Digital twin model component data storage method, equipment and medium

Abstract

The invention discloses a digital twin model component data storage method and device and a medium, and relates to the field of data storage, and the method comprises the steps: obtaining the component data of a digital twin model; establishing a graph structure data set according to the component data; according to the graph structure data set, adopting a pre-trained deep learning model to determine feature representation and category of each component; the deep learning model comprises a graph convolutional neural network, a full connection layer and a classifier which are connected in sequence, the output of the graph convolutional neural network is feature representation, and the output of the classifier is a category; and generating a personalized hash code corresponding to each component according to the feature vector of each component, the feature representation of each component and the category of each component, and storing the personalized hash code in a database. According to the method, the query efficiency of the digital twin model component is improved, the physical space required for storing the component data is reduced, and the resource consumption is reduced.

Description

Technical Field

[0001] The present application relates to the field of data storage, and in particular to a method, device, and medium for storing digital twin model component data. Background Art

[0002] In intelligent pump station management, Building Information Modeling (BIM) is a crucial component of the data infrastructure, supporting efficient data query and visualization of pump station information. Rapid BIM retrieval and optimization not only impact system performance but also directly influence decision-making efficiency, operational maintenance effectiveness, and user experience.

[0003] BIM contains highly complex multidimensional information such as geometric shapes, engineering properties, and spatial relationships. The interrelationships and hierarchies between these data require efficient indexing and search strategies. Traditionally, BIM component data is stored in a structured database. This structured storage method provides advanced management and query capabilities for objects and their attributes, making it suitable for rule-based applications and traditional data analysis tasks. However, as BIM component data becomes increasingly complex and contains large amounts of data, this traditional storage method has also exposed various technical challenges and limitations. Its technical shortcomings include:

[0004] 1. Difficulty in indexing: Traditional databases are limited in their efficiency in querying large amounts of data due to their indexing strategies and algorithms. When it comes to large-scale BIMs (including thousands or even tens of thousands of components), searching for specific component information directly in the raw data can become time-consuming and inefficient, especially when exact matching or similarity retrieval is required.

[0005] 2. Data redundancy and conflict: Current storage methods can result in a large number of duplicate data records, especially when dealing with similar but not identical BIM components. This not only increases storage space requirements, but also increases the likelihood of bit errors and can complicate subsequent queries and management.

[0006] 3. Low query efficiency: Under the existing data organization structure, performing complex searches in large databases often relies on full table scans or index building. This approach is greatly limited by performance bottlenecks.

[0007] 4. Resource consumption: As BIM grows in complexity and scale, the demand for storing and processing this data also increases. This involves not only hardware costs (such as servers, storage devices, etc.), but also operation and maintenance costs and power consumption.

[0008] 5. Limited flexibility: Traditional databases often have strict restrictions on data types and structures, which may not be suitable for the flexible and changing BIM requirements, such as adding new component types or modifying existing component properties. Poor adaptability may lead to frequent data migration or reconstruction operations, increasing time and resource costs. Summary of the Invention

[0009] The purpose of this application is to provide a method, device and medium for storing digital twin model component data, which can improve the query efficiency of digital twin model components, reduce the physical space required for storing component data, and reduce resource consumption.

[0010] To achieve the above objectives, this application provides the following solutions:

[0011] In a first aspect, the present application provides a method for storing component data of a digital twin model, comprising:

[0012] Obtaining component data of the digital twin model; the component data includes a feature vector of each component and the relationship between components;

[0013] A graph structure data set is established based on the component data; the graph structure data set includes node features and graph structure features, the node features include each component and a feature vector of each component, and the graph structure features include the relationship between components;

[0014] Determine the feature representation and category of each component using a pre-trained deep learning model based on the graph structure dataset; wherein the deep learning model includes a graph convolutional neural network, a fully connected layer, and a classifier connected in sequence, the output of the graph convolutional neural network is the feature representation, and the output of the classifier is the category;

[0015] According to the feature vector of each component, the feature representation of each component and the category of each component, a personalized hash code corresponding to each component is generated and stored in the database.

[0016] In a second aspect, the present application provides a computer device comprising: 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 above-mentioned method for storing component data of a digital twin model.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the above-mentioned method for storing digital twin model component data.

[0018] According to the specific embodiments provided in this application, this application has the following technical effects:

[0019] The present application provides a method, device, and medium for storing component data of a digital twin model. By understanding the complex relationships between components through a graph convolutional neural network, a more effective feature representation can be provided for the digital twin model of massive components. Furthermore, a personalized hash code corresponding to each component is generated based on the feature vector, feature representation, and category of each component. By storing the personalized hash code of the component, the physical space required for storing data is reduced, and the corresponding component can be efficiently found from massive data during retrieval. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is an application environment diagram of a method for storing component data of a digital twin model in one embodiment of the present application;

[0022] Figure 2 A flowchart of a method for storing component data of a digital twin model provided in one embodiment of the present application;

[0023] Figure 3 This is a general framework diagram of a method for storing component data of a digital twin model provided in one embodiment of the present application;

[0024] Figure 4 This is a schematic diagram of a deep learning model in one embodiment of the present application;

[0025] Figure 5 Schematic diagram of a graph structure data set in one embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] First, some technical terms involved in the embodiments of this application are introduced.

[0028] BIM components: BIM refers to the use of building information models to manage the entire design, construction, and operation and maintenance process. BIM component data refers to the data set used to describe a specific construction element in a BIM system, including but not limited to geometric characteristics (such as shape and size), physical properties (such as material type and weight), environmental factors (such as energy consumption estimation), and related connections and other related information.

[0029] Graph Convolutional Networks (GCN): is a deep learning architecture for processing graph data. It can perform convolution operations directly on nodes, edges, and the entire graph structure to capture complex local and global relationships in the data, and can well understand and generate high-value feature representations for complex structures.

[0030] Loss function: A metric used in machine learning and deep learning to evaluate model performance. It measures the difference between the model output and the actual results and is used to guide weight adjustments during training to optimize prediction accuracy.

[0031] A hashing algorithm is a process that converts input data of any size into a fixed-size output (often called a "hash" or "hash code"). It is widely used in information retrieval, database indexing, secure storage, and other fields, especially to provide fast search and matching capabilities when processing large amounts of data.

[0032] This application addresses the problem of low retrieval efficiency of BIM components in current intelligent pumping stations and slow loading speed when components are changed or associated with real-time data. It provides a storage method for component data of a digital twin model, which combines deep learning, feature extraction and hash coding processes to generate personalized hash codes. The personalized hash codes of each component are stored in the database in advance. When the front-end searches, the corresponding components can be efficiently found from massive data. When new BIM components are stored, they can be quickly stored through the trained deep learning model, which is convenient for subsequent retrieval, thereby achieving effective filtering and rapid positioning of large-scale BIM component data and significantly reducing query time.

[0033] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0034] The storage method of digital twin model component data provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the component data of the digital twin model to the server 104, and the server 104 generates a personalized hash code for each component based on the received component data of the digital twin model and stores it in the database. In addition, in some embodiments, the storage method of the digital twin model component data can also be implemented separately by the server 104 or the terminal 102.

[0035] Terminal 102 may include, but is not limited to, various desktop computers, laptops, smartphones, tablet computers, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Server 104 may be implemented as a standalone server or a server cluster consisting of multiple servers, or may be a cloud server.

[0036] In an exemplary embodiment, Figure 2 and Figure 3 As shown, a method for storing component data of a digital twin model is provided. The method is executed by a computer device, specifically a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, including the following steps 201 to 204.

[0037] Step 201: Obtain component data of the digital twin model. The component data includes the feature vector of each component and the relationship between components. The digital twin model is a building information model of the digital twin intelligent pump station.

[0038] In a specific application example, step 201 includes the following steps 11 to 13.

[0039] Step 11: Obtain the attribute information of each component in the digital twin model.

[0040] Specifically, attribute information that reflects the similarities or differences between components is extracted from the multidimensional BIM, and components are simply classified based on their attribute information. For each component in the BIM, the component's geometric information is associated with relevant attribute characteristics during the modeling process. This attribute information is derived, such as geometric attributes (such as volume and shape), physical attributes (such as material type and weight), and environmental factors (such as light and temperature). K categories are organized, such as [door, table, chair, generator, wall, gate, transformer, etc.]. 1*k .

[0041] Step 12: Determine the relationship between components based on the attribute information of each component.

[0042] Step 13: normalize the attribute information of each component to obtain the feature vector of each component.

[0043] By normalizing the attribute information within each category, the eigenvectors of each component have the same dimensions. Specifically, small eigenvectors are padded with zero vectors to ensure that each eigenvector has the same matrix data format. For example, if a door consists of four points and a table consists of six points, the door is expanded by two zero vectors, equal to the number of points in the table.

[0044] The final component data is Φ={Φ1,Φ2,Φ3,……Φ n}; where Φ is component data, Φ n is the characteristic vector of the nth component and its relationship with other components, and n is the number of components.

[0045] Step 202: Create a graph structure dataset based on the component data. The graph structure dataset includes node features and graph structure features. The node features include each component and its feature vector. The graph structure features include the relationship between components.

[0046] Step 203: Based on the graph structure dataset, a pre-trained deep learning model is used to determine the feature representation and category of each component. Figure 4 As shown, the deep learning model includes a graph convolutional neural network, a fully connected layer and a classifier connected in sequence. The output of the graph convolutional neural network is a feature representation, and the output of the classifier is a category.

[0047] This application builds a deep learning model that can process graph structure data in order to extract and understand complex component relationships from BIM. The deep learning model is pre-trained using a training sample set, and each training sample in the training sample set includes a graph structure data set sample and the true category of each component therein. There are no less than 10 components of each category in the graph structure data set sample. For example, if the graph structure data set sample includes table 1, table 2, chair 1, chair 2, transformer 1, transformer 2 and transformer 3, then table 1 and table 2 belong to the same category. The loss function during deep learning model training can use a hash loss function. The loss function value is calculated by calculating the error between the category output by the classifier and the true category. If the loss function value does not reach the target range, training and optimization are continued until the loss function value is minimized and performs well in the test set.

[0048] like Figure 5 As shown, for a graph structure dataset G, there are N nodes ( Figure 4 R, S, T, U, V in the graph), each node has its own characteristics. The node represents the component, and the node feature represents the feature vector of the component. Suppose these nodes form an N*D matrix, namely the node feature X, and D represents the feature dimension of each node, that is, the dimension of the feature vector. In addition, the relationship between each node can also be extracted as an N*N relationship matrix, namely the graph structure feature A, also known as the adjacency matrix. The node feature X and the graph structure feature A are the input of the graph convolutional neural network, and the graph convolutional neural network outputs the probability that each component belongs to each category (the probability that R belongs to the first category is 1.1, the probability that R belongs to the second category is 3.2, the probability that R belongs to the third category is 4.2, and so on).

[0049] Based on the L-layer graph convolutional neural network with layer-by-layer propagation rules, the propagation method between layers is:

[0050]

[0051] Among them, H l+1 is the activation matrix of the l+1th layer, is the activation matrix of layer l, W (l) is the weight matrix of the lth layer, δ(·) represents the nonlinear activation function, I N It is an N-dimensional unit matrix. Since the diagonal of the graph structure feature A is all 0, it is (l) When multiplying, the characteristics of the node itself are ignored, and an identity matrix I is added to A. N This will make the diagonal elements become 1, for The standardized matrix, for The data in row p and column q in the table is The total number of columns, for The data in row p and column q are normalized, because Is a matrix that has not been normalized. If it is the same as H (l) Direct multiplication will change the original distribution of features, because different nodes have different numbers and weights of edges. Some nodes are connected to multiple edges, which causes the feature values of nodes with multiple edges to be much larger than those of nodes with fewer edges after aggregation. Therefore, it is necessary to Standardize the process so that Each row of the sum is 1, is a symmetric and normalized matrix.

[0052] In this application, the graph convolutional neural network has 4 propagation layers. After the input data is calculated by the above-mentioned propagation layer formula, it enters the fully connected layer, undergoes fully connected processing, enters the softmax classifier, and outputs k results, including the probability that each component belongs to each category.

[0053] Step 204 : Generate a personalized hash code corresponding to each component based on the feature vector of each component, the feature representation of each component, and the category of each component, and store it in a database.

[0054] This application generates a personalized hash code for each component, which can maintain category differentiation while maintaining spatial compactness, reduce hash conflicts, and improve component retrieval efficiency.

[0055] In a specific application example, step 204 includes the following steps 41 and 42 .

[0056] Step 41: For the a-th generation process of any component, a primary hash function and an auxiliary hash function are used to obtain a preliminary hash code for the component generated the a-th time based on the number of generation times and the component's characteristic information. The characteristic information includes a feature vector, feature representation, and category; a ≥ 0.

[0057] Specifically, based on the characteristic information of the component, a primary hash function is used to determine the primary hash code of the component. Based on the number of times it is generated and the characteristic information of the component, an auxiliary hash function is used to determine the auxiliary hash code of the component. Based on the primary hash code and the auxiliary hash code, the preliminary hash code of the component generated for the ath time is determined:

[0058] NewHashValue=H1(data)+a×H2(data);

[0059] Among them, NewHashValue is the preliminary hash code of the component generated for the ath time, data is the characteristic information of the component, H1() is the main hash function, H2() is the auxiliary hash function, and a is the number of generations.

[0060] The process of determining a primary hash code of a component using a primary hash function based on the characteristic information of the component includes: performing a hash calculation on the characteristic information of the component to obtain a first hash code of the component; performing a linear transformation on the first hash code of the component to obtain a second hash code of the component; and using a HashingTrick algorithm to map the second hash code of the component to a fixed-length binary hash code to obtain a primary hash code of the component.

[0061] Specifically, the following formula is used to determine the primary hash code of the i-th component:

[0062] h i '=(g(h i ))mod2 m ;

[0063] Among them, h i ' is the primary hash code of the i-th component, h i is the first hash code of the i-th component, m is the length of the binary hash code, mod represents the modulo operation, g() represents the linear transformation, and the softplus activation function is used here to provide a smooth approximation of positive real numbers and map real values to non-negative values. The non-negative values are then mapped to a fixed-length binary hash code through the HashingTrick algorithm.

[0064] The basic idea of determining the main hash code is to use one or more hash functions to perform a modulo operation on each real number and intercept the corresponding bits as part of the hash code based on the result. Assume that an m-bit binary hash code needs to be generated. First, for each element g(h i ) uses multiple different hash functions, each of which maps randomly to a set of integers. Ideally, each h i ' is a uniform distribution between 0 and 2 m A random number of -1.

[0065] Step 42, determine whether the preliminary hash code of the component generated for the ath time is the same as the personalized hash code of any target component. If so, perform the a+1th generation process of the component. If not, use the preliminary hash code of the component generated for the ath time as the personalized hash code of the component; the target component is the remaining components except the component.

[0066] In addition, when generating personalized hash codes for components, it is also necessary to consider the similarity between hash codes of components of the same category and the diversity between hash codes of components of different categories, thereby reducing hash collisions. hash (h i ”,h' j ')=W·|d(h i ”,h' j ')| p Calculate the difference between two personalized hash codes, thereby increasing the similarity between hash codes of components of the same category and reducing the similarity between hash codes of components of different categories. i " is the personalized hash code of the i-th component, h' j ' is the personalized hash code of the jth component, L hash (h i ”,h' j ') is h i ” and h' j ', W is the weighting coefficient, d(h i ”,h' j ') is h i " and h" j The distance between them, p is a positive integer used to increase the sensitivity of the loss function.

[0067] The personalized hash codes generated by this application not only consider the internal feature information of each BIM component, but also its associated information in the geometric structure. This can provide more effective representation learning and feature extraction capabilities for BIM with massive components, thereby generating more accurate and robust hash codes. By handling hash conflicts, the proximity problem of different components in the hash space is resolved, improving retrieval efficiency and accuracy.

[0068] In the design of the hash table, the goal is to map the characteristic information of each component to a unique position in the table through a hash function. However, in actual application scenarios, the characteristic information of BIM components is often much larger than the number of possible hash codes, and there is a probability that different components are mapped to the same hash code. In order to ensure that the generated hash codes are independent at each position (that is, different binary bits corresponding to different hash functions) and do not cause conflicts, this application adopts the "re-hashing method" for calculation. If a component finds that its position is already occupied (that is, a hash collision occurs) after the hash code is generated for the first time, by introducing a second (or more) hash function, new and different hash values can be generated for known hash collisions, thereby reducing the probability of conflicts and improving the efficiency of the hash table.

[0069] To better understand the process of generating a personalized hash code for each component in step 204 of the present application, the following steps are described in detail:

[0070] (1) Select two hash functions: H1() and H2(). H1() is the primary hash function used for initial hashing, and H2() is the auxiliary hash function used to handle collisions.

[0071] (2) Calculate the main hash value: For each component, use the main hash function H1() to obtain a main hash code to determine the location where this component should be placed.

[0072] (3) If the position is already occupied, a new hash code is calculated using the auxiliary hash function H2() and the known primary hash code as parameters.

[0073] (4) Loop processing: If the position of the newly calculated hash code is still occupied, continue to use the same H2() and the number of generation times a that increases accordingly to find another available position until an empty position is found.

[0074] This application provides an efficient, accurate and highly scalable method for BIM components to process and index large amounts of data. It can not only effectively reduce the conflict rate, but also adapt to the specific needs of different categories. When a specific type of BIM component needs to be retrieved, the component can be quickly located through the hash table, thereby improving query efficiency and system performance in practical applications.

[0075] In summary, the beneficial effects of this application include at least the following:

[0076] 1. Improved query efficiency: Using GCN to process BIM component data enables more efficient data indexing and retrieval. By training GCN to understand the complex relationships between components, it can intelligently parse and match user queries, reducing unnecessary full table scans or complex calculations, thereby significantly improving query performance. By generating personalized hash codes, related or similar objects can be quickly found in a predefined hash space, significantly reducing the time complexity of queries. It supports not only exact matches but also fuzzy queries, improving search efficiency in large databases.

[0077] 2. Reduced data redundancy and conflict: GCN-processed data can more accurately represent the relationships and attributes between components and eliminate or reduce the possibility of duplicate records through the hashing process. This not only saves storage space, but also reduces maintenance costs and query errors caused by mismatches, thereby improving data consistency and reliability.

[0078] 3. Reduced resource consumption: By storing personalized hash codes, the physical space required to store data is reduced, and the demand for hardware resources when processing large amounts of data is reduced.

[0079] 4. Enhanced flexibility and adaptability: By learning the dynamic relationships between BIM components, GCN can respond more flexibly to changes in user needs or the addition of new components. It can adaptively adjust prediction and matching strategies without the need for frequent data reconstruction or index updates, making it more efficient in handling rapidly changing needs. It can also better integrate different data formats and types, increasing overall compatibility and scalability.

[0080] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0081] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0082] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0083] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0084] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0085] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but is not limited thereto.

[0086] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0087] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for storing component data of a digital twin model, characterized in that: The method for storing component data of the digital twin model includes: Obtaining component data of the digital twin model; the component data includes a feature vector of each component and the relationship between components; A graph structure data set is established based on the component data; the graph structure data set includes node features and graph structure features, the node features include each component and a feature vector of each component, and the graph structure features include the relationship between components; Determine the feature representation and category of each component using a pre-trained deep learning model based on the graph structure dataset; wherein the deep learning model includes a graph convolutional neural network, a fully connected layer, and a classifier connected in sequence, the output of the graph convolutional neural network is the feature representation, and the output of the classifier is the category; According to the feature vector of each component, the feature representation of each component and the category of each component, a personalized hash code corresponding to each component is generated and stored in the database.

2. The method for storing component data of a digital twin model according to claim 1, characterized in that: Obtain component data of the digital twin model, including: Obtain the attribute information of each component in the digital twin model; Determine the relationship between components based on the attribute information of each component; The attribute information of each component is normalized to obtain the feature vector of each component.

3. The method for storing component data of a digital twin model according to claim 1, characterized in that: The digital twin model is a building information model of the digital twin intelligent pumping station.

4. The method for storing component data of a digital twin model according to claim 1, characterized in that: Generate a personalized hash code for each component based on the feature vector, feature representation, and category of each component, specifically including: For the a-th generation process of any component, a primary hash function and an auxiliary hash function are used to obtain a preliminary hash code of the component generated the a-th time according to the number of generation times and the characteristic information of the component; the characteristic information includes a characteristic vector, characteristic representation and category; a≥0; Determine whether the preliminary hash code of the component generated for the ath time is the same as the personalized hash code of any target component. If so, perform the a+1th generation process of the component. If not, use the preliminary hash code of the component generated for the ath time as the personalized hash code of the component; the target component is the remaining components except the component.

5. The method for storing component data of a digital twin model according to claim 4, characterized in that: According to the number of times the component is generated and the characteristic information of the component, a primary hash function and an auxiliary hash function are used to obtain a preliminary hash code of the component generated for the ath time, specifically including: Determine a primary hash code of the component using a primary hash function according to the characteristic information of the component; Determine the auxiliary hash code of the component using an auxiliary hash function according to the number of times it is generated and the characteristic information of the component; Determine a preliminary hash code of the component generated for the ath time based on the primary hash code and the auxiliary hash code.

6. The method for storing component data of a digital twin model according to claim 5, characterized in that: According to the characteristic information of the component, a primary hash function is used to determine the primary hash code of the component, specifically including: Performing a hash calculation on the characteristic information of the component to obtain a first hash code of the component; Performing a linear transformation on the first hash code of the component to obtain a second hash code of the component; The Hashing Trick algorithm is used to map the second hash code of the component to a binary hash code of fixed length to obtain the primary hash code of the component.

7. The method for storing component data of a digital twin model according to claim 6, characterized in that: The primary hash code of the i-th component is determined using the following formula: h i ' =(g(h i ))mod2 m ; Among them, h i ' is the primary hash code of the i-th component, h i is the first hash code of the i-th component, m is the length of the binary hash code, g() represents linear transformation, and mod represents modulo operation.

8. The method for storing component data of a digital twin model according to claim 4, characterized in that: The following formula is used to obtain the preliminary hash code of the component generated for the ath time: NewHashValue=H1(data)+a×H2(data); Among them, NewHashValue is the preliminary hash code of the component generated for the ath time, data is the characteristic information of the component, H1() is the main hash function, H2() is the auxiliary hash function, and a is the number of generations.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and runnable on the processor, characterized in that the processor executes the computer program to implement the method for storing digital twin model component data according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the method for storing digital twin model component data according to any one of claims 1 to 8.

Images