Method, device and equipment for automatically arranging spray heads and storage medium

Abstract

The invention discloses a method, a device and equipment for automatically arranging spray headers and a storage medium. The method comprises the following steps: determining an arrangement area in which the spray headers need to be arranged from a target building model; performing three-dimensional gridding sampling on the arrangement area to obtain a plurality of spatial feature points, and determining a feature value of each spatial feature point under a preset feature item to form a corresponding feature vector; inputting the feature vector of each spatial feature point into a pre-trained prediction model, and obtaining a spray header arrangement probability of each spatial feature point output by the prediction model; based on the spray header arrangement probability of each spatial feature point, screening out arrangement point locations from all the spatial feature points, and arranging a spray header on each arrangement point location; according to the invention, the accurate and efficient full-automatic arrangement of the spray heads can be realized, and the dependence on manual design and model precision is obviously reduced.

Description

Technical Field

[0001] This invention relates to the field of computer-aided design technology, and in particular to a method, apparatus, device, and storage medium for automatically arranging sprinkler heads. Background Technology

[0002] In the field of building fire protection engineering design, the proper placement of sprinkler heads is a crucial aspect of ensuring fire safety. Currently, the industry still largely relies on designers manually positioning and placing sprinkler heads in building information models according to design specifications. This method is not only inefficient and tedious, but also highly dependent on the designer's personal experience, consuming significant manpower and making it difficult to guarantee consistency in design speed and quality. To improve efficiency, some software tools with automatic placement functions have emerged on the market. However, most of these existing tools are based on fixed geometric algorithms, which have significant limitations in applicability. They can usually only handle regular quadrilateral areas such as rectangles and trapezoids well. When faced with complex polygons, arcs, or irregular building spaces, their placement effect is often unsatisfactory, or they may even fail to complete automatic placement. Furthermore, even if placement is successful, the accuracy of the results is poor, often resulting in unreasonable point locations and non-compliant spacing, still requiring designers to make extensive manual adjustments and corrections.

[0003] Therefore, how to overcome the shortcomings of existing technologies and provide an automatic sprinkler head arrangement scheme that can intelligently adapt to different spatial forms, has high layout accuracy, and can significantly improve design efficiency has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus, device, and storage medium for automatically arranging sprinkler heads, which can achieve precise and efficient fully automatic arrangement of sprinkler heads, significantly reducing the reliance on manual design and model accuracy.

[0005] According to one aspect of the present invention, a method for automatically arranging sprinkler heads is provided, the method comprising: Identify the areas where sprinkler heads need to be placed from the target building model; The arrangement area is sampled in three dimensions to obtain multiple spatial feature points, and the feature value of each spatial feature point under a preset feature term is determined to form a corresponding feature vector; The feature vector of each spatial feature point is input into the pre-trained prediction model, and the sprinkler head arrangement probability of each spatial feature point output by the prediction model is obtained. Based on the sprinkler head placement probability of each spatial feature point, placement points are selected from all spatial feature points, and sprinkler heads are placed at each placement point.

[0006] Optionally, the step of performing three-dimensional mesh sampling on the arrangement area to obtain multiple spatial feature points includes: Obtain the spatial outline of the layout area enclosed by wall elements and column elements; Determine the three-dimensional bounding box of the spatial contour; Within the three-dimensional bounding box, a grid is divided along the X, Y, and Z axes at a preset sampling interval, and the grid intersections are used as the spatial feature points.

[0007] Optionally, determining the feature value of each spatial feature point under a preset feature term to form a corresponding feature vector includes: Determine a first feature value to characterize whether the spatial feature point is located in the area where sprinkler heads are prohibited from being placed. A second feature value is determined to characterize whether there are obstacles around the spatial feature point that would impede the installation and use of the sprinkler head; A third characteristic value is determined to characterize the fire risk level of the area where the spatial feature point is located; The first feature value, the second feature value, and the third feature value are combined to form the feature vector of the spatial feature point.

[0008] Optionally, the step of selecting placement points from all spatial feature points based on the sprinkler head placement probability of each spatial feature point, and placing sprinkler heads at each placement point, includes: Spatial feature points with a sprinkler head placement probability greater than a preset probability threshold are selected as candidate points. Filter out the points located outside the actual outline of the arrangement area from all candidate points to obtain the arrangement points.

[0009] Optionally, before determining the area from the target building model where the sprinkler heads need to be placed, the method further includes: Obtain multiple historical building models with correctly positioned sprinkler heads; Multiple sample space regions enclosed by wall and column elements are extracted from each historical building model; Three-dimensional mesh sampling was performed on each sample space region to obtain multiple sample feature points, and the feature vector of each sample feature point and the label used to characterize whether a sprinkler head was actually placed at the sample feature point were determined. The prediction model is obtained by training a preset neural network model with the feature vector of each sample feature point as input and the label as the expected output.

[0010] Optionally, the step of training a preset neural network model using the feature vector of each sample feature point as input and the label as the expected output to obtain the prediction model includes: During the training of the neural network model, the model parameters are optimized by minimizing the composite loss function; The composite loss function is obtained by weighted combination of the following three parts: a basic loss part for calculating the difference between the predicted sprinkler head placement probability and the corresponding label; a distance loss part for calculating the spatial distance between the predicted sprinkler head position and the actual sprinkler head position; and a quantity loss part for calculating the absolute difference between the predicted number of sprinkler heads and the actual number of sprinkler heads.

[0011] To achieve the above objectives, the present invention also provides an apparatus for automatically arranging sprinkler heads, the apparatus comprising: The determination module is used to identify the areas where sprinkler heads need to be placed from the target building model; The sampling module is used to perform three-dimensional mesh sampling on the arrangement area to obtain multiple spatial feature points, and to determine the feature value of each spatial feature point under a preset feature term to form a corresponding feature vector. The prediction module is used to input the feature vector of each spatial feature point into the pre-trained prediction model and obtain the sprinkler head arrangement probability of each spatial feature point output by the prediction model. The layout module selects layout points from all spatial feature points based on the sprinkler head layout probability of each spatial feature point, and then places sprinkler heads at each layout point.

[0012] Optionally, the device further includes a training module for: Obtain multiple historical building models with correctly positioned sprinkler heads; Multiple sample space regions enclosed by wall and column elements are extracted from each historical building model; Three-dimensional mesh sampling was performed on each sample space region to obtain multiple sample feature points, and the feature vector of each sample feature point and the label used to characterize whether a sprinkler head was actually placed at the sample feature point were determined. The prediction model is obtained by training a preset neural network model with the feature vector of each sample feature point as input and the label as the expected output.

[0013] To achieve the above objectives, the present invention also provides a computer device, which specifically includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for automatically arranging sprinkler heads described above.

[0014] To achieve the above objectives, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for automatically arranging sprinkler heads described above.

[0015] The method, apparatus, equipment, and storage medium for automatically arranging sprinkler heads provided by this invention transform the arrangement problem into intelligent decision-making based on a three-dimensional grid, enabling precise handling of areas with various complex and irregular shapes, thus greatly expanding the applicability of the automatic arrangement function. Furthermore, by using deep learning algorithms to train the model, the model can deeply learn and internalize fire protection arrangement standards, significantly improving the accuracy and rationality of the arrangement scheme, and the output results are more in line with actual engineering needs. This invention can achieve precise and efficient fully automatic sprinkler head arrangement, significantly reducing reliance on manual design and model accuracy. Attached Figure Description

[0016] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a schematic diagram of an optional process for the automatic sprinkler head arrangement method provided in Embodiment 1; Figure 2 A schematic diagram of the parameter setting interface provided in Embodiment 1; Figure 3 This is a schematic diagram of the complete process of automatically deploying sprinkler heads based on deep learning, as provided in Example 1. Figure 4 This is a schematic diagram showing the result of the automatic sprinkler head arrangement provided in Example 1; Figure 5 This is a flowchart illustrating the preprocessing of historical sample data provided in Example 1. Figure 6 This is a visual representation of the historical sample data provided in Example 1; Figure 7 This is a schematic diagram illustrating the complete model training process provided in Example 1; Figure 8 This is a schematic diagram of an optional component structure of the automatic sprinkler head arrangement device provided in Embodiment 2; Figure 9 This is a schematic diagram of an optional hardware structure for the computer device provided in Embodiment 3. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0018] Example 1 This invention provides a method for automatically arranging sprinkler heads, such as... Figure 1 As shown, the method specifically includes the following steps: Step S101: Determine the area where sprinkler heads need to be placed from the target building model.

[0019] The target building model can be BIM (Building Information Modeling); the layout area is a three-dimensional space, and the layout area can be a spatial area selected by the user from the target building model, or a closed area enclosed by wall elements and column elements automatically identified from the target building model.

[0020] Step S102: Perform three-dimensional mesh sampling on the arrangement area to obtain multiple spatial feature points, and determine the feature value of each spatial feature point under the preset feature terms to form a corresponding feature vector.

[0021] In this embodiment, the arrangement area can be sampled in a grid according to a preset sampling interval to obtain multiple spatial feature points. In addition, the feature vector of the spatial feature point can include at least one of the following: a prohibited arrangement feature to characterize whether the spatial feature point is located in the prohibited arrangement area of ​​the sprinkler head, an obstacle feature to characterize whether there are obstacles around the spatial feature point that hinder the installation and use of the sprinkler head, and a risk level feature to characterize the fire risk level of the arrangement area. Of course, in practical applications, the spatial feature point can also include features of other dimensions, such as a type feature to characterize the type of sprinkler head to be arranged, a flow feature to characterize the flow coefficient of the sprinkler head, etc., which are not specifically limited here.

[0022] Step S103: Input the feature vector of each spatial feature point into the pre-trained prediction model, and obtain the sprinkler head arrangement probability of each spatial feature point output by the prediction model.

[0023] In this embodiment, a specified neural network model can be trained in advance using historical sample data to obtain a prediction model. The input of the prediction model is the feature vector of each spatial feature point in the arrangement area, and the output of the prediction model is the probability of the sprinkler head arrangement corresponding to each spatial feature point. Preferably, the value of the sprinkler head arrangement probability is between 0 and 1. The closer the sprinkler head arrangement probability is to 0, the lower the probability of the sprinkler head being arranged at the spatial feature point. The closer the sprinkler head arrangement probability is to 1, the higher the probability of the sprinkler head being arranged at the spatial feature point.

[0024] Step S104: Based on the sprinkler head placement probability of each spatial feature point, select placement points from all spatial feature points, and place sprinkler heads at each placement point.

[0025] Preferably, spatial feature points with a sprinkler head placement probability greater than a preset probability threshold can be set as placement points.

[0026] In this embodiment, by transforming the layout problem into intelligent decision-making based on three-dimensional grid points, it can accurately handle areas with various complex and irregular shapes, greatly expanding the applicability of the automatic layout function. Furthermore, by training the model using deep learning algorithms, the model can deeply learn and internalize fire protection layout specifications, significantly improving the accuracy and rationality of the layout scheme, and the output results are more in line with actual engineering needs. This embodiment can achieve precise and efficient fully automatic sprinkler head layout, significantly reducing reliance on manual design and model accuracy.

[0027] Specifically, step S102, which involves performing three-dimensional mesh sampling on the arrangement area to obtain multiple spatial feature points, includes: Step A1: Obtain the spatial outline of the layout area enclosed by wall elements and column elements; Step A2: Determine the three-dimensional bounding box of the spatial contour; Step A3: Within the three-dimensional bounding box, divide the area into grids along the X, Y, and Z axes at preset sampling intervals, and use the grid intersections as the spatial feature points.

[0028] Preferably, the preset sampling interval is 200mm.

[0029] Furthermore, step S102, which involves determining the feature value of each spatial feature point under a preset feature term to form a corresponding feature vector, specifically includes: Step A4: Determine a first feature value to characterize whether the spatial feature point is located in the sprinkler head prohibited placement area; Among them, the restricted area is defined as an area where sprinkler heads should not be placed, based on specifications or experience; in the feature vector, binary values ​​are used to identify whether the spatial feature point is located within the restricted area; preferably, it is determined whether the distance between the spatial feature point and any wall element is less than 100mm. If so, the first feature value is set to 1; otherwise, the first feature value is set to 0.

[0030] Step A5: Determine a second feature value to characterize whether there are obstacles around the spatial feature point that would hinder the installation and use of the sprinkler head; Here, obstacles refer to building structures within the layout area that physically block the installation of sprinkler heads or affect their spraying range, such as walls, beams, and columns; in the feature vector, they are represented by binary values; preferably, it is determined whether there are wall elements, beam elements, or column elements at the spatial feature points. If so, the second feature value is set to 1; otherwise, the second feature value is set to 0.

[0031] Step A6: Determine the third characteristic value used to characterize the fire risk level of the area where the spatial feature point is located; Preferred, such as Figure 2 The image shows the parameter setting interface, where users can input the layout algorithm, layout area, and layout parameters. The layout parameters include the hazard level (i.e., fire risk level) of the layout area. The system retrieves the fire risk level that the user has set for the layout area in advance and sets the third feature value as the fire risk level. The third feature value is represented by an integer.

[0032] Step A7: Combine the first feature value, the second feature value, and the third feature value to form the feature vector of the spatial feature point.

[0033] In this embodiment, steps A1 to A7 above can discretize the complex building space into standard three-dimensional grid points, and assign a feature vector with a unified structure to each point, effectively solving the core technical problem that unstructured BIM model data cannot be directly processed by deep learning models. This preprocessing process digitizes information on components such as walls and columns, as well as design specifications (e.g., no-go zones within 100mm of a wall), into feature vectors containing obstacles, no-go zones, and hazard levels, providing standardized input for the neural network, enabling it to consider multi-dimensional spatial constraints simultaneously.

[0034] Furthermore, step S104, which involves selecting sprinkler head placement locations from all spatial feature points based on the sprinkler head placement probability for each spatial feature point, and placing sprinkler heads at each placement location, specifically includes: Step B1: Select spatial feature points with a sprinkler head placement probability greater than a preset probability threshold as candidate locations; Step B2: Filter out the points located outside the actual outline of the arrangement area from all candidate points to obtain the arrangement points.

[0035] In this embodiment, since the actual layout area may have various shapes, when a polygonal layout area is obtained, the bounding box of the polygonal area is first obtained, and then feature points are sampled on the bounding box at intervals of 200mm. However, this causes a problem: many points located outside the polygon are also collected. From a business logic perspective, these points should not be used to place sprinkler heads. Therefore, after obtaining the layout result of the model, these points should be filtered to improve the final display effect.

[0036] like Figure 3 The diagram shows the complete flowchart of an automated sprinkler head deployment system based on deep learning. The designer selects the deployment area and sets the deployment parameters. The system first performs grid sampling on the deployment area to obtain multiple feature points, and then inputs the feature vector of each feature point into a trained neural network prediction model to output the prediction result. The system deploys the sprinkler heads based on the prediction result. The designer can also fine-tune the automatically deployed sprinkler heads to meet business requirements. Figure 4 The image shown is a schematic diagram illustrating the result of automatically deploying sprinkler heads. Figure 4 The circles in the diagram represent the locations where the points are arranged.

[0037] Furthermore, prior to step S103, the method further includes: Step C1: Obtain multiple historical building models with correctly arranged sprinkler heads.

[0038] Step C2: Extract multiple sample space regions enclosed by wall elements and column elements from each historical building model; In this embodiment, it is necessary to collect a large number of historical projects in which the sprinkler heads have been arranged as required. A historical project may contain multiple spatial areas, and data will be collected on a spatial area basis, that is, a spatial area will be used as a sample.

[0039] Step C3: Perform three-dimensional mesh sampling on each sample space region to obtain multiple sample feature points, and determine the feature vector of each sample feature point and the label used to characterize whether a sprinkler head is actually placed at the sample feature point; In this embodiment, a historical project is stored in the form of a BIM model. Such data cannot be directly learned by a neural network, so a preprocessing algorithm is needed to extract useful information from the BIM model. The processing logic of the preprocessing algorithm is as follows: Figure 5As shown, firstly, the polygonal outline enclosed by walls and columns in the space is obtained on a spatial basis, and the bounding box of the polygonal outline is generated; then, sample feature points are collected at 200mm intervals in the X, Y, and Z axes; then, for each sample feature point, its feature vector is calculated, which contains the following three dimensions: 1) Restricted area layout feature: Determine whether the sample feature point is less than 100mm away from any wall, if so, it is 1, otherwise it is 0; 2) Obstacle feature: Determine whether the coordinates of the sample feature point contain walls, beams, or columns, if so, it is 1, otherwise it is 0; 3) Risk level feature: Determined according to the fire risk level of the area where the sample feature point is located, and represented as an integer; finally, a corresponding label needs to be generated for each sample feature point. When the coordinates of the sample feature point contain a sprinkler head, the label is 1, otherwise it is 0. It should also be noted that the "restricted area layout feature" mentioned above is equivalent to the "first feature value", the "obstacle feature" is equivalent to the "second feature value", and the "risk level feature" is equivalent to the "third feature value". It should be noted that the higher the fire risk level, the denser the sprinkler head arrangement should be. In order for the model to adapt to the arrangement requirements of different fire risk levels, this information needs to be input into the model so that the model can learn the relationship between sprinkler head spacing and fire risk level.

[0040] Additionally, the feature extraction results of all sample feature points are serialized into a JSON file for storage, resulting in a dataset; the visualization of the JSON file content is shown below. Figure 6 As shown, in Figure 6 In the diagram, red lines represent areas with obstacles, blue lines represent areas where sprinkler heads are prohibited from being installed, yellow dots represent the actual locations of sprinkler heads, and gray represents the fire risk level (the higher the risk level, the darker the gray).

[0041] Step C4: Using the feature vector of each sample feature point as input and the label as the expected output, train the preset neural network model to obtain the prediction model; Preferably, the preset neural network model is a CNN (Convolutional Neural Network) model.

[0042] In this embodiment, the model training process represented by steps C1 to C4 above can transform a large number of historical BIM models with correctly arranged sprinkler heads into a standardized mesh feature point dataset. This solves the technical problems of deep learning models lacking high-quality training data and being unable to directly learn complex layout rules from unstructured BIM models. By accurately generating feature vectors and corresponding labels for each sample feature point, including placement restrictions, obstacles, and risk levels, the designer's experience and fire protection regulations are digitized into learnable targets for the model. This process enables the CNN model to automatically summarize the inherent rules of sprinkler head layout from the data, rather than relying on manually written fixed rules. The final trained model can intelligently adapt to different spatial forms, achieving accurate and standardized automatic layout, significantly reducing the algorithm's dependence on specific spatial shapes and the workload of subsequent manual adjustments.

[0043] Furthermore, step C4 specifically includes: During the training of the neural network model, the model parameters are optimized by minimizing the composite loss function; The composite loss function is obtained by weighted combination of the following three parts: a basic loss part for calculating the difference between the predicted sprinkler head placement probability and the corresponding label; a distance loss part for calculating the spatial distance between the predicted sprinkler head position and the actual sprinkler head position; and a quantity loss part for calculating the absolute difference between the predicted number of sprinkler heads and the actual number of sprinkler heads.

[0044] In this embodiment, the performance of the current model can be evaluated using a loss function during training. A smaller loss indicates a better model performance, and vice versa. Simultaneously, the model is also optimized during training based on the calculation results of the loss function. Therefore, the design of the loss function is crucial to the final result. Preferably, the loss function used in this embodiment includes the following three parts: 1) Base loss: calculating the difference between the model's predicted result and the actual result using the cross-entropy function; 2) Distance loss: calculating the distance between the predicted sprinkler heads and the actual sprinkler heads, using the distance as the loss; the larger the distance, the larger the loss; as the distance between the predicted and actual sprinkler heads gradually decreases, the loss gradually decreases; 3) Quantity loss: calculating the absolute value of the predicted and actual sprinkler head quantities; the larger the absolute value, the larger the loss; otherwise, the loss gradually decreases.

[0045] In this embodiment, after designing the neural network model and loss function, multiple rounds of training and validation are performed using the sample dataset to obtain a predictive model that has learned the layout specifications.

[0046] In addition, the diversity of sample data is an important factor in ensuring the training effect. Therefore, the acquisition of multiple historical building models with correctly arranged sprinkler heads in step C1 specifically includes: rotating the acquired historical model along the Z-axis at multiple angles to obtain multiple sample building models, and then performing the above steps C2 to C4 based on all the obtained sample building models.

[0047] like Figure 7 The diagram shows the complete process of training a deep learning-based model. In the model training process, historical items are first collected, and then features are extracted from the historical items in spatial units to generate a training sample dataset. The preset model is then trained using a preset model and a constructed composite loss function to obtain the final prediction model.

[0048] In this embodiment, the building space is discretized into standard three-dimensional grid points, and each point is assigned a unified structured feature vector to achieve a digital representation of the layout environment. During model training, a composite loss function is used to guide the neural network model to optimize the accuracy of the sprinkler head positions and the rationality of their number. To obtain better training results, the diversity of training data is a crucial factor affecting the training effect. The extracted training model is randomly rotated, and the rotated model is used as new training input to enrich the sample data.

[0049] Example 2 This invention provides an automatic sprinkler head arrangement device, such as... Figure 8 As shown, the device specifically includes the following components: The determination module 801 is used to determine the area where sprinkler heads need to be placed from the target building model; The sampling module 802 is used to perform three-dimensional mesh sampling on the arrangement area to obtain multiple spatial feature points, and to determine the feature value of each spatial feature point under a preset feature term to form a corresponding feature vector. The prediction module 803 is used to input the feature vector of each spatial feature point into the pre-trained prediction model and obtain the sprinkler head arrangement probability of each spatial feature point output by the prediction model. The arrangement module 804 is used to select arrangement points from all spatial feature points based on the sprinkler head arrangement probability of each spatial feature point, and to arrange sprinkler heads at each arrangement point.

[0050] Specifically, the sampling module 802 is used for: Obtain the spatial outline of the layout area enclosed by wall elements and column elements; Determine the three-dimensional bounding box of the spatial contour; Within the three-dimensional bounding box, a grid is divided along the X, Y, and Z axes at a preset sampling interval, and the grid intersections are used as the spatial feature points.

[0051] Furthermore, the sampling module 802 is also used for: Determine a first feature value to characterize whether the spatial feature point is located in the area where sprinkler heads are prohibited from being placed. A second feature value is determined to characterize whether there are obstacles around the spatial feature point that would impede the installation and use of the sprinkler head; A third characteristic value is determined to characterize the fire risk level of the area where the spatial feature point is located; The first feature value, the second feature value, and the third feature value are combined to form the feature vector of the spatial feature point.

[0052] Furthermore, the arrangement module 804 is specifically used for: Spatial feature points with a sprinkler head placement probability greater than a preset probability threshold are selected as candidate points. Filter out the points located outside the actual outline of the arrangement area from all candidate points to obtain the arrangement points.

[0053] In addition, the device also includes a training module for: Obtain multiple historical building models with correctly positioned sprinkler heads; Multiple sample space regions enclosed by wall and column elements are extracted from each historical building model; Three-dimensional mesh sampling was performed on each sample space region to obtain multiple sample feature points, and the feature vector of each sample feature point and the label used to characterize whether a sprinkler head was actually placed at the sample feature point were determined. The prediction model is obtained by training a preset neural network model with the feature vector of each sample feature point as input and the label as the expected output.

[0054] Furthermore, the training module is specifically used for: During the training of the neural network model, the model parameters are optimized by minimizing the composite loss function; The composite loss function is obtained by weighted combination of the following three parts: a basic loss part for calculating the difference between the predicted sprinkler head placement probability and the corresponding label; a distance loss part for calculating the spatial distance between the predicted sprinkler head position and the actual sprinkler head position; and a quantity loss part for calculating the absolute difference between the predicted number of sprinkler heads and the actual number of sprinkler heads.

[0055] Example 3 This embodiment also provides a computer device, such as a smartphone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server, or cabinet server (including a standalone server or a server cluster composed of multiple servers), etc., capable of executing programs. Figure 9 As shown, the computer device 90 in this embodiment includes, but is not limited to, a memory 901 and a processor 902 that are communicatively connected to each other via a system bus. It should be noted that... Figure 9 Only a computer device 90 with components 901-902 is shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0056] In this embodiment, the memory 901 (i.e., the readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 901 may be an internal storage unit of the computer device 90, such as the hard disk or memory of the computer device 90. In other embodiments, the memory 901 may also be an external storage device of the computer device 90, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Of course, the memory 901 may include both the internal storage unit and the external storage device of the computer device 90. In this embodiment, the memory 901 is typically used to store the operating system and various application software installed on the computer device 90. Furthermore, the memory 901 can also be used to temporarily store various types of data that have been output or will be output.

[0057] In some embodiments, processor 902 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. This processor 902 is typically used to control the overall operation of computer device 90.

[0058] Specifically, in this embodiment, the processor 902 is used to execute a program for an automatic sprinkler head arrangement method stored in the memory 901. When the program for the automatic sprinkler head arrangement method is executed, it performs the following steps: Identify the areas where sprinkler heads need to be placed from the target building model; The arrangement area is sampled in three dimensions to obtain multiple spatial feature points, and the feature value of each spatial feature point under a preset feature term is determined to form a corresponding feature vector; The feature vector of each spatial feature point is input into the pre-trained prediction model, and the sprinkler head arrangement probability of each spatial feature point output by the prediction model is obtained. Based on the sprinkler head placement probability of each spatial feature point, placement points are selected from all spatial feature points, and sprinkler heads are placed at each placement point.

[0059] For a detailed description of the above method steps, please refer to Example 1. This example will not be repeated here.

[0060] Example 4 This embodiment also provides a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, app store, etc., which stores a computer program. When the computer program is executed by a processor, it implements the following method steps: Identify the areas where sprinkler heads need to be placed from the target building model; The arrangement area is sampled in three dimensions to obtain multiple spatial feature points, and the feature value of each spatial feature point under a preset feature term is determined to form a corresponding feature vector; The feature vector of each spatial feature point is input into the pre-trained prediction model, and the sprinkler head arrangement probability of each spatial feature point output by the prediction model is obtained. Based on the sprinkler head placement probability of each spatial feature point, placement points are selected from all spatial feature points, and sprinkler heads are placed at each placement point.

[0061] For a detailed description of the above method steps, please refer to the first embodiment. This embodiment will not repeat the details here.

[0062] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0063] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0064] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0065] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method of automatically arranging a showerhead, characterized by, The method comprises: determining a layout area requiring arrangement of a sprinkler head from a target building model; performing three-dimensional grid sampling on the layout area to obtain a plurality of spatial feature points, and determining a feature value of each spatial feature point under a preset feature item to form a corresponding feature vector; inputting the feature vector of each spatial feature point into a pre-trained prediction model, and obtaining a sprinkler head arrangement probability of each spatial feature point output by the prediction model; based on the sprinkler head arrangement probability of each spatial feature point, screening arrangement points from all spatial feature points, and arranging a sprinkler head at each arrangement point.

2. The method of automatically arranging a spray head of claim 1, wherein, The three-dimensional grid sampling on the layout area to obtain a plurality of spatial feature points comprises: obtaining a space contour surrounded by wall elements and column elements in the layout area; determining a three-dimensional bounding box of the space contour; performing grid division in the three-dimensional bounding box along the X-axis, Y-axis and Z-axis directions at a preset sampling interval, and taking the grid intersection points as the spatial feature points.

3. The method of automatically arranging a spray head of claim 1, wherein, The determination of the feature value of each spatial feature point under the preset feature item to form the corresponding feature vector comprises: determining a first feature value for representing whether the spatial feature point is in a sprinkler head prohibited arrangement area; determining a second feature value for representing whether there is an obstacle around the spatial feature point that hinders installation and use of the sprinkler head; determining a third feature value for representing a fire risk level of the area where the spatial feature point is located; combining the first feature value, the second feature value and the third feature value into the feature vector of the spatial feature point.

4. The method of automatically arranging a spray head of claim 1, wherein, The screening of arrangement points from all spatial feature points based on the sprinkler head arrangement probability of each spatial feature point, and the arrangement of a sprinkler head at each arrangement point comprise: screening spatial feature points with a sprinkler head arrangement probability greater than a preset probability threshold as candidate points; filtering out points outside an actual contour of the layout area from all candidate points to obtain arrangement points.

5. The method of automatically arranging a showerhead according to any one of claims 1 to 4, wherein, Before the determination of the layout area requiring arrangement of a sprinkler head from the target building model, the method further comprises: obtaining a plurality of historical building models with correctly arranged sprinkler heads; extracting a plurality of sample space areas surrounded by wall elements and column elements from each historical building model respectively; performing three-dimensional grid sampling on each sample space area to obtain a plurality of sample feature points, and determining a feature vector of each sample feature point and a label for representing whether a sprinkler head is actually arranged at the sample feature point; training a preset neural network model with the feature vector of each sample feature point as input and the label as expected output to obtain the prediction model.

6. The method of automatically arranging a showerhead of claim 5, wherein, The training of the preset neural network model with the feature vector of each sample feature point as input and the label as expected output to obtain the prediction model comprises: in the process of training the neural network model, optimizing model parameters by minimizing a composite loss function; The composite loss function is obtained by weighted combination of three parts: a basic loss part for calculating the difference between the predicted spray head arrangement probability and the corresponding label; a distance loss part for calculating the spatial distance between the predicted spray head position and the actual spray head position; and a quantity loss part for calculating the absolute difference between the predicted spray head quantity and the actual spray head quantity.

7. An apparatus for automatically arranging a showerhead, the apparatus comprising: The device comprises: A determination module configured to determine an arrangement area requiring arrangement of spray heads from a target building model; A sampling module configured to perform three-dimensional grid sampling on the arrangement area to obtain a plurality of spatial feature points, and determine a feature value of each spatial feature point under a preset feature item to form a corresponding feature vector; A prediction module configured to input the feature vector of each spatial feature point into a pre-trained prediction model, and obtain a spray head arrangement probability of each spatial feature point output by the prediction model; An arrangement module configured to screen arrangement points from all spatial feature points based on the spray head arrangement probability of each spatial feature point, and arrange spray heads at each arrangement point.

8. The apparatus of claim 7, wherein, The device further comprises a training module configured to: Obtain a plurality of historical building models in which spray heads have been correctly arranged; Extract a plurality of sample space areas surrounded by wall elements and column elements from each historical building model respectively; Perform three-dimensional grid sampling on each sample space area to obtain a plurality of sample feature points, and determine a feature vector of each sample feature point and a label for representing whether a spray head is actually arranged at the sample feature point; Train a preset neural network model with the feature vector of each sample feature point as input and the label as expected output, to obtain the prediction model.

9. A computer device comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images