Intelligent decision-making and risk early warning system for constructional engineering

Abstract

The invention relates to an intelligent decision-making and risk early warning method for constructional engineering, and belongs to the technical field of constructional engineering management. The method comprises the following steps: acquiring real-time construction information data of the constructional engineering, synchronously uploading the real-time construction information data to a cloud server through a data transmission network, constructing a historical construction information data set of the constructional engineering, and obtaining a historical construction information standard set of the constructional engineering through data preprocessing, a building engineering historical construction information feature set is extracted through a data mining technology, a building engineering risk early warning initial model is obtained through gradient lifting decision tree training and testing, and optimal parameters are selected through Bayesian iteration in combination with a building engineering cost sensitive function to obtain a building engineering risk early warning model. According to the real-time construction information data of the constructional engineering, constructional engineering risk early warning information is obtained through the constructional engineering risk early warning model and sent to a terminal through a remote communication system, so that managers are helped to make decisions in time, and the construction safety of the constructional engineering is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of construction project management, and in particular relates to a construction project intelligent decision-making and risk early warning method and system. Background Art

[0002] In traditional construction project management, the decision-making process often relies on manual processing. As the scale of construction projects expands, the limitations of this approach become increasingly prominent. The introduction of intelligent technology provides managers with powerful auxiliary tools, which can generate construction project risk warning information by collecting and analyzing a large amount of construction data in real time, thereby helping managers make more accurate decisions and ensuring the safety of construction workers.

[0003] However, the existing early warning model for construction project risks has the problem of low early warning accuracy, which easily leads to false alarms or missed alarms, reducing the effectiveness of the early warning system. In addition, after the existing technology generates early warning information, it cannot be quickly transmitted to management personnel, which further reduces the decision-making efficiency, making it impossible to take effective preventive and response measures in time, resulting in increased safety risks in construction projects, which will not only cause significant economic losses, but may also lead to casualties. Summary of the invention

[0004] In order to solve the above-mentioned problems existing in the prior art, the present invention proposes a method for intelligent decision-making and risk warning of construction projects, which obtains real-time construction information of construction projects and synchronously uploads it to a cloud server for secure storage and management. By constructing a highly accurate construction project risk warning model, it effectively identifies potential construction risks and generates warning information in a timely manner. At the same time, it is quickly sent to the terminal through a remote communication system to ensure that managers can grasp the latest construction risk status and improve decision-making efficiency, thereby taking corresponding preventive and response measures to ensure the safety of construction projects and reduce economic losses.

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

[0006] A construction engineering intelligent decision-making and risk early warning method, comprising:

[0007] Acquire real-time construction information data of the building project, and synchronously upload the real-time construction information data of the building project to the cloud server through the data transmission network to obtain a building project construction information database;

[0008] Constructing a historical construction information data set of a construction project according to the construction information database of the construction project, and obtaining a standard set of historical construction information of the construction project through data preprocessing according to the historical construction information data set of the construction project;

[0009] According to the standard set of historical construction information of the construction project, a feature set of historical construction information of the construction project is extracted by data mining technology, and according to the feature set of historical construction information of the construction project, a risk early warning model of the construction project is obtained by gradient boosting decision tree training and testing;

[0010] According to the real-time construction information data of the construction project, the construction project risk warning information is obtained through the construction project risk warning model, and the construction project risk warning information is sent to the terminal through the remote communication system.

[0011] Preferably, the step of acquiring real-time construction information data of a construction project and synchronously uploading the real-time construction information data of the construction project to a cloud server through a data transmission network to obtain a construction information database of the construction project comprises:

[0012] The real-time construction information data of the construction project includes construction temperature data, construction humidity data, construction structure vibration data, and construction structure displacement data;

[0013] Synchronously uploading the real-time construction information data of the construction project to the cloud server via the SFTP transmission protocol;

[0014] According to the real-time construction information data of the construction project, a construction information database of the construction project is established through the cloud server and a data backup and recovery mechanism is set.

[0015] Preferably, the construction project risk warning model is obtained by training and testing a gradient boosting decision tree based on the construction project historical construction information feature set, including:

[0016] According to the feature set of the historical construction information of the building project, a training set of the historical construction information of the building project and a test set of the historical construction information of the building project are obtained by dividing the data set;

[0017] According to the historical construction information training set of the construction project, an initial model for early warning of construction project risks is obtained by gradient boosting decision tree training;

[0018] According to the test set of historical construction information of the construction project, a warning result of the initial model of the risk warning of the construction project is obtained by a gradient boosting decision tree test;

[0019] According to the warning result of the initial model of risk warning of construction engineering, the performance index of the initial model of risk warning of construction engineering is evaluated to obtain the evaluation result of the initial model of risk warning of construction engineering. The performance index of the initial model of risk warning of construction engineering includes the accuracy rate of the initial model of risk warning of construction engineering. The mathematical expression is:

[0020]

[0021] Among them, A is the accuracy rate of the initial model for construction project risk warning, R is the recall rate of the initial model for construction project risk warning, TP is the number of samples that the initial model for construction project risk warning correctly predicts as construction project risk samples, FP is the number of samples that the initial model for construction project risk warning will actually be normal samples of construction projects but are incorrectly predicted as construction project risk samples by the model, TN is the number of samples that the initial model for construction project risk warning will actually be normal samples of construction projects and are correctly predicted as normal samples of construction projects by the model, and FN is the number of samples that the initial model for construction project risk warning will actually be construction project risk samples but are incorrectly predicted as normal samples of construction projects by the model;

[0022] According to the evaluation result of the initial model for early warning of construction project risks, the initial model for early warning of construction project risks is optimized through iterative conditions to obtain the early warning model for construction project risks.

[0023] Preferably, the optimization iteration conditions of the construction engineering risk warning initial model include:

[0024] Iterating the initial model of risk warning of construction projects through Bayesian optimization according to the preset number of iterations of the initial model of risk warning of construction projects to obtain the optimal parameter set of the initial model of risk warning of construction projects, wherein the optimal parameter set of the initial model of risk warning of construction projects is the top ten parameter sets with the best accuracy of the initial model of risk warning of construction projects within the preset number of iterations of the initial model of risk warning of construction projects;

[0025] According to the optimal parameter set of the initial model for risk early warning of construction projects, the risk early warning model of construction projects is obtained by adjusting and optimizing the risk cost sensitivity function of construction projects. The mathematical expression of the risk cost sensitivity function of construction projects is:

[0026] Cost = C FP *FP+C FN *FN

[0027] Wherein, FP is the number of samples that are actually normal samples of construction projects but are mistakenly predicted as risk samples of construction projects by the initial model of construction project risk warning, FN is the number of samples that are actually risk samples of construction projects but are mistakenly predicted as normal samples of construction projects by the initial model of construction project risk warning, and C FP is the FP cost weight of construction project risk warning, C FN FN cost weight for construction project risk warning;

[0028] According to the optimal parameter set of the initial model for early warning of construction project risks, the construction project risk cost corresponding to each parameter is calculated by using the construction project risk cost sensitivity function;

[0029] According to the construction project risk costs corresponding to the parameters, the minimum construction project risk cost parameter is selected by comparison;

[0030] According to the construction project risk warning initial model, a construction project risk warning model is obtained by setting the minimum parameter of the construction project risk cost.

[0031] Preferably, the method of iterating the initial model of risk warning of construction engineering through Bayesian optimization according to the preset number of iterations of the initial model of risk warning of construction engineering to obtain the optimal parameter set of the initial model of risk warning of construction engineering comprises:

[0032] According to the gradient boosting decision tree, a hyperparameter space of the initial model for early warning of construction engineering risks is defined and a prior distribution is initialized, wherein the hyperparameter space of the initial model for early warning of construction engineering risks includes a learning rate, the number of trees, a minimum split size, a minimum leaf node size, and a maximum depth;

[0033] Initialize the construction project risk warning initial model by randomly selecting a set of parameters according to the hyperparameter space of the construction project risk warning initial model;

[0034] Iteratively updating the prior distribution according to the construction project risk early warning initial model until a preset number of iterations of the construction project risk early warning initial model is reached;

[0035] According to the prior distribution, the optimal parameter combination is selected by maximizing the expectation to obtain the optimal parameter set of the initial model of construction project risk warning.

[0036] An intelligent decision-making and risk warning system for construction projects using the above-mentioned intelligent decision-making and risk warning method for construction projects, comprising a data acquisition module, a data storage module, a risk warning module, and a remote communication module;

[0037] The data acquisition module is used to obtain real-time construction information data of the building project through sensors;

[0038] The data storage module is used to synchronously upload the real-time construction information data of the construction project to the cloud server through the data transmission network to obtain a construction information database of the construction project;

[0039] The risk warning module is used to obtain the risk warning information of the construction project through the risk warning model of the construction project according to the real-time construction information data of the construction project;

[0040] The remote communication module is used to send the construction project risk warning information to the terminal.

[0041] 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 above-mentioned intelligent decision-making and risk warning method for construction engineering is implemented.

[0042] A storage medium containing computer executable instructions, which are used to execute the above-mentioned construction engineering intelligent decision-making and risk warning method when executed by a computer processor.

[0043] The beneficial effects of the present invention are:

[0044] (1) Real-time construction information of construction projects is synchronously uploaded to the cloud server through the data transmission network for secure storage and management, ensuring the real-time and traceability of the information.

[0045] (2) The optimal parameter set of the initial model for risk warning of construction projects is obtained by iterating the initial model for risk warning of construction projects through Bayesian optimization, thereby improving the prediction accuracy of the model.

[0046] (3) According to the optimal parameter set of the initial model for risk warning of construction projects, the risk warning model of construction projects is obtained by adjusting and optimizing the risk cost sensitivity function of construction projects, finding a balance between false alarms and missed alarms, and selecting the optimal risk parameters of construction projects, thereby reducing the risks and costs in the actual application of construction projects.

[0047] (4) A highly accurate construction project risk warning model is constructed through the gradient boosting decision tree, which can effectively identify potential construction risks and generate warning information in a timely manner and send it to the terminal quickly through the remote communication system, ensuring that managers can grasp the latest construction risk status and improve decision-making efficiency, so as to take corresponding preventive and response measures to ensure the safety of construction projects and reduce economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0049] Figure 1 The present invention is a flowchart of a construction engineering intelligent decision-making and risk warning method. DETAILED DESCRIPTION

[0050] 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.

[0051] See also Figure 1 , a construction engineering intelligent decision-making and risk early warning method, comprising:

[0052] S1: Acquire real-time construction information data of a construction project through a sensor, and synchronously upload the real-time construction information data of the construction project to a cloud server through a data transmission network to obtain a construction information database of the construction project;

[0053] S2: constructing a data set of historical construction information of a building project according to the said database of construction information of the building project, and obtaining a standard set of historical construction information of the building project through data preprocessing according to the said data set of historical construction information of the building project;

[0054] S3: extracting a feature set of historical construction information of a construction project through data mining technology according to the standard set of historical construction information of the construction project, and obtaining a risk early warning model of the construction project through gradient boosting decision tree training and testing according to the feature set of historical construction information of the construction project;

[0055] S4: Obtaining construction project risk warning information through the construction project risk warning model according to the real-time construction information data of the construction project, and sending the construction project risk warning information to the terminal through the remote communication system.

[0056] In step S1, real-time construction information data of a construction project is obtained through a sensor, and the real-time construction information data of the construction project is synchronously uploaded to a cloud server through a data transmission network to obtain a construction information database of the construction project, which specifically includes the following steps:

[0057] S101: Acquire real-time construction information data of a construction project through a sensor, wherein the real-time construction information data of the construction project includes construction temperature data of the construction project, construction humidity data of the construction project, construction structure vibration data, and construction structure displacement data of the construction project;

[0058] S102: Synchronously uploading the real-time construction information data of the building project to a cloud server via the SFTP transmission protocol;

[0059] S103: Establishing a construction project construction information database through the cloud server according to the real-time construction information data of the construction project and setting a data backup and recovery mechanism.

[0060] In step S3, obtaining a construction project risk warning model through gradient boosting decision tree training and testing according to the construction project historical construction information feature set specifically includes the following steps:

[0061] S301: obtaining a training set of historical construction information of a building project and a test set of historical construction information of a building project by dividing the data set according to the feature set of historical construction information of the building project;

[0062] S302: Obtaining an initial model for early warning of construction project risks by gradient boosting decision tree training based on the training set of historical construction information of the construction project;

[0063] S303: Obtaining the warning result of the initial model of risk warning of the construction project through a gradient boosting decision tree test according to the test set of historical construction information of the construction project;

[0064] S304: According to the warning result of the initial model of risk warning of the construction project, the performance index of the initial model of risk warning of the construction project is evaluated to obtain the evaluation result of the initial model of risk warning of the construction project, wherein the performance index of the initial model of risk warning of the construction project includes the accuracy rate of the initial model of risk warning of the construction project, and the mathematical expression is:

[0065]

[0066] Among them, A is the accuracy rate of the initial model for construction project risk warning, R is the recall rate of the initial model for construction project risk warning, TP is the number of samples that the initial model for construction project risk warning correctly predicts as construction project risk samples, FP is the number of samples that the initial model for construction project risk warning will actually be normal samples of construction projects but are incorrectly predicted as construction project risk samples by the model, TN is the number of samples that the initial model for construction project risk warning will actually be normal samples of construction projects and are correctly predicted as normal samples of construction projects by the model, and FN is the number of samples that the initial model for construction project risk warning will actually be construction project risk samples but are incorrectly predicted as normal samples of construction projects by the model;

[0067] S305: Obtaining a construction project risk warning model by optimizing iterative conditions of the construction project risk warning initial model according to the evaluation result of the construction project risk warning initial model.

[0068] The optimization iteration conditions of the initial model for early warning of construction project risks in step S305 specifically include the following steps:

[0069] S305-1: Iterate the initial model of risk warning of construction projects through Bayesian optimization according to the preset number of iterations of the initial model of risk warning of construction projects to obtain the optimal parameter set of the initial model of risk warning of construction projects, wherein the optimal parameter set of the initial model of risk warning of construction projects is the top ten parameter sets with the best accuracy performance of the initial model of risk warning of construction projects within the preset number of iterations of the initial model of risk warning of construction projects.

[0070] The step S305-1 specifically includes:

[0071] According to the gradient boosting decision tree, a hyperparameter space of the initial model for early warning of construction engineering risks is defined and a prior distribution is initialized, wherein the hyperparameter space of the initial model for early warning of construction engineering risks includes a learning rate, the number of trees, a minimum split size, a minimum leaf node size, and a maximum depth;

[0072] Initialize the construction project risk warning initial model by randomly selecting a set of parameters according to the hyperparameter space of the construction project risk warning initial model;

[0073] Iteratively updating the prior distribution according to the construction project risk early warning initial model until a preset number of iterations of the construction project risk early warning initial model is reached;

[0074] According to the prior distribution, the optimal parameter combination is selected by maximizing the expectation to obtain the optimal parameter set of the initial model of construction project risk warning:

[0075] S305-2: According to the optimal parameter set of the initial model for risk early warning of construction projects, the risk early warning model of construction projects is obtained by adjusting and optimizing the risk cost sensitivity function of construction projects. The mathematical expression of the risk cost sensitivity function of construction projects is:

[0076] Cost = C FP *FP+C FN *FN

[0077] Wherein, FP is the number of samples that are actually normal samples of construction projects but are mistakenly predicted as risk samples of construction projects by the initial model of construction project risk warning, FN is the number of samples that are actually risk samples of construction projects but are mistakenly predicted as normal samples of construction projects by the initial model of construction project risk warning, and C FP is the FP cost weight of construction project risk warning, C FN FN cost weight for construction project risk warning;

[0078] S305-3: Calculating the construction project risk cost corresponding to each parameter through the construction project risk cost sensitivity function according to the optimal parameter set of the construction project risk warning initial model;

[0079] S305-4: selecting and comparing the construction project risk costs corresponding to the parameters to obtain the minimum construction project risk cost parameter;

[0080] S305-5: Obtain a construction project risk warning model according to the construction project risk warning initial model by setting the construction project risk cost minimum parameter.

[0081] In step S4, the construction project risk warning information is sent to the terminal through the remote communication system. It should be noted that the construction project risk warning information includes abnormal construction information and normal construction information of the construction project;

[0082] An intelligent decision-making and risk warning system for construction projects, comprising a data acquisition module, a data storage module, a risk warning module, and a remote communication module;

[0083] The data acquisition module is used to obtain real-time construction information data of the building project through sensors;

[0084] The data storage module is used to synchronously upload the real-time construction information data of the construction project to the cloud server through the data transmission network to obtain a construction information database of the construction project;

[0085] The risk warning module is used to obtain the risk warning information of the construction project through the risk warning model of the construction project according to the real-time construction information data of the construction project;

[0086] The remote communication module is used to send the construction project risk warning information to relevant terminals.

[0087] 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.

[0088] 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.

[0089] 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).

[0090] 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 construction engineering intelligent decision-making and risk early warning method, characterized in that: include: Acquire real-time construction information data of the building project, and synchronously upload the real-time construction information data of the building project to the cloud server through the data transmission network to obtain a building project construction information database; Constructing a historical construction information data set of a construction project according to the construction information database of the construction project, and obtaining a standard set of historical construction information of the construction project through data preprocessing according to the historical construction information data set of the construction project; According to the standard set of historical construction information of the construction project, a feature set of historical construction information of the construction project is extracted by data mining technology, and according to the feature set of historical construction information of the construction project, a risk early warning model of the construction project is obtained by gradient boosting decision tree training and testing; According to the real-time construction information data of the construction project, the construction project risk warning information is obtained through the construction project risk warning model, and the construction project risk warning information is sent to the terminal through the remote communication system.

2. The intelligent decision-making and risk warning method for construction engineering according to claim 1 is characterized in that: The obtaining of real-time construction information data of a construction project, and synchronously uploading the real-time construction information data of the construction project to a cloud server through a data transmission network to obtain a construction information database of the construction project comprises: The real-time construction information data of the construction project includes construction temperature data, construction humidity data, construction structure vibration data, and construction structure displacement data; Synchronously uploading the real-time construction information data of the construction project to the cloud server via the SFTP transmission protocol; According to the real-time construction information data of the construction project, a construction information database of the construction project is established through the cloud server and a data backup and recovery mechanism is set.

3. The intelligent decision-making and risk warning method for construction engineering according to claim 1 is characterized in that: The construction project risk warning model obtained by training and testing a gradient boosting decision tree based on the construction project historical construction information feature set includes: According to the feature set of the historical construction information of the building project, a training set of the historical construction information of the building project and a test set of the historical construction information of the building project are obtained by dividing the data set; According to the historical construction information training set of the construction project, an initial model for early warning of construction project risks is obtained by gradient boosting decision tree training; According to the test set of historical construction information of the construction project, a warning result of the initial model of the risk warning of the construction project is obtained by a gradient boosting decision tree test; According to the warning result of the initial model of risk warning of construction engineering, the performance index of the initial model of risk warning of construction engineering is evaluated to obtain the evaluation result of the initial model of risk warning of construction engineering. The performance index of the initial model of risk warning of construction engineering includes the accuracy rate of the initial model of risk warning of construction engineering. The mathematical expression is: Among them, A is the accuracy rate of the initial model for construction project risk warning, R is the recall rate of the initial model for construction project risk warning, TP is the number of samples that the initial model for construction project risk warning correctly predicts as construction project risk samples, FP is the number of samples that the initial model for construction project risk warning will actually be normal samples of construction projects but are incorrectly predicted as construction project risk samples by the model, TN is the number of samples that the initial model for construction project risk warning will actually be normal samples of construction projects and are correctly predicted as normal samples of construction projects by the model, and FN is the number of samples that the initial model for construction project risk warning will actually be construction project risk samples but are incorrectly predicted as normal samples of construction projects by the model; According to the evaluation result of the initial model for early warning of construction project risks, the initial model for early warning of construction project risks is optimized through iterative conditions to obtain the early warning model for construction project risks.

4. A construction engineering intelligent decision-making and risk early warning method according to claim 3, characterized in that: The optimization and iteration conditions of the initial model for early warning of construction engineering risks include: Iterating the initial model of risk warning of construction projects through Bayesian optimization according to the preset number of iterations of the initial model of risk warning of construction projects to obtain the optimal parameter set of the initial model of risk warning of construction projects, wherein the optimal parameter set of the initial model of risk warning of construction projects is the top ten parameter sets with the best accuracy of the initial model of risk warning of construction projects within the preset number of iterations of the initial model of risk warning of construction projects; According to the optimal parameter set of the initial model for risk early warning of construction projects, the risk early warning model of construction projects is obtained by adjusting and optimizing the risk cost sensitivity function of construction projects. The mathematical expression of the risk cost sensitivity function of construction projects is: Cost=C FP *FP+C FN *FN Wherein, FP is the number of samples that are actually normal samples of construction projects but are mistakenly predicted as risk samples of construction projects by the initial model of construction project risk warning, FN is the number of samples that are actually risk samples of construction projects but are mistakenly predicted as normal samples of construction projects by the initial model of construction project risk warning, and C FP is the FP cost weight of construction project risk warning, C FN FN cost weight for risk warning of construction projects; According to the optimal parameter set of the initial model for early warning of construction project risks, the construction project risk cost corresponding to each parameter is calculated by using the construction project risk cost sensitivity function; According to the construction project risk costs corresponding to the parameters, the minimum construction project risk cost parameter is selected by comparison; According to the construction project risk warning initial model, a construction project risk warning model is obtained by setting the minimum parameter of the construction project risk cost.

5. A construction engineering intelligent decision-making and risk early warning method according to claim 4, characterized in that: The optimal parameter set of the initial model for risk warning of construction projects is obtained by iterating the initial model for risk warning of construction projects through Bayesian optimization according to the preset number of iterations of the initial model for risk warning of construction projects, including: According to the gradient boosting decision tree, a hyperparameter space of the initial model for early warning of construction engineering risks is defined and a prior distribution is initialized, wherein the hyperparameter space of the initial model for early warning of construction engineering risks includes a learning rate, the number of trees, a minimum split size, a minimum leaf node size, and a maximum depth; Initialize the construction project risk warning initial model by randomly selecting a set of parameters according to the hyperparameter space of the construction project risk warning initial model; Iteratively updating the prior distribution according to the construction project risk early warning initial model until a preset number of iterations of the construction project risk early warning initial model is reached; According to the prior distribution, the optimal parameter combination is selected by maximizing the expectation to obtain the optimal parameter set of the initial model of construction project risk warning.

6. A construction engineering intelligent decision-making and risk warning system using the construction engineering intelligent decision-making and risk warning method of claim 1, comprising a data acquisition module, a data storage module, a risk warning module, and a remote communication module, characterized in that: The data acquisition module is used to obtain real-time construction information data of the building project through sensors; The data storage module is used to synchronously upload the real-time construction information data of the construction project to the cloud server through the data transmission network to obtain a construction information database of the construction project; The risk warning module is used to obtain the construction project risk warning information through the construction project risk warning model according to the real-time construction information data of the construction project; The remote communication module is used to send the construction project risk warning information to the terminal.

7. 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, it implements a construction engineering intelligent decision-making and risk warning method as described in any one of claims 1-6.

8. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute a construction engineering intelligent decision-making and risk warning method as described in any one of claims 1-6.

Images