Constructional engineering multi-dimensional data fusion analysis system

Abstract

The invention relates to a building engineering multi-dimensional data fusion analysis system, and belongs to the technical field of multi-dimensional data processing. The method comprises the steps of obtaining building engineering multi-dimensional data, building equipment node topology and a preset building engineering multi-dimensional data set, and obtaining building engineering multi-dimensional preprocessing data through a data preprocessing model according to the building engineering multi-dimensional data set, obtaining a community division equipment node similarity network through a correlation division model according to the building engineering multi-dimensional preprocessing data and the building equipment node topology, and the data fusion analysis module is used for obtaining building engineering multi-dimensional fusion analysis data through a data fusion model according to the community division equipment node similarity network, and uploading the building engineering multi-dimensional fusion analysis data to a cloud for analysis according to the building engineering multi-dimensional fusion analysis data. According to the method, the correlation analysis of the multi-dimensional data of the constructional engineering is realized, and meanwhile, the multi-dimensional data of the constructional engineering is scientifically and efficiently fused.

Description

Technical Field

[0001] The present invention belongs to the technical field of multi-dimensional data processing, and in particular relates to a multi-dimensional data fusion analysis system for construction projects. Background Art

[0002] Construction engineering tasks require the linkage of multiple devices to complete, and the generated multi-dimensional data has internal correlations; at the same time, affected by construction equipment failures, multi-dimensional data has uncertainty and incompleteness, and it is necessary to fully analyze the correlation of multi-dimensional data to correct the original data source. Therefore, based on the correlation between multi-dimensional data and the correlation within multi-dimensional data, multi-dimensional data fusion can improve the accuracy and efficiency of construction engineering equipment failure analysis.

[0003] Traditional data fusion technology mainly analyzes and fuses single-attribute data from multiple sources, ignoring the correlation problem of multi-dimensional data; the current fusion method based on Kalman filtering has the problem that it is difficult to establish a mathematical model in the application scenario; the fusion method based on Bayesian estimation has the problem that it is difficult to obtain the required prior probability for each data source, and is not suitable for construction engineering scenarios; the fusion method based on machine learning converges slowly, is prone to fall into local optimality, and the fusion result depends on the sample quality. The above methods still have limitations in dealing with multi-dimensional data fusion in construction engineering. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides a multi-dimensional data fusion analysis system for construction engineering.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A multi-dimensional data fusion analysis system for construction engineering, comprising: a data acquisition module, a data preprocessing module, a correlation division module, and a data fusion analysis module;

[0007] The data acquisition module is used to obtain multi-dimensional data of construction projects and topology of construction equipment nodes, preset a multi-dimensional data set of construction projects, and build a data fusion analysis model based on the multi-dimensional data set of construction projects. The data fusion analysis model includes a data preprocessing model, a correlation partitioning model, and a data fusion model;

[0008] The data preprocessing module is used to obtain multi-dimensional preprocessing data of the construction project through a data preprocessing model according to the multi-dimensional data set of the construction project;

[0009] The correlation partitioning module is used to obtain a community partitioning device node similarity network based on the multi-dimensional pre-processed data of the construction project and the topology of the construction device nodes through a correlation partitioning model;

[0010] The data fusion analysis module is used to obtain multi-dimensional fusion analysis data of the construction project through a data fusion model according to the community division device node similarity network, and upload the multi-dimensional fusion analysis data of the construction project to the cloud for analysis.

[0011] Preferably, obtaining the multidimensional preprocessed data of the construction project through a data preprocessing model according to the multidimensional data set of the construction project comprises:

[0012] Processing missing values ​​by linear interpolation based on the multidimensional dataset of the construction project to obtain a complete multidimensional dataset of the construction project;

[0013] The linear difference expression is:

[0014]

[0015] Wherein, x0 and x1 are the horizontal coordinates of the multi-dimensional data of the construction project, y0 and y1 are the vertical coordinates of the multi-dimensional data of the construction project, x is the position of the missing value, and y is the value of the missing value;

[0016] According to the complete multidimensional data set of the construction project, irrelevant features are eliminated by using the autocorrelation coefficient to obtain a complete relevant multidimensional data set of the construction project;

[0017] The autocorrelation coefficient expression is:

[0018]

[0019] Wherein, ACF(k) represents the autocorrelation coefficient of the complete multidimensional data of the construction project at lag k, t represents time, k represents lag time k, X represents the complete multidimensional data of the construction project, Cov(X t ,X t-k ) represents the covariance of the complete multidimensional data of the construction project at time t and tk, Var(X t ) represents the variance of the complete multidimensional data of the construction project at time t;

[0020] Obtaining the multidimensional preprocessed data of the construction project through normalization processing according to the complete multidimensional data set related to the construction project;

[0021] The normalization expression is:

[0022]

[0023] Where a represents the data in the complete multidimensional dataset of the construction project, X re For the complete multidimensional dataset of the construction project, min(X re ) represents the minimum value in the complete multidimensional dataset of the construction project, max(Xre ) represents the maximum value in the complete related multidimensional dataset of the construction project, Multi-dimensional preprocessing data for the construction project.

[0024] Preferably, the method of obtaining a community partitioning device node similarity network based on the multi-dimensional pre-processed data of the construction project and the topology of the construction device nodes through a correlation partitioning model includes:

[0025] Obtaining a construction engineering multidimensional preprocessing data grid by grid division according to the construction engineering multidimensional preprocessing data;

[0026] According to the building equipment node topology and the multi-dimensional preprocessed data grid of the construction project, a device node correlation matrix is ​​obtained by using a local maximum information coefficient method;

[0027] Obtaining a device node similarity network through graph transformation according to the device node correlation matrix;

[0028] According to the multi-dimensional pre-processed data grid of the construction project, a GMM model of the construction project and device node community labels are obtained by modeling the GMM probability density function;

[0029] Obtaining a node topology attribute model by improving the SBM model prior probability function according to the device node similarity network and the device node community label;

[0030] A construction engineering multidimensional data likelihood probability model is established by fusing the node topology attribute model and the construction engineering GMM model;

[0031] The community partitioning device node similarity network is obtained through the EM algorithm according to the construction engineering multidimensional data likelihood probability model.

[0032] Preferably, the local maximum information coefficient method expression is:

[0033] Sim(S X ,S Y )=max{M(D) m,n},

[0034]

[0035] Wherein, M(D) is the feature matrix of multidimensional preprocessing data of construction engineering, m represents the mth row of the feature matrix of multidimensional preprocessing data of construction engineering, n represents the nth column of the feature matrix of multidimensional preprocessing data of construction engineering, D represents the node pair in the topology of building equipment node, G represents the multidimensional preprocessing data grid of construction engineering, I represents mutual information, S X is a node in the building equipment node topology, S Yis a node in the building equipment node topology, Sim(S X ,S Y ) represents node S X and node S Y The maximum information coefficient between .

[0036] Preferably, the GMM prior probability function expression is:

[0037]

[0038] Where X is the multidimensional preprocessed data grid of the construction project, θ represents the GMM model parameters, P(X|θ) represents the GMM prior probability function, K represents the number of Gaussian distributions, k represents the kth Gaussian distribution, π k represents the mixing coefficient of the kth Gaussian distribution, N(X|μ k ,Σ k ) represents the GMM probability density function, μk represents the mean vector of the kth Gaussian distribution, Σ k represents the covariance matrix of the k-th Gaussian distribution.

[0039] Preferably, the improved SBM model prior probability function expression is:

[0040]

[0041] Wherein, P(A|Z,B) is the prior probability function of the improved SBM model, represents a node in the building equipment node topology, j represents a node in the building equipment node topology, Zi represents the community label of node i, and Z j represents the community label of node j, B ZiZj represents the connection probability matrix of the community to which node i and node j belong, A ij To connect the judgment label, judge A ij Is it 0? If yes, there is no connection between node i and node j; otherwise, there is a connection between node i and node j.

[0042] Preferably, the EM algorithm expression is:

[0043]

[0044]

[0045] Among them, E represents the expected calculation, Q(θ|θ (t) ) indicates that according to θ (t) The expected value of the computation guides the update function of θ.

[0046] Preferably, the obtaining of multi-dimensional fusion data of construction projects through a data fusion model according to the community division device node similarity network includes:

[0047] Obtaining a node data correlation matrix based on the multi-dimensional preprocessed data of the construction project by using the local maximum information coefficient method;

[0048] According to the community partitioning device node similarity network and the node data correlation matrix, the building engineering evidence BPA is obtained by generating an evidence probability function;

[0049] The expression of the probability function of generating evidence is:

[0050]

[0051]

[0052] Among them, m(S i ) represents the probability function of generating evidence, D k (S i ) represents node S i The support for each community after division, D j (S i ) represents node S i The support for all communities, K represents the number of communities, j represents the jth community, n k represents the number of nodes in the kth community, Sim(S i ,S j ) represents node S i and node S j The maximum information coefficient between

[0053] A trust interval matrix is ​​obtained by trust interval calculation based on the building engineering evidence BPA;

[0054] The trust interval calculation expression is:

[0055]

[0056]

[0057]

[0058] Among them, BI ij represents the confidence interval of the basic probability distribution function of evidence, Bel mj represents the trust function, Plm j represents the likelihood function, K i and R represents a proposition, m j represents the basic probability distribution function modified by evidence;

[0059] According to the community trust interval, aggregating the community trust descending interval through an ordered weighted average operator;

[0060] The multi-dimensional fusion analysis data of the construction project is obtained by sorting according to the descending interval of the community trust.

[0061] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the multi-dimensional data fusion analysis system for construction projects is implemented.

[0062] A storage medium containing computer executable instructions, which are used to execute the above-mentioned construction engineering multi-dimensional data fusion analysis system when executed by a computer processor.

[0063] The beneficial effects of the present invention are:

[0064] (1) By processing missing values ​​through the linear interpolation, the integrity of the multi-dimensional data of the construction project is ensured; by eliminating irrelevant features through the autocorrelation coefficient, the noise data can be reduced; by the normalization processing, the stability of data processing is improved; by pre-processing the multi-dimensional data of the construction project through the above steps, the reliability and efficiency of data fusion analysis are ensured;

[0065] (2) The correlation between the nodes of the construction engineering equipment and the correlation between the node data are calculated by the local maximum information coefficient method, which can better handle the correlation of the multi-dimensional data set of the construction engineering and improve the fusion quality;

[0066] (3) The node topology model is obtained by detecting the node similarity network through the improved SBM model, which can more accurately learn the complex relationship between community structure and nodes, adapt to the changes and uncertainties of the network, and improve the ability to process the correlation of multi-dimensional data sets of construction projects;

[0067] (4) The multi-dimensional fusion analysis data of construction projects obtained through the community division device node similarity network and data fusion model can comprehensively integrate and analyze the multi-dimensional data in the construction projects. Through the ordered weighted average operator aggregation and trust interval calculation, the scientificity and accuracy of the multi-dimensional data fusion analysis of construction projects can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0069] Figure 1 The present invention provides a multi-dimensional data fusion analysis system for construction projects. DETAILED DESCRIPTION

[0070] The example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein: on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art. In addition, the described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure. The blocks shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices. The flowcharts shown in the accompanying drawings are only exemplary illustrations and do not necessarily include all the content and operations / steps, nor do they necessarily have to be executed in the order described. For example, some operations / steps may be decomposed, while some operations / steps may be combined or partially combined, so the actual execution order may change according to actual circumstances.

[0071] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0072] See also Figure 1 , a multi-dimensional data fusion analysis system for construction engineering, including: a data acquisition module, a data preprocessing module, a correlation division module, and a data fusion analysis module;

[0073] The data acquisition module is used to obtain multi-dimensional data of construction projects and topology of construction equipment nodes, preset a multi-dimensional data set of construction projects, and build a data fusion analysis model based on the multi-dimensional data set of construction projects. The data fusion analysis model includes a data preprocessing model, a correlation partitioning model, and a data fusion model;

[0074] The data preprocessing module is used to obtain multi-dimensional preprocessing data of the construction project through a data preprocessing model according to the multi-dimensional data set of the construction project;

[0075] The correlation partitioning module is used to obtain a community partitioning device node similarity network based on the multi-dimensional pre-processed data of the construction project and the topology of the construction device nodes through a correlation partitioning model;

[0076] The data fusion analysis module is used to obtain multi-dimensional fusion analysis data of the construction project through a data fusion model according to the community division device node similarity network, and upload the multi-dimensional fusion analysis data of the construction project to the cloud for analysis;

[0077] In this embodiment, obtaining the multidimensional preprocessed data of the construction project through the data preprocessing model according to the multidimensional data set of the construction project includes:

[0078] Processing missing values ​​by linear interpolation based on the multidimensional dataset of the construction project to obtain a complete multidimensional dataset of the construction project;

[0079] The linear difference expression is:

[0080]

[0081] Wherein, x0 and x1 are the horizontal coordinates of the multi-dimensional data of the construction project, y0 and y1 are the vertical coordinates of the multi-dimensional data of the construction project, x is the position of the missing value, and y is the value of the missing value;

[0082] According to the complete multidimensional data set of the construction project, irrelevant features are eliminated by using the autocorrelation coefficient to obtain a complete relevant multidimensional data set of the construction project;

[0083] The autocorrelation coefficient is calculated as:

[0084]

[0085] Wherein, ACF(k) represents the autocorrelation coefficient of the complete multidimensional data of the construction project at lag k, t represents time, k represents lag time k, X represents the complete multidimensional data of the construction project, Cov(X t ,X t-k ) represents the covariance of the complete multidimensional data of the construction project at time t and tk, Var(X t ) represents the variance of the complete multidimensional data of the construction project at time t;

[0086] The multidimensional preprocessed data of the construction project is obtained by normalizing the complete multidimensional data set related to the construction project.

[0087] The normalization expression is:

[0088]

[0089] Where a represents the data in the complete multidimensional dataset of the construction project, X re For the complete multidimensional dataset of the construction project, min(X re) represents the minimum value in the complete multidimensional dataset of the construction project, max(X re ) represents the maximum value in the complete related multidimensional dataset of the construction project, Multi-dimensional preprocessing data for the construction project.

[0090] In this embodiment, the method of obtaining a community partitioning device node similarity network based on the multi-dimensional pre-processed data of the construction project and the topology of the construction device nodes through a correlation partitioning model includes:

[0091] Obtaining a construction engineering multidimensional preprocessing data grid by grid division according to the construction engineering multidimensional preprocessing data;

[0092] According to the building equipment node topology and the multi-dimensional preprocessed data grid of the construction project, a device node correlation matrix is ​​obtained by using a local maximum information coefficient method;

[0093] The expression of the local maximum information coefficient method is:

[0094] Sim(S X ,S Y )=max{M(D) m，n},

[0095]

[0096] Wherein, M(D) is the feature matrix of multidimensional preprocessing data of construction engineering, m represents the mth row of the feature matrix of multidimensional preprocessing data of construction engineering, n represents the nth column of the feature matrix of multidimensional preprocessing data of construction engineering, D represents the node pair in the topology of building equipment node, G represents the multidimensional preprocessing data grid of construction engineering, I represents mutual information, S X is a node in the building equipment node topology, S Y is a node in the building equipment node topology, Sim(S X ,S Y ) represents node S X and node S Y The maximum information coefficient between

[0097] Obtaining a device node similarity network through graph transformation according to the device node correlation matrix;

[0098] According to the multi-dimensional pre-processed data grid of the construction project, a GMM model of the construction project and device node community labels are obtained by modeling the GMM probability density function;

[0099] The GMM prior probability function expression is:

[0100]

[0101] Where X is the multidimensional preprocessed data grid of the construction project, θ represents the GMM model parameters, P(X|θ) represents the GMM prior probability function, K represents the number of Gaussian distributions, k represents the kth Gaussian distribution, π k represents the mixing coefficient of the kth Gaussian distribution, N(X|μ k ,∑ k ) represents the GMM probability density function, μ k represents the mean vector of the kth Gaussian distribution, Σ k represents the covariance matrix of the kth Gaussian distribution;

[0102] Obtaining a node topology attribute model by improving the SBM model prior probability function according to the device node similarity network and the device node community label;

[0103] The improved SBM model prior probability function expression is:

[0104]

[0105] Wherein, P(A|Z,B) is the prior probability function of the improved SBM model, represents a node in the building equipment node topology, j represents a node in the building equipment node topology, and Z i represents the community label of node i, Z j represents the community label of node j, B ZiZj represents the connection probability matrix of the community to which node i and node j belong, A ij To connect the judgment label, judge A ij Is it 0? If yes, there is no connection between node i and node j; if no, there is a connection between node i and node j;

[0106] A construction engineering multidimensional data likelihood probability model is established by fusing the node topology attribute model and the construction engineering GMM model;

[0107] Obtaining the community division device node similarity network through the EM algorithm according to the construction engineering multidimensional data likelihood probability model;

[0108] The EM algorithm expression is:

[0109]

[0110]

[0111] Among them, E represents the expected calculation, Q(θ|θ (t) ) indicates that according to θ (t) The expected value of the computation guides the update function of θ.

[0112] In this embodiment, the method of obtaining multi-dimensional fusion data of construction projects through a data fusion model according to the community division device node similarity network includes:

[0113] Obtaining a node data correlation matrix based on the multi-dimensional preprocessed data of the construction project by using the local maximum information coefficient method;

[0114] According to the community partitioning device node similarity network and the node data correlation matrix, the building engineering evidence BPA is obtained by generating an evidence probability function;

[0115] The expression of the probability function of generating evidence is:

[0116]

[0117]

[0118] Among them, m(S i ) represents the probability function of generating evidence, D k (S i ) represents node S i The support for each community after division, D j (S i ) represents node S i The support for all communities, K represents the number of communities, j represents the jth community, n k represents the number of nodes in the kth community, Sim(S i ,S j ) represents node S i and node S j The maximum information coefficient between

[0119] A trust interval matrix is ​​obtained by trust interval calculation based on the building engineering evidence BPA;

[0120] The trust interval calculation expression is:

[0121]

[0122]

[0123]

[0124] Among them, BI ij represents the confidence interval of the basic probability distribution function of evidence, Bel mj represents the trust function, Plm j represents the likelihood function, K i and R represents a proposition, m j represents the basic probability distribution function modified by evidence;

[0125] According to the community trust interval, aggregating the community trust descending interval through an ordered weighted average operator;

[0126] The multi-dimensional fusion analysis data of the construction project is obtained by sorting according to the descending interval of the community trust.

[0127] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0128] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0129] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0130] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A multi-dimensional data fusion analysis system for construction engineering, comprising a data acquisition module, a data preprocessing module, a correlation division module, and a data fusion analysis module, characterized in that: The data acquisition module is used to obtain multi-dimensional data of construction projects and topology of construction equipment nodes, preset a multi-dimensional data set of construction projects, and build a data fusion analysis model based on the multi-dimensional data set of construction projects. The data fusion analysis model includes a data preprocessing model, a correlation partitioning model, and a data fusion model; The data preprocessing module is used to obtain multi-dimensional preprocessing data of the construction project through a data preprocessing model according to the multi-dimensional data set of the construction project; The correlation partitioning module is used to obtain a community partitioning device node similarity network based on the multi-dimensional pre-processed data of the construction project and the topology of the construction device nodes through a correlation partitioning model; The data fusion analysis module is used to obtain multi-dimensional fusion analysis data of the construction project through a data fusion model according to the community division device node similarity network, and upload the multi-dimensional fusion analysis data of the construction project to the cloud for analysis.

2. The construction engineering multi-dimensional data fusion analysis system according to claim 1 is characterized in that: The obtaining of multi-dimensional pre-processed data of the construction project by using a data pre-processing model according to the multi-dimensional data set of the construction project comprises: Processing missing values ​​by linear interpolation based on the multidimensional dataset of the construction project to obtain a complete multidimensional dataset of the construction project; The linear difference expression is: Wherein, x0 and x1 are the horizontal coordinates of the multi-dimensional data of the construction project, y0 and y1 are the vertical coordinates of the multi-dimensional data of the construction project, x is the position of the missing value, and y is the value of the missing value; According to the complete multidimensional data set of the construction project, irrelevant features are eliminated by using the autocorrelation coefficient to obtain a complete relevant multidimensional data set of the construction project; The autocorrelation coefficient expression is: Wherein, ACF(k) represents the autocorrelation coefficient of the complete multidimensional data of the construction project at lag k, t represents time, k represents lag time k, X represents the complete multidimensional data of the construction project, Cov(X t ,X t-k ) represents the covariance of the complete multidimensional data of the construction project at time t and tk, Var(X t ) represents the variance of the complete multidimensional data of the construction project at time t; Obtaining the multidimensional preprocessed data of the construction project through normalization processing according to the complete multidimensional data set related to the construction project; The normalization expression is: Where a represents the data in the complete multidimensional dataset of the construction project, X re For the complete multidimensional dataset of the construction project, min(X re ) represents the minimum value in the complete multidimensional dataset of the construction project, max(X re ) represents the maximum value in the complete related multidimensional dataset of the construction project, Multi-dimensional preprocessing data for the construction project.

3. The construction engineering multi-dimensional data fusion analysis system according to claim 1 is characterized in that: The device node similarity network of community partitioning is obtained by using a correlation partitioning model based on the multi-dimensional pre-processed data of the construction project and the topology of the construction device nodes, and includes: Obtaining a construction engineering multidimensional preprocessing data grid by grid division according to the construction engineering multidimensional preprocessing data; According to the building equipment node topology and the multi-dimensional pre-processed data grid of the construction project, a device node correlation matrix is ​​obtained by using a local maximum information coefficient method; Obtaining a device node similarity network through graph transformation according to the device node correlation matrix; According to the multi-dimensional pre-processed data grid of the construction project, a GMM model of the construction project and device node community labels are obtained by modeling the GMM probability density function; Obtaining a node topology attribute model by improving the SBM model prior probability function according to the device node similarity network and the device node community label; A construction engineering multidimensional data likelihood probability model is established by fusing the node topology attribute model and the construction engineering GMM model; The community division device node similarity network is obtained through the EM algorithm according to the construction engineering multidimensional data likelihood probability model.

4. The construction engineering multi-dimensional data fusion analysis system according to claim 3 is characterized in that: The expression of the local maximum information coefficient method is: Sim(S X ,S Y )=max{M(D) m,n }, Wherein, M(D) is the feature matrix of multidimensional preprocessing data of construction engineering, m represents the mth row of the feature matrix of multidimensional preprocessing data of construction engineering, n represents the nth column of the feature matrix of multidimensional preprocessing data of construction engineering, D represents the node pair in the topology of building equipment node, G represents the multidimensional preprocessing data grid of construction engineering, I represents mutual information, S X is a node in the building equipment node topology, S Y is a node in the building equipment node topology, Sim(S X ,S Y ) represents node S X and node S Y The maximum information coefficient between .

5. The construction engineering multi-dimensional data fusion analysis system according to claim 3 is characterized in that: The GMM prior probability function expression is: Where X is the multidimensional preprocessed data grid of the construction project, θ represents the GMM model parameters, P(X|θ) represents the GMM prior probability function, K represents the number of Gaussian distributions, k represents the kth Gaussian distribution, π k represents the mixing coefficient of the kth Gaussian distribution, N(X|μ k ,∑ k ) represents the GMM probability density function, μ k represents the mean vector of the kth Gaussian distribution, ∑ k represents the covariance matrix of the k-th Gaussian distribution.

6. The construction engineering multi-dimensional data fusion analysis system according to claim 3 is characterized in that: The improved SBM model prior probability function expression is: Wherein, P(A|Z,B) is the prior probability function of the improved SBM model, represents a node in the building equipment node topology, j represents a node in the building equipment node topology, and Z i represents the community label of node i, Z j represents the community label of node j, B ZiZj represents the connection probability matrix of the community to which node i and node j belong, A ij To connect the judgment label, judge A ij Is it 0? If yes, there is no connection between node i and node j; otherwise, there is a connection between node i and node j.

7. The construction engineering multi-dimensional data fusion analysis system according to claim 3 is characterized in that: The EM algorithm expression is: Among them, E represents the expected calculation, Q(θ|θ (t) ) indicates that according to θ (t) The expected value of the computation guides the update function of θ.

8. The construction engineering multi-dimensional data fusion analysis system according to claim 1, characterized in that: The obtaining of multi-dimensional fusion data of construction engineering by using a data fusion model based on the community division device node similarity network includes: Obtaining a node data correlation matrix based on the multi-dimensional preprocessed data of the construction project by using the local maximum information coefficient method; According to the community partitioning device node similarity network and the node data correlation matrix, the building engineering evidence BPA is obtained by generating an evidence probability function; The expression of the probability function of generating evidence is: Among them, m(S i ) represents the probability function of generating evidence, D k (S i ) represents node S i The support for each community after division, D j (S i ) represents node S i The support for all communities, K represents the number of communities, j represents the jth community, n k represents the number of nodes in the kth community, Sim(S i ,S j ) represents node S i and node S j The maximum information coefficient between A trust interval matrix is ​​obtained by trust interval calculation based on the building engineering evidence BPA; The trust interval calculation expression is: Among them, BI ij represents the confidence interval of the basic probability distribution function of evidence, Bel mj represents the trust function, Plm j represents the likelihood function, K i and R represents a proposition, m j represents the basic probability distribution function modified by evidence; According to the community trust interval, aggregating the community trust descending interval through an ordered weighted average operator; The multi-dimensional fusion analysis data of the construction project is obtained by sorting according to the descending interval of the community trust.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, a multi-dimensional data fusion analysis system for construction projects as described in any one of claims 1-8 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the construction engineering multi-dimensional data fusion analysis system as described in any one of claims 1-8.

Images