A construction management method and system for artificial intelligence computing power centers

Abstract

This invention provides a construction management method and system for an artificial intelligence computing center, relating to the field of data processing technology. The method includes: constructing an original BIM model of the artificial intelligence computing center; reconstructing each component in the original BIM model using a mesh; performing similarity mapping on each component after mesh reconstruction and merging and storing similar components; decomposing the construction tasks of the artificial intelligence computing center according to the merged and stored BIM model; collaboratively allocating the decomposed tasks to generate a construction plan; simulating the construction process using an artificial neural network to predict the completion time, completion cost, and importance of each task in the construction plan; optimizing the construction plan with the goal of reducing the total construction time and total construction cost and improving the stability of the construction plan; and constructing the artificial intelligence computing center according to the optimized construction plan.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a construction and management method and system for an artificial intelligence computing center. Background Technology

[0002] Intelligent computing centers refer to infrastructure that provides intelligent computing power by building intelligent computing server clusters based on chips such as GPUs and FPGAs. Currently, my country is very active in research and development of building construction, which is broadly categorized into traditional buildings (reinforced concrete), prefabricated buildings, and steel structure buildings. For artificial intelligence computing center projects, rapid deployment and operation are crucial to maximizing efficiency. Therefore, selecting a suitable structural form and utilizing a digital management model are essential to ensuring construction economy while minimizing the construction period.

[0003] As various industries in my country continue to increase their demands for computing power, the construction cycle of artificial intelligence computing center projects is becoming shorter and shorter. At present, the traditional construction management model can no longer guarantee the construction period requirements of new buildings, making it impossible for traditional construction management to play its normal role in production. The inability to guarantee the building's usage time will cause huge losses to the upstream and downstream industries of computing power application under the new situation.

[0004] Modern technologies such as BIM (Building Information Modeling) have been gradually introduced into the construction industry to improve efficiency and quality through digitalization. However, with the continuous increase in building scale, especially in the construction of ultra-large-scale buildings such as artificial intelligence computing centers, existing construction technologies and the application of BIM models still face significant challenges. Although BIM can comprehensively display the design and construction information of a building project, when it comes to complex and large-scale projects, the sheer size and complexity of BIM models make it particularly difficult to use them to develop detailed construction plans during the construction process. Furthermore, current BIM-based construction plan optimization technologies often focus on reducing costs and shortening the construction period, neglecting the stability of the construction plan in the face of unforeseen circumstances. This means that in actual construction, when unexpected events occur, the originally planned construction schedule may be disrupted, failing to meet deadlines, or even resulting in resource waste and cost overruns. Summary of the Invention

[0005] To address the challenges posed by the massive size and complex data of existing BIM models, which make it extremely difficult to develop detailed construction plans during the construction process, current BIM-based construction plan optimization technologies often focus on reducing costs and shortening the construction period, neglecting the stability of the construction plan in the face of unforeseen circumstances. This can lead to disruptions in the actual construction process when unexpected events occur, resulting in delays, resource waste, and cost overruns. This invention provides a construction management method and system for artificial intelligence computing centers.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] First aspect

[0008] This invention provides a construction management method for an artificial intelligence computing center, comprising:

[0009] S1: Constructing the original BIM model for the artificial intelligence computing center;

[0010] S2: Perform mesh reconstruction on each component in the original BIM model;

[0011] S3: Perform similarity mapping on each component after mesh reconstruction, and merge and store similar components;

[0012] S4: Based on the merged and stored BIM model, the construction tasks of the artificial intelligence computing center are decomposed.

[0013] S5: Coordinate and allocate the decomposed tasks to generate a construction plan;

[0014] S6: Using artificial neural networks, simulate the construction process and predict the completion time, cost, and importance of each task in the construction plan;

[0015] S7: Optimize the construction plan with the goal of reducing the total construction time and cost and improving the stability of the construction plan;

[0016] S8: Construct the artificial intelligence computing center according to the optimized construction plan.

[0017] Second aspect

[0018] This invention provides a construction management system for an artificial intelligence computing center, comprising:

[0019] processor;

[0020] A memory storing computer-readable instructions, which, when executed by the processor, implement the construction and management method for the artificial intelligence computing center as described in the first aspect.

[0021] Third aspect

[0022] The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the construction and management method for the artificial intelligence computing center as described in the first aspect.

[0023] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following:

[0024] (1) In this embodiment of the invention, by reconstructing the BIM model into a grid and merging and storing similar components, the complexity and volume of the BIM model are reduced, thereby effectively reducing the consumption of computing and storage resources. This process enables the construction team to obtain the required model information more quickly, improves the efficiency of the construction preparation stage, and helps to quickly formulate a construction plan.

[0025] (2) In this embodiment of the invention, the construction process is simulated using an artificial neural network, which can predict the completion time, cost, and importance of each task based on historical data and current conditions. This predictive ability makes the construction plan more accurate, can anticipate potential risks and challenges in advance, and reduce plan deviations and uncertainties in execution.

[0026] (3) In this embodiment of the invention, the stability of the construction plan is taken into account on the basis of reducing the total construction time and total construction cost, so as to optimize the construction plan, improve the stability of the construction plan, avoid waste of resources, and ensure the timely completion of the project. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 A flowchart illustrating a construction management method for an artificial intelligence computing center, provided as an embodiment of the present invention;

[0029] Figure 2 This is a structural schematic diagram of a construction management method for an artificial intelligence computing center provided in an embodiment of the present invention;

[0030] Figure 3This is a structural diagram of an artificial intelligence computing center construction management system provided in an embodiment of the present invention. Detailed Implementation

[0031] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0032] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0033] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent.

[0034] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0035] Reference manual attached Figure 1 The diagram illustrates a flowchart of a construction and management method for an artificial intelligence computing center provided by an embodiment of the present invention.

[0036] Reference manual attached Figure 2 The diagram shows a structural schematic of a construction and management method for an artificial intelligence computing center provided by an embodiment of the present invention.

[0037] This invention provides a construction management method for an artificial intelligence computing center. This method can be implemented using an artificial intelligence computing center construction management device, which can be a terminal or a server. The processing flow of the artificial intelligence computing center construction management method may include the following steps:

[0038] S1: Construct the original BIM model for the artificial intelligence computing center.

[0039] BIM (Building Information Modeling) is a digital tool for architectural design and construction management. It integrates the physical and functional information of a building into a unified digital platform through 3D modeling technology. A BIM model contains not only geometric data of the building but also information on structure, materials, equipment, time, and cost, simulating the entire lifecycle of a building project. It helps designers, engineers, and architects collaborate effectively during the design, construction, and operation phases, optimizing resource allocation, reducing errors and waste, and improving building quality and efficiency. Through real-time updates and sharing, BIM technology promotes communication and decision support among project teams, especially in complex building projects, where BIM models provide more efficient project management and control.

[0040] Specifically, the various components of the computing center (such as computer rooms, servers, air conditioning, and power systems) can be modeled in BIM software using architectural design drawings and related data. Next, based on actual needs and design requirements, the geometry, spatial relationships, and technical parameters of each component are described in detail to ensure the model fully reflects actual construction and operational needs. This process generates a BIM model containing all relevant information, providing a foundation for subsequent construction planning, resource management, and performance simulation.

[0041] S2: Reconstruct the mesh of each component in the original BIM model.

[0042] In one possible implementation, S2 specifically includes sub-steps S201 to S205:

[0043] S201: Use the properties of the 3D engine to count the number of vertices and triangles in the original BIM model.

[0044] S202: By extracting point cloud data from the mesh configuration information constituting the surface, shape information is separated, conforming to geometric and topological properties, and non-reducible edges are excluded.

[0045] S203: Delete the original triangular mesh and check the deleted original triangular mesh based on curvature calculation and QEM method.

[0046] S204: Using the extracted point cloud data, the centroid of the triangle is used as the new vertex, reducing the original vertex.

[0047] The centroid is the intersection of the three medians of the triangle.

[0048] S205: Determine if the number of vertices after reduction is less than the reduction threshold. If yes, reconstruct the triangle mesh using the new vertices. Otherwise, return to S204 and continue reducing the number of vertices.

[0049] Those skilled in the art can set the size of the reduction threshold according to the actual situation, and the present invention does not impose any limitations.

[0050] In this embodiment of the invention, by reconstructing the individual components of the original BIM model using a mesh, the complexity and data volume of the model can be significantly reduced. This optimization not only helps improve computational and storage efficiency but also reduces the computational burden while maintaining the integrity of the model's geometric and topological information, providing a more efficient foundation for subsequent construction planning, resource allocation, and real-time simulation. Furthermore, mesh simplification can also improve the rendering speed and model loading efficiency of the 3D engine, ensuring rapid response and efficient execution in large-scale, complex projects.

[0051] S3: Perform similarity mapping on each component after mesh reconstruction, and merge and store similar components.

[0052] In one possible implementation, S3 specifically includes sub-steps S301 to S308:

[0053] S301: Align the components by translating the center points of each component to the same origin.

[0054] The center point refers to the center point of the cuboid that can minimally enclose the component.

[0055] It should be noted that by translating the center points of each component to the same origin and aligning them, the positioning differences between different components can be eliminated, ensuring the consistency and standardization of components in space. This facilitates subsequent comparison and matching of component shapes and structures, avoiding misjudgments caused by positional differences.

[0056] S302: Determine whether the first component and the second component are of the same category. If yes, proceed to the next step. Otherwise, determine that the first component and the second component are not similar.

[0057] S303: Determine whether the dimensional difference between the smallest enclosing cuboids of the first component and the second component is less than a preset dimensional difference value. If yes, proceed to the next step. Otherwise, determine that the first component and the second component are not similar.

[0058] Those skilled in the art can set the preset size difference value according to the actual situation, and the present invention does not limit it.

[0059] S304: Determine whether the positional difference between the centroids of the first component and the second component is less than a preset positional difference value. If yes, proceed to the next step. Otherwise, determine that the first component and the second component are dissimilar.

[0060] Those skilled in the art can set the magnitude of the preset position difference value according to the actual situation, and the present invention does not limit it.

[0061] It's worth noting that by comparing component categories, minimum bounding box size differences, and centroid position differences, dissimilar components can be quickly filtered out, avoiding unnecessary calculations and thus improving the efficiency of similarity mapping. A preset difference threshold ensures that only truly similar components are further processed, avoiding a large amount of invalid computation and optimizing the entire process.

[0062] S305: For each vertex in the triangular mesh of the first component, find the nearest neighbor vertex in the triangular mesh of the second component to form a first nearest neighbor list; for each vertex in the triangular mesh of the second component, find the nearest neighbor vertex in the triangular mesh of the first component to form a second nearest neighbor list.

[0063] List1 = {(P a Q a ),a=1,2,…,A}

[0064] List2 = {(Q b ,P b ), b=1,2,…,B}

[0065] Where List1 represents the first nearest neighbor list, P a Let Q represent the a-th vertex of the first component. a Let A represent the nearest neighbor vertex of the i-th vertex in the first component of the second component, let A represent the total number of vertices in the first component, and let List2 represent the second nearest neighbor list. b P represents the b-th vertex of the second component. b Let B represent the nearest neighbor vertex of the b-th vertex of the second component in the first component, and let B represent the total number of vertices in the second component.

[0066] It's worth noting that by calculating the nearest neighbor vertices of each vertex between two components and creating a nearest neighbor list, the similarity between the two components at a detailed level can be captured. This vertex-by-vertex comparison allows for more accurate matching of the geometry between components, improving the accuracy of subsequent similarity calculations.

[0067] S306: Calculate the weighted distance between the first nearest neighbor list and the second nearest neighbor list:

[0068]

[0069] Where D represents the weighted distance, Aera a Let Aera represent the area of ​​the triangle adjacent to the a-th vertex of the first component. b This represents the area of ​​the triangle adjacent to the b-th vertex of the second component.

[0070] It should be noted that vertices in the mesh have varying degrees of importance. For example, vertices describing local details are adjacent to smaller triangles and therefore have lower importance. Therefore, this application uses the area of ​​adjacent triangles as a weight to reflect the importance of different vertices and improve the accuracy of similarity calculation.

[0071] In this embodiment of the invention, a weighted distance calculation, incorporating the area of ​​the triangle containing each vertex, reflects the importance of different vertices within the component. This ensures that the influence of local details and important parts is reasonably amplified during similarity calculation, thereby improving the accuracy of similarity measurement and making the calculation results more consistent with the matching requirements of the actual structure.

[0072] S307: Calculate the similarity between the first nearest neighbor list and the second nearest neighbor list based on the weighted distance:

[0073]

[0074] Where sim represents similarity and exp represents an exponential function with the natural constant as the base.

[0075] It should be noted that the larger the weighted distance between the nearest neighbor lists of two components, the lower the similarity; conversely, the smaller the weighted distance between the nearest neighbor lists of two components, the higher the similarity.

[0076] Furthermore, the similarity between two components is calculated based on a weighted distance, and an exponential decay function is used to measure the similarity, so that a smaller weighted distance corresponds to a higher similarity. This more accurately reflects the geometric similarity between the two components. In this way, similar components can be effectively identified, providing a basis for subsequent merging and storage.

[0077] S308: When the similarity between the first nearest neighbor list and the second nearest neighbor list is greater than the preset similarity, the first component and the second component are determined to be similar components and are merged and stored.

[0078] Those skilled in the art can set the preset similarity level according to the actual situation, and the present invention does not limit it.

[0079] In this embodiment of the invention, the similarity of components can be accurately identified and processed while ensuring efficient computation. By merging and storing similar components, data redundancy is reduced, and the optimization effect of the BIM model is improved. This not only improves the data processing efficiency during construction but also provides more accurate and reliable data support for subsequent construction planning and resource management.

[0080] S4: Based on the merged and stored BIM model, decompose the construction tasks of the artificial intelligence computing center.

[0081] S5: Coordinate and allocate the decomposed tasks to generate a construction plan.

[0082] The construction plan mainly includes the execution sequence of various tasks and the units responsible for executing each task.

[0083] Therefore, S5 specifically involves: determining the execution order of each decomposed task and the execution unit of each task, and generating a construction plan.

[0084] S6: Through artificial neural networks, the construction process is simulated to predict the completion time, cost, and importance of various tasks in the construction plan.

[0085] Artificial neural networks are computational models that mimic the structure and function of biological nervous systems. They process input data and perform tasks such as pattern recognition, classification, and prediction by connecting a series of nodes (neurons).

[0086] Artificial neural networks consist of an input layer, hidden layers, and an output layer. The input layer receives external data, the hidden layers process and abstract the data through weighted summation and activation functions, and the output layer provides the final result. Through the backpropagation algorithm, the neural network can continuously adjust the weights and biases during training to minimize prediction error. Artificial neural networks excel at handling complex nonlinear problems and are widely used in fields such as image recognition, speech processing, and predictive analytics. They can automatically learn from large amounts of data and discover potential patterns and features.

[0087] Task feature vectors are formed based on data such as the type and scale of each task, required resources (such as manpower, materials, equipment, etc.), working environment, weather, material supply, equipment status, actual completion time of similar previous projects or tasks, cost, and resources used.

[0088] The input layer is used to input the task feature vector.

[0089] The hidden layers are used to perform a weighted summation of the input state vectors through the neurons in each hidden layer, resulting in the hidden states for completion time, completion cost, and importance.

[0090]

[0091] Among them, y vt The hidden state represents the completion time of the output of the v-th hidden layer neuron, σ1 represents the hidden layer activation function, and W vt This represents the weight vector indicating the completion time of the v-th hidden layer neuron. T This represents the transpose operation, where X represents the input task feature vector, composed of multiple task feature values. uLet b represent the feature value of the u-th task, where U represents the total number of state parameters. vt ω represents the completion time bias term of the v-th hidden layer neuron. uvt y represents the completion time weight of the u-th state parameter in the v-th hidden layer neuron. vc W represents the completion cost hidden state of the output of the v-th hidden layer neuron. vc b represents the completion cost weight vector of the v-th hidden layer neuron. vc ω represents the completion cost bias term of the v-th hidden layer neuron. uvc y represents the completion cost weight of the u-th state parameter in the v-th hidden layer neuron. vw W represents the importance hidden state of the output of the v-th hidden layer neuron. vw b represents the importance weight vector of the v-th hidden layer neuron. vw ω represents the importance bias term of the v-th hidden layer neuron. uvw This represents the importance weight of the u-th state parameter in the v-th hidden layer neuron.

[0092] The output layer is used to calculate the completion time, completion cost, and importance of each task based on the hidden states of completion time, completion cost, and importance.

[0093]

[0094]

[0095] Where t represents the completion time, σ² represents the output layer activation function, and ω vt b represents the connection weight between the j-th hidden layer neuron and the completion time output node. t The bias term for the output node represents the completion time, V represents the total number of neurons in the hidden layer, c represents the completion cost, and ω represents the completion time. vc b represents the connection weight between the j-th hidden layer neuron and the completed cost output node. c The bias term represents the output node of the completed cost, w represents importance, and ω represents the bias term. vw b represents the connection weight between the j-th hidden layer neuron and the importance output node. w The bias term represents the importance of the output node.

[0096] In this embodiment of the invention, by leveraging the powerful learning capabilities of neural networks, patterns can be automatically learned from historical data and actual conditions, providing more accurate predictions of construction tasks. This helps project managers optimize construction plans, rationally allocate resources, and improve the accuracy of decision-making. Simultaneously, the nonlinear modeling capabilities of neural networks enable them to handle complex construction task characteristics and interrelationships, thereby enhancing the adaptability and stability of construction plans.

[0097] S7: Optimize the construction plan with the goal of reducing the total construction time and cost and improving the stability of the construction plan.

[0098] In one possible implementation, with the goal of reducing the total construction time and total construction cost and improving the stability of the construction plan, the construction plan is optimized using a particle swarm optimization algorithm.

[0099] Particle Swarm Optimization (PSO) is a global optimization algorithm based on swarm intelligence, mimicking the behavior of flocks of birds foraging or schools of fish swimming. The algorithm searches for the optimal solution by having a swarm of "particles" move through the search space. Each particle represents a possible solution and adjusts its flight speed and position based on the fitness (objective function value) of the current solution. During the search process, each particle updates its position based on its historical best position and the best position of the swarm, thus guiding the entire swarm towards the optimal solution.

[0100] Optionally, the fitness function of the particle swarm optimization algorithm is specifically:

[0101]

[0102] Where L represents the fitness function, Y represents the construction plan, T(Y) represents the total construction time of the construction plan, and λ T λ represents the weighting coefficient for the total construction time, C(Y) represents the total construction cost of the construction plan, and λ represents the total construction time. C The weighting coefficient represents the total construction cost, S(Y) represents the stability of the construction plan, and λ represents the weighting coefficient. S Weighting coefficients representing stability.

[0103] In this regard, those skilled in the art can set the weighting coefficient λ of the total construction time according to the actual situation. T The weighting coefficient λ of the total construction cost C and the stability weighting coefficient λ S The size is not limited in this invention.

[0104] Identify the critical path in the construction plan, and calculate the total construction time by summing the completion times of each task on the critical path:

[0105]

[0106] Where T represents the total construction time, Cr represents the total number of critical paths, and t represents the total number of critical paths. i This represents the completion time of the i-th task.

[0107] Specifically, we can analyze the dependencies between tasks, especially sequential dependencies, that is, which tasks can only start after other tasks are completed. This can be represented by a dependency graph, and then the critical path can be extracted based on the dependency graph.

[0108] The total construction cost is calculated by adding up the costs of completing each task:

[0109]

[0110] Where C represents the total construction cost, co i This represents the completion cost of the i-th task. Completion cost generally includes labor costs, material costs, equipment costs, etc.

[0111] The stability of the construction plan is specifically as follows:

[0112]

[0113] Where S represents the stability index of the construction plan, used to measure the stability of the task coordination and allocation scheme, especially its performance under uncertainties. CIW i fs represents the cumulative importance of the i-th task, n represents the total number of tasks, and fs represents the cumulative importance of the i-th task. i Let represent the free float time of the i-th task, represent the maximum time that the i-th task can be delayed without affecting the earliest start time of its successor tasks, and let e represent the natural constant. -i Let represent the exponential decay factor of the i-th task. As the task number i increases, the exponential decay factor decreases, and the subsequent impact of the i-th task gradually decreases during calculation. `min` indicates taking the minimum value. `s` i′ d represents the start time of the i′-th task. i Succ represents the duration of the i-th task. i Let s represent the set of successor tasks for the i-th task. i w represents the start time of the i-th task. i w represents the importance of the i-th task. i′ This indicates the importance of the i′-th task.

[0114] In this embodiment of the invention, the stability index of the construction plan effectively measures the stability of the task coordination and allocation scheme in the face of uncertainties by considering the free float time and cumulative importance of tasks. It can identify critical tasks, optimize resource allocation, and dynamically adjust the construction plan in the event of unforeseen events. Ultimately, this method improves the stability of the construction plan, making it more resilient to uncertainty, thereby ensuring timely project completion and minimizing resource waste.

[0115] Specifically, the specific implementation methods of particle swarm optimization algorithms are already very mature existing technologies, and will not be elaborated upon in this invention.

[0116] S8: Construct an artificial intelligence computing center in accordance with the optimized construction plan.

[0117] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following:

[0118] (1) In this embodiment of the invention, by reconstructing the BIM model into a grid and merging and storing similar components, the complexity and volume of the BIM model are reduced, thereby effectively reducing the consumption of computing and storage resources. This process enables the construction team to obtain the required model information more quickly, improves the efficiency of the construction preparation stage, and helps to quickly formulate a construction plan.

[0119] (2) In this embodiment of the invention, the construction process is simulated using an artificial neural network, which can predict the completion time, cost, and importance of each task based on historical data and current conditions. This predictive ability makes the construction plan more accurate, can anticipate potential risks and challenges in advance, and reduce plan deviations and uncertainties in execution.

[0120] (3) In this embodiment of the invention, the stability of the construction plan is taken into account on the basis of reducing the total construction time and total construction cost, so as to optimize the construction plan, improve the stability of the construction plan, avoid waste of resources, and ensure the timely completion of the project.

[0121] Reference manual attached Figure 3 The diagram shows a structural schematic of an artificial intelligence computing center construction management system provided by the present invention.

[0122] This invention also provides an artificial intelligence computing center construction management system 20, applied to the aforementioned artificial intelligence computing center construction management method, comprising:

[0123] Processor 201.

[0124] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the construction and management method for the artificial intelligence computing center as described in the method embodiment is implemented.

[0125] The AI ​​computing center construction management system 20 provided by this invention can execute the above-mentioned AI computing center construction management method and achieve the same or similar technical effects. To avoid duplication, this invention will not elaborate further.

[0126] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following:

[0127] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0128] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0129] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0130] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0131] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0132] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0133] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0134] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0135] In the embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0136] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0137] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0138] If the functionality is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0139] This invention provides a computer-readable storage medium storing a computer program thereon, characterized in that, when the program is executed by a processor, it implements the construction and management method for an artificial intelligence computing center as described in the method embodiment.

[0140] The computer-readable storage medium provided by this invention can realize the steps and effects of the construction and management method for the artificial intelligence computing center in the above-described method embodiments. To avoid repetition, this invention will not repeat them.

[0141] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0142] The following points need to be explained:

[0143] (1) The accompanying drawings of the embodiments of the present invention only involve the structures involved in the embodiments of the present invention. Other structures can refer to the general design.

[0144] (2) For clarity, the thickness of layers or regions is enlarged or reduced in the drawings used to describe embodiments of the present invention; that is, these drawings are not drawn to actual scale. It is understood that when an element such as a layer, film, region, or substrate is referred to as being “above” or “below” another element, the element may be “directly” located “above” or “below” the other element, or there may be intermediate elements.

[0145] (3) Where there is no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0146] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A construction management method for an artificial intelligence computing center, characterized in that, include: S1: Constructing the original BIM model for the artificial intelligence computing center; S2: Perform mesh reconstruction on each component in the original BIM model; S3: Perform similarity mapping on each component after mesh reconstruction, and merge and store similar components; S4: Based on the merged and stored BIM model, the construction tasks of the artificial intelligence computing center are decomposed. S5: Coordinate and allocate the decomposed tasks to generate a construction plan; S6: Using artificial neural networks, simulate the construction process and predict the completion time, cost, and importance of each task in the construction plan; S7: Optimize the construction plan with the goal of reducing the total construction time and cost and improving the stability of the construction plan; S8: Construct the artificial intelligence computing center according to the optimized construction plan; Specifically, S7 involves optimizing the construction plan using a particle swarm optimization algorithm, with the goal of reducing the total construction time and cost and improving the stability of the construction plan. The fitness function of the particle swarm optimization algorithm is specifically as follows: ； in, L Represents the fitness function. Y Indicates the construction plan. T ( Y The number () indicates the total construction duration of the construction plan. λ T The weighting coefficient represents the total construction time. C ( Y () represents the total construction cost of the construction plan. λ C The weighting coefficient representing the total construction cost. S ( Y This indicates the stability of the construction plan. λ S Weighting coefficients representing stability; The critical path in the construction plan is determined, and the total construction time is calculated by summing the completion times of each task on the critical path: ； in, T Indicates the total construction time. Cr The total number of critical paths t i Indicates the first i The completion time of each task; The total construction cost is calculated by adding up the completion costs of each task: ； in, C This represents the total construction cost. co i Indicates the first i The cost of completing the task; The stability of the construction plan is specifically as follows: ； ； ； in, S This indicator represents the stability of the construction plan and is used to measure the stability of the task coordination and allocation scheme. CIW i Indicates the first i The cumulative importance of each task n Indicates the total number of tasks. fs i Indicates the first i The free float time of the task represents the time of the first task. i The maximum time a task can be delayed without affecting the earliest start time of its successor tasks. e Represents the natural constant. Indicates the first i The exponential decay factor of each task, increasing with the task number. i As the value increases, the number decay factor will decrease. i The subsequent impact of a task gradually decreases during calculation; min indicates taking the minimum value. Indicates the first The start time of the task. d i Indicates the first i The duration of the task Succ i Indicates the first i The set of successor tasks for each task. s i Indicates the first i The start time of the task. w i Indicates the first i The importance of this task Indicates the first The importance of this task.

2. The construction and management method for an artificial intelligence computing center according to claim 1, characterized in that, S2 specifically includes: S201: Use the properties of the 3D engine to count the number of vertices and triangles in the original BIM model; S202: By extracting point cloud data from the mesh configuration information constituting the surface, separating shape information, conforming to geometric and topological properties, and excluding non-reducible edges; S203: Delete the original triangle mesh and check the deleted original triangle mesh based on curvature calculation and QEM method; S204: Using the extracted point cloud data, the centroid of the triangle is used as the new vertex, reducing the original vertex; S205: Determine if the number of vertices after reduction is less than the reduction threshold; if yes, rebuild the triangle mesh using the new vertices; otherwise, return to S204 and continue reducing the number of vertices.

3. The construction and management method for an artificial intelligence computing center according to claim 1, characterized in that, S3 specifically includes: S301: Align the components by translating the center points of each component to the same origin. S302: Determine whether the first component and the second component are of the same category; if yes, proceed to the next step; otherwise, determine that the first component and the second component are not similar. S303: Determine whether the size difference between the smallest enclosing cuboids of the first component and the second component is less than a preset size difference value; if yes, proceed to the next step; otherwise, determine that the first component and the second component are not similar. S304: Determine whether the positional difference between the centroid positions of the first component and the second component is less than a preset positional difference value; if yes, proceed to the next step; otherwise, determine that the first component and the second component are not similar. S305: For each vertex in the triangular mesh of the first component, find the nearest neighbor vertex in the triangular mesh of the second component to form a first nearest neighbor list; for each vertex in the triangular mesh of the second component, find the nearest neighbor vertex in the triangular mesh of the first component to form a second nearest neighbor list. S306: Calculate the weighted distance between the first nearest neighbor list and the second nearest neighbor list; S307: Calculate the similarity between the first nearest neighbor list and the second nearest neighbor list based on the weighted distance; S308: When the similarity between the first nearest neighbor list and the second nearest neighbor list is greater than a preset similarity, the first component and the second component are determined to be similar components and are merged and stored.

4. The construction and management method for an artificial intelligence computing center according to claim 1, characterized in that, Specifically, S5 involves determining the execution order of each decomposed task and the execution unit of each task, and generating a construction plan.

5. The construction and management method for an artificial intelligence computing center according to claim 1, characterized in that, The artificial neural network includes: an input layer, a hidden layer, and an output layer; Task feature vectors are formed based on data such as the type, scale, required resources, working environment, weather, material supply, equipment status, actual completion time, cost, and resources used in previous similar projects or tasks. The input layer is used to input the task's feature vector; The hidden layer is used to perform a weighted summation of the input state vector through each hidden layer neuron to obtain the hidden state of completion time, the hidden state of completion cost, and the hidden state of importance. The output layer is used to calculate the completion time, completion cost, and importance of each task based on the hidden states of completion time, completion cost, and importance.

6. A construction management system for an artificial intelligence computing center, characterized in that, include: processor; A memory storing computer-readable instructions, which, when executed by the processor, implement the construction and management method for an artificial intelligence computing center as described in any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the construction and management method for the artificial intelligence computing center as described in any one of claims 1 to 5.

Images