching image.

[0044] In some embodiments, the execution subject can perform image stitching on each optimized building wide-angle image in the optimized building wide-angle image set to obtain a building area stitching image. For example, the optimized building wide-angle images can be sequentially stitched according to the time sequence of the image frames to obtain the building area stitching image.

[0045] In an actual scenario, the execution subject can perform image stitching on each optimized building wide-angle image in the optimized building wide-angle image set by the following steps:

[0046] In a first step, for each of the optimized building wide-angle images, feature point extraction is performed on the lateral edge region of the optimized building wide-angle image to generate edge region features. The lateral edge region is a rectangular region on both sides of the optimized building wide-angle image. For example, the SIFT (Scale-Invariant Feature Transform) algorithm can be used to perform feature point extraction on the lateral edge region of the optimized building wide-angle image to generate edge region features.

[0047] In a second step, based on the edge region features corresponding to the optimized building wide-angle images, image matching is performed on the optimized building wide-angle images in the set of optimized building wide-angle images, and an image stitching order index sequence is generated. The image stitching order index sequence represents the image stitching order of each of the optimized building wide-angle images in the set of optimized building wide-angle images. For example, the execution subject can perform image matching on the optimized building wide-angle images in the set of optimized building wide-angle images through feature point matching.

[0048] In a third step, through the image stitching order index sequence, image stitching is performed on each of the optimized building wide-angle images in the set of optimized building wide-angle images to obtain a building region stitched image. For example, the optimized building wide-angle image corresponding to index 1 can be stitched on the left side of the optimized building wide-angle image corresponding to index 3, the optimized building wide-angle image corresponding to index 3 can be stitched on the left side of the optimized building wide-angle image corresponding to index 4, and the optimized building wide-angle image corresponding to index 4 can be stitched on the left side of the optimized building wide-angle image corresponding to index 1.

[0049] In step 105, based on the building region stitched image and the pre-trained building information generation model, an original building region model corresponding to the building region is generated.

[0050] In some embodiments, the execution subject can generate an original building region model corresponding to the building region based on the building region stitched image and the pre-trained building information generation model.

[0051] In an actual scenario, the execution subject can generate an original building region model corresponding to the building region by the following steps:

[0052] In the first step, an initial building area model and building area model information are generated according to the above building area spliced image and the above building information generation model. The building area model information includes a set of building area model element information, and the building area model element information includes a region element type, a region element feature vector, and region element position information. The region element position information represents the position of the building area model element corresponding to the building area model element information in the initial building area model. The building information generation model can include an encoder, a decoder, a feature extraction model, and a threshold adjustment network. The encoder includes a first 2D convolutional layer, a first residual convolutional layer, a second residual convolutional layer, a third residual convolutional layer, a fourth residual convolutional layer, a second 2D convolutional layer, a third 2D convolutional layer, and a fourth 2D convolutional layer. A max-pooling layer is arranged between the first 2D convolutional layer and the first residual convolutional block. A max-pooling layer is arranged between the second 2D convolutional layer and the third 2D convolutional layer. A max-pooling layer is arranged between the third 2D convolutional layer and the fourth 2D convolutional layer. The channel number of the first residual convolutional layer is (64, 64, 256). The channel number of the second residual convolutional layer is (128, 128, 256). The channel number of the third residual convolutional layer is (128, 128, 256). The channel number of the fourth residual convolutional layer is (128, 128, 256). The decoder includes four three-dimensional deconvolutional layers connected in series. For example, the decoder can include a first three-dimensional deconvolutional layer, a second three-dimensional deconvolutional layer, a third three-dimensional deconvolutional layer, and a fourth three-dimensional deconvolutional layer. The feature extraction model includes a first three-dimensional convolutional layer, a second three-dimensional convolutional layer, a first fully connected layer, a first attention layer, and a second attention layer. The first attention layer and the second attention layer each include an attention mechanism layer and a three-dimensional deconvolutional layer. The threshold adjustment network can use YOLO as the backbone network. For example, the threshold adjustment network extracts image features from the building area spliced image and converts them into feature images of different feature dimensions for superposition. The region element position information represents the position of the region model element corresponding to the region model element information in the original building area model. The region element type represents the element category of the region model element. The region element feature vector can be a one-dimensional feature vector of the region model element. The region element feature vector can be a one-dimensional feature vector corresponding to the target framed by the predicted anchor box. The region element position information can represent the position of the three-dimensionally reconstructed target in the original building area model. The region element type can be the category of the target framed by the predicted anchor box. For example, the region element position information can be determined by projection.

[0053] The first step can include:

[0054] 1. Based on the encoder included in the above building information generation model, a spliced image encoding feature corresponding to the above building area spliced image is generated.

[0055] 2. The decoder included in the building information generation model generates image decoding features corresponding to the image encoding features of the stitched image.

[0056] 3. The feature extraction model included in the building information generation model generates image extraction features corresponding to the image decoding features.

[0057] 4. The threshold adjustment network included in the building information generation model generates adjustment parameters corresponding to the stitched image of the building area.

[0058] 5. The initial building area model and the building area model information are generated by the adjustment parameters and the image extraction features.

[0059] In the second step, for each building area model element information in the building area model element information set, the following processing steps are performed:

[0060] 1. Determine whether there is a building area model element in the pre-set building area model element library that matches the building area model element information according to the region element type and the region element feature vector included in the building area model element information. The determination of whether there is a building area model element in the pre-set building area model element library that matches the building area model element information includes: first, encoding the region element type included in the building area model element information to generate a region element type encoding vector. Second, concatenate the region element type encoding vector with the region element feature vector included in the building area model element information to obtain a concatenated vector. Then, hash the concatenated vector to obtain a hash vector. Finally, match the hash vector with the vector identifier corresponding to the building area model element in the building area model element library to determine whether there is a building area model element in the building area model element library that matches the building area model element information. The building area model element library can be a database storing pre-constructed and updated building area model elements. The building area model element can be a three-dimensional model of mechanical and electrical equipment. For example, the execution subject can determine whether there is a building area model element in the pre-set building area model element library that matches the building area model element information by data query. The vector identifier can represent the vector of the building area model element.

[0061] 2. In response to the presence of a matching building area model element in the building area model element library, determine the building area model element that matches the building area model element information as a candidate building area model element.

[0062] Thirdly, according to each candidate building area model element, an element update is performed on the initial building area model to generate an updated initial building area model as the original building area model. For example, for each candidate building area model element, an element in the initial building area model corresponding to the candidate building area model element is replaced by the candidate building area model element to generate an updated initial building area model as the original building area model.

[0063] Thus, the feature extraction model is added to the structure of the encoder-decoder to better extract the shape, texture and spatial relationship of the three-dimensional model. At the same time, the attention mechanism is introduced into the feature extraction model to improve the reconstruction quality and details of the model. Then, by introducing the threshold adjustment network, the three-dimensional reconstruction can be selectively performed by controlling the threshold during reconstruction when the building area model is reconstructed, which greatly improves the model accuracy of the building area model obtained by modeling.

[0064] Step 106: Obtain the mechanical and electrical equipment model information corresponding to each mechanical and electrical equipment coding identifier in the mechanical and electrical equipment coding identifier group to obtain a mechanical and electrical equipment model information group.

[0065] In some embodiments, the execution subject can obtain the mechanical and electrical equipment model information corresponding to each mechanical and electrical equipment coding identifier in the mechanical and electrical equipment coding identifier group to obtain a mechanical and electrical equipment model information group. The mechanical and electrical equipment model information includes: a mechanical and electrical equipment model, installation position information, and equipment size information. The mechanical and electrical equipment model can represent a three-dimensional model of the mechanical and electrical equipment. The installation position information can represent the installation position of the mechanical and electrical equipment in the building area. The equipment size information can represent the size (length, width and height) of the mechanical and electrical equipment.

[0066] Step 107: Fill the original building area model according to the mechanical and electrical equipment model information group and the mechanical and electrical equipment coding identifier group to obtain a target building area model.

[0067] In some embodiments, the execution subject can fill the original building area model according to the mechanical and electrical equipment model information group and the mechanical and electrical equipment coding identifier group to obtain a target building area model. For example, each mechanical and electrical equipment model can be added to the original building area model, and each mechanical and electrical equipment model can be placed at the corresponding installation position.

[0068] In an actual scenario, the execution subject can fill the original building area model to obtain a target building area model by the following steps:

[0069] Firstly, for each mechanical and electrical equipment model information in the mechanical and electrical equipment model information group, the following filling steps are performed:

[0070] 1. Fill the electromechanical equipment model included in the electromechanical equipment model information to the installation position corresponding to the installation position information in the original building area model.

[0071] 2. Determine the electromechanical equipment code identifier corresponding to the electromechanical equipment model information as the target electromechanical equipment code identifier.

[0072] 3. Mark the target electromechanical equipment code identifier on the electromechanical equipment model corresponding to the electromechanical equipment model information in the original building area model.

[0073] Secondly, determine the original building area model filled as the target building area model.

[0074] Step 108, according to the target building area model, control the associated installation equipment to install each electromechanical equipment to be installed.

[0075] In some embodiments, the execution subject can control the associated installation equipment to install each electromechanical equipment to be installed according to the target building area model. For example, according to the posture and position of the electromechanical equipment model shown in the target building area model, the associated installation equipment can be controlled to install / put the electromechanical equipment to be installed to the corresponding position in the building area. The installation equipment can include a mechanical arm, a forklift, a carrying device, etc.

[0076] Step 109, in response to determining that each electromechanical equipment is installed, control the electromechanical equipment installation monitoring device to collect the building data of the building area after installation as the target building data, and according to the target building data, verify the position of each installed electromechanical equipment.

[0077] In some embodiments, the execution subject can control the electromechanical equipment installation monitoring device to collect the building data of the building area after installation of each electromechanical equipment is completed as target building data, and perform position verification on each installed electromechanical equipment according to the target building data, in response to determining that the installation of each electromechanical equipment is completed. The target building data can be the building data of the building area collected after installation of each electromechanical equipment is completed, and can include a building wide-angle image and a building wide-angle depth image. The depth image, also known as the distance image or range image, records the distance from the image collection device to each point in the scene, and directly reflects the geometric shape of the visible surface of the scene. This feature makes the depth image have important applications in three-dimensional reconstruction, pose estimation and other fields, because it provides three-dimensional coordinate information of the object. Therefore, the actual installation position information of each electromechanical equipment can be determined by using the characteristics of the depth image. Then, it is determined whether there is a deviation between the actual installation position information of each electromechanical equipment and the corresponding installation position information. If there is a deviation, the installed electromechanical equipment is position corrected.

[0078] The application also provides a computer device 200. As shown in Figure 2 The computer device 200 includes a bus 201, a processor 202, a memory 203 and a communication interface 204. The processor 202, the memory 203 and the communication interface 204 communicate through the bus 201. The computer device 200 can be a server or a terminal device. It should be understood that the number of processors and memories in the computer device 200 is not limited.

[0079] The bus 201 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one line is used to represent the bus, but it does not mean that there is only one bus or only one type of bus. The bus 201 can include a path for transmitting information between each component (for example, the memory 203, the processor 202, the communication interface 204) of the computer device 200.

[0080] The processor 202 can include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0081] The memory 203 can include a volatile memory, such as a random access memory (RAM) for example. The memory 203 can also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD) for example.

[0082] The memory 203 stores executable program codes, and the processor 202 executes the executable program codes to implement the functions of the aforementioned obtaining module, sampling module, determining module, and mixing module respectively, so as to implement the aforementioned method for installation and monitoring of mechanical and electrical equipment applied to a building area. That is, the memory 203 stores instructions for executing the aforementioned method for installation and monitoring of mechanical and electrical equipment applied to a building area.

[0083] The communication interface 204 uses a transceiving module such as, but not limited to, a network interface card or a transceiver, to implement the communication between the computer device 200 and other devices or communication networks.

[0084] The embodiments of the present application also provide a chip, which includes a processor and a data interface. The processor reads instructions stored on the memory through the data interface to execute the aforementioned method for installation and monitoring of mechanical and electrical equipment applied to a building area.

[0085] The embodiments of the present application also provide a computer readable storage medium. The aforementioned computer readable storage medium can be any available medium or data storage device that can be used to store instructions that can be executed by a computer device or a data center containing one or more available media. The aforementioned available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk), etc. The computer readable storage medium includes instructions, and the aforementioned instructions instruct the computer device to execute the aforementioned method for installation and monitoring of mechanical and electrical equipment applied to a building area.

[0086] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present disclosure.

[0087] The above examples are only used to illustrate the technical solutions of the present application, but not to limit the same; although the present application has been described in detail with reference to the foregoing examples, it should be understood by those of ordinary skill in the art that the technical solutions recorded in the foregoing examples can be modified, or some technical features thereof can be replaced by equivalent ones; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for installation and monitoring of mechanical and electrical equipment applied to a building area, comprising: collecting, by a mechanical and electrical equipment installation monitoring device, building data in a building area where mechanical and electrical equipment is to be installed, wherein the building data comprises a set of building wide-angle images corresponding to the building area; encoding each mechanical and electrical equipment to be installed in the building area to generate a mechanical and electrical equipment encoding identification, thereby obtaining a set of mechanical and electrical equipment encoding identifications; generating an optimized set of building wide-angle images from the set of building wide-angle images, wherein the optimized building wide-angle images are images obtained by locally fusing and optimizing multiple building wide-angle images; image stitching each optimized building wide-angle image in the optimized set of building wide-angle images to obtain a building area stitched image; generating an original building area model corresponding to the building area according to the building area stitched image and a pre-trained building information generation model; obtaining mechanical and electrical equipment model information corresponding to each mechanical and electrical equipment encoding identification in the set of mechanical and electrical equipment encoding identifications, thereby obtaining a set of mechanical and electrical equipment model information, wherein the mechanical and electrical equipment model information comprises a mechanical and electrical equipment model, installation location information, and equipment size information; filling the original building area model according to the set of mechanical and electrical equipment model information and the set of mechanical and electrical equipment encoding identifications, thereby obtaining a target building area model; controlling associated installation equipment to install each mechanical and electrical equipment to be installed according to the target building area model; in response to determining that each mechanical and electrical equipment is installed, controlling the mechanical and electrical equipment installation monitoring device to collect building data of the building area after installation is completed as target building data, and performing position verification on each installed mechanical and electrical equipment according to the target building data; wherein generating an original building area model corresponding to the building area comprises: According to the building region splicing image and the building information generation model, an initial building region model and building region model information are generated, wherein the building region model information includes a set of building region model element information, the building region model element information includes a region element type, a region element feature vector and region element position information, the region element position information represents the position of the building region model element corresponding to the building region model element information in the initial building region model, the building information generation model includes an encoder, a decoder, a feature extraction model and a threshold adjustment network, the encoder includes a first 2D convolution layer, a first residual convolution layer, a second residual convolution layer, a third residual convolution layer, a fourth residual convolution layer, a second 2D convolution layer, a third 2D convolution layer and a fourth 2D convolution layer, a max-pooling layer is arranged between the first 2D convolution layer and the first residual convolution block, a max-pooling layer is arranged between the second 2D convolution layer and the third 2D convolution layer, a max-pooling layer is arranged between the third 2D convolution layer and the fourth 2D convolution layer, the decoder includes four three-dimensional deconvolution layers connected in series, the decoder includes a first three-dimensional deconvolution layer, a second three-dimensional deconvolution layer, a third three-dimensional deconvolution layer and a fourth three-dimensional deconvolution layer, the feature extraction model includes a first three-dimensional convolution layer, a second three-dimensional convolution layer, a first fully connected layer, a first attention layer and a second attention layer, the first attention layer and the second attention layer each include an attention mechanism layer and a three-dimensional deconvolution layer; For each building region model element information in the set of building region model element information, the following processing steps are performed: According to the region element type and the region element feature vector included in the building region model element information, it is determined whether there is a building region model element in the pre-set building region model element library that matches the building region model element information; In response to the presence of a matching building region model element in the building region model element library, the building region model element that matches the building region model element information is determined as a candidate building region model element; According to each candidate building region model element, the initial building region model is updated to generate an updated initial building region model as an original building region model.

2. The method for installation and monitoring of electromechanical devices applied to a building area according to claim 1, characterized in that, The generation of the initial building region model and the building region model information according to the building region splicing image and the building information generation model includes: Based on the encoder included in the building information generation model, splicing image encoding features corresponding to the building region splicing image are generated; Through the decoder included in the building information generation model, image decoding features corresponding to the splicing image encoding features are generated; Through the feature extraction model included in the building information generation model, image extraction features corresponding to the image decoding features are generated; Through the threshold adjustment network included in the building information generation model, adjustment parameters corresponding to the building region splicing image are generated; Through the adjustment parameters and the image extraction features, the initial building region model and the building region model information are generated.

3. The method for installation and monitoring of electromechanical devices applied to a building area according to claim 1, characterized in that, The original building area model is filled according to the electromechanical equipment model information set and the electromechanical equipment code identification set, to obtain a target building area model, comprising: For each electromechanical equipment model information in the electromechanical equipment model information set, the following filling steps are performed: An electromechanical equipment model included in the electromechanical equipment model information is filled into an installation position corresponding to the installation position information in the original building area model; An electromechanical equipment code identification corresponding to the electromechanical equipment model information is determined as a target electromechanical equipment code identification; The target electromechanical equipment code identification is marked on an electromechanical equipment model corresponding to the electromechanical equipment model information in the original building area model; The original building area model after filling is determined as the target building area model.

4. A computer device, wherein, The computer device comprises a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the method according to any one of claims 1-3.

5. A computer readable storage medium, wherein, The computer readable storage medium stores a computer program, wherein the computer program, when executed by the processor, implements the steps of the method according to any one of claims 1-3.

Images