AI-based construction project risk prediction and decision optimization method and system

Abstract

The invention provides a construction project risk prediction and decision optimization method and system based on AI, and relates to the field of construction project risk prediction, and the method comprises the steps: decomposing a construction project into a plurality of stages, recognizing the risk factors of each stage, constructing a multi-level risk index system, determining the weight of each index, forming a fuzzy relation matrix, and determining the risk level. And a corresponding risk coping strategy is generated, and effective prediction and decision optimization of the construction project risk are realized.

Description

Technical Field

[0001] The present application relates to the field of construction project risk prediction, and in particular to an AI-based construction project risk prediction and decision optimization method and system. Background Art

[0002] During the implementation of construction projects, there are many risks, such as safety risks, cost risks, schedule risks, quality risks, etc. If these risks are not identified and managed in a timely manner, they may lead to serious consequences such as project delays, cost overruns, substandard quality, and even safety accidents.

[0003] Traditional construction project risk prediction and decision-making rely primarily on manual experience, conducted through expert evaluation and historical data comparison. However, this approach has numerous limitations: First, manual evaluations are significantly influenced by subjective factors, and the experience and judgment criteria of different experts vary, making it difficult to ensure the accuracy and consistency of risk assessment results. Second, as construction projects continue to expand in scale and complexity, the number of risk factors involved increases. Manual processing of large amounts of information is inefficient, making it difficult to comprehensively and promptly identify and predict risks, and unable to quickly generate effective risk response strategies. Summary of the Invention

[0004] The embodiments of the present application provide an AI-based construction project risk prediction and decision optimization method and system to improve the above-mentioned problems.

[0005] To achieve the above objectives, this application adopts the following technical solutions:

[0006] First, this application proposes an AI-based construction project risk prediction and decision optimization method, which includes:

[0007] Break down construction projects into phases based on the work breakdown structure and identify risk factors for each phase;

[0008] Construct a multi-level risk indicator system based on risk factors, which includes primary indicators and secondary indicators;

[0009] Based on the preset scaling rules, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix. The weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization.

[0010] Define the risk level domain, evaluate the risk level of each secondary indicator in the multi-level risk indicator system based on historical project data and industry standards, calculate the support rate of each risk level, and form a fuzzy relationship matrix;

[0011] Based on the weights of each indicator and the fuzzy relationship matrix, a comprehensive evaluation calculation is performed to determine the risk level of the construction project as a whole or at each stage.

[0012] In conjunction with the first aspect, in some embodiments, based on a preset scaling rule, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified, a judgment matrix is ​​constructed, and the weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization, including:

[0013] The scaling method is used to quantitatively score the relative importance of indicators at the same level in the multi-level risk indicator system and construct a judgment matrix.

[0014] In conjunction with the first aspect, in some embodiments, based on a preset scaling rule, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified, a judgment matrix is ​​constructed, and the weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization, including:

[0015] By multiplying the weight vector of each indicator with the fuzzy relationship matrix, the secondary indicator evaluation results are obtained;

[0016] The evaluation results of the secondary indicators are used as a new fuzzy matrix, and the final risk level is calculated in combination with the weights of the primary indicators in the multi-level risk indicator system.

[0017] In conjunction with the first aspect, in some implementations, a risk level domain is defined, and based on historical project data and industry standards, a risk level assessment is performed on each secondary indicator in the multi-level risk indicator system. The support rate of each risk level is calculated to form a fuzzy relationship matrix, including:

[0018] Define multiple risk levels of different degrees to form the risk level domain.

[0019] In conjunction with the first aspect, in some implementations, a risk level domain is defined, and based on historical project data and industry standards, a risk level assessment is performed on each secondary indicator in the multi-level risk indicator system. The support rate of each risk level is calculated to form a fuzzy relationship matrix, including:

[0020] The fuzzy relationship matrix is ​​subjected to consistency check. If the consistency requirement is not met, the risk level of the secondary indicators in the multi-level risk indicator system is re-evaluated based on historical project data and industry standards. In conjunction with the first aspect, in some embodiments, the method further includes:

[0021] According to the determined risk level and the preset strategy library, the corresponding risk response strategy is matched and generated.

[0022] In conjunction with the first aspect, in some embodiments, according to the determined risk level and the preset strategy library, a corresponding risk response strategy is matched and generated, including:

[0023] According to the risk level, the strategies in the strategy library are divided into emergency response strategies, key prevention and control strategies, and routine monitoring strategies;

[0024] If the determined risk level is high risk or very high risk, the emergency response strategy will be matched first from the strategy library; if it is medium risk, the key prevention and control strategy will be matched; if it is low risk or very low risk, the conventional monitoring strategy will be matched.

[0025] Based on the specific secondary indicators that lead to risk levels in the multi-level risk indicator system, targeted strategies are further screened among the matched strategy types.

[0026] In conjunction with the first aspect, in some embodiments, according to the determined risk level and the preset strategy library, a corresponding risk response strategy is matched and generated, including:

[0027] Conduct feasibility assessment on the generated risk response strategies based on the actual resource situation, cost budget and time constraints of the construction project;

[0028] If the risk response strategy is not feasible, an alternative strategy will be selected from the strategy library and regenerated according to the preset priority rules.

[0029] Secondly, this application proposes an AI-based construction project risk prediction and decision optimization system, characterized in that the system is configured to:

[0030] Break down construction projects into phases based on the work breakdown structure and identify risk factors for each phase;

[0031] Construct a multi-level risk indicator system based on risk factors, which includes primary indicators and secondary indicators;

[0032] Based on the preset scaling rules, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix. The weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization.

[0033] Define the risk level domain, evaluate the risk level of each secondary indicator in the multi-level risk indicator system based on historical project data and industry standards, calculate the support rate of each risk level, and form a fuzzy relationship matrix;

[0034] Based on the weights of each indicator and the fuzzy relationship matrix, a comprehensive evaluation calculation is performed to determine the risk level of the construction project as a whole or at each stage.

[0035] Secondly, this application proposes an AI-based construction project risk prediction and decision optimization system, which is configured to:

[0036] Based on the preset scaling rules, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix. The weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization, including:

[0037] The scaling method is used to quantitatively score the relative importance of indicators at the same level in the multi-level risk indicator system and construct a judgment matrix.

[0038] In conjunction with the second aspect, in some embodiments, the system is configured to:

[0039] Based on the preset scaling rules, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix. The weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization, including:

[0040] By multiplying the weight vector of each indicator with the fuzzy relationship matrix, the secondary indicator evaluation results are obtained;

[0041] The evaluation results of the secondary indicators are used as a new fuzzy matrix, and the final risk level is calculated in combination with the weights of the primary indicators in the multi-level risk indicator system.

[0042] In conjunction with the second aspect, in some embodiments, the system is configured to:

[0043] Define the risk level domain, evaluate the risk level of each secondary indicator in the multi-level risk indicator system based on historical project data and industry standards, calculate the support rate of each risk level, and form a fuzzy relationship matrix, including:

[0044] Define multiple risk levels of different degrees to form the risk level domain.

[0045] In conjunction with the second aspect, in some embodiments, the system is configured to:

[0046] Define the risk level domain, evaluate the risk level of each secondary indicator in the multi-level risk indicator system based on historical project data and industry standards, calculate the support rate of each risk level, and form a fuzzy relationship matrix, including:

[0047] The fuzzy relationship matrix is ​​checked for consistency. If the consistency requirement is not met, the risk level of the secondary indicators in the multi-level risk indicator system is re-evaluated based on historical project data and industry standards. In conjunction with the second aspect, in some embodiments, the system is configured as follows:

[0048] According to the determined risk level and the preset strategy library, the corresponding risk response strategy is matched and generated.

[0049] In conjunction with the second aspect, in some embodiments, the system is configured to:

[0050] Based on the determined risk level and the preset strategy library, the corresponding risk response strategies are matched and generated, including:

[0051] According to the risk level, the strategies in the strategy library are divided into emergency response strategies, key prevention and control strategies, and routine monitoring strategies;

[0052] If the determined risk level is high risk or very high risk, the emergency response strategy will be matched first from the strategy library; if it is medium risk, the key prevention and control strategy will be matched; if it is low risk or very low risk, the conventional monitoring strategy will be matched.

[0053] Based on the specific secondary indicators that lead to risk levels in the multi-level risk indicator system, targeted strategies are further screened among the matched strategy types.

[0054] In conjunction with the second aspect, in some embodiments, the system is configured to:

[0055] Based on the determined risk level and the preset strategy library, the corresponding risk response strategies are matched and generated, including:

[0056] Conduct feasibility assessment on the generated risk response strategies based on the actual resource situation, cost budget and time constraints of the construction project;

[0057] If the risk response strategy is not feasible, an alternative strategy will be selected from the strategy library and regenerated according to the preset priority rules.

[0058] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including:

[0059] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method proposed in the first aspect of the embodiment of the present invention.

[0060] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the embodiment of the present invention.

[0061] In summary, the above method and system have the following technical effects:

[0062] This application proposes an AI-based construction project risk prediction and decision-making optimization method. By decomposing a construction project into multiple stages, identifying the risk factors in each stage, constructing a multi-level risk indicator system, determining the weight of each indicator, forming a fuzzy relationship matrix, and then determining the risk level, and generating corresponding risk response strategies, it can achieve effective prediction of construction project risks and decision-making optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A flowchart of an AI-based construction project risk prediction and decision optimization method proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0065] This application proposes an AI-based construction project risk prediction and decision optimization method. Figure 1 , the method comprises the following steps:

[0066] S101: Break down the construction project into multiple phases based on the work breakdown structure and identify the risk factors for each phase.

[0067] The Work Breakdown Structure (WBS) is a scientific project management tool that, according to the project's inherent logic and implementation process, gradually breaks down large and complex construction projects from top to bottom into multiple, clearly defined, relatively independent, and manageable phases, such as preliminary planning, design, construction, and acceptance and delivery. After completing the project phase division, for each phase, various possible risk factors are thoroughly and carefully sorted out, drawing on past experience with similar projects, knowledge from industry experts, and project site surveys. For example, during the construction phase, it is necessary to consider construction safety risks (such as safety hazards associated with working at height), construction schedule risks (such as equipment failure leading to work stoppages), and material supply risks (such as raw material shortages), thereby laying the foundation for subsequent risk management.

[0068] S102: Construct a multi-level risk indicator system based on risk factors. The multi-level risk indicator system includes primary indicators and secondary indicators.

[0069] It is understandable that after identifying the rich risk factors at each stage, in order to achieve systematic management and analysis of risks, it is necessary to classify and integrate these risk factors and build a multi-level risk indicator system. Among them, the first-level indicators are a macro-summary classification of risks, usually covering key areas such as safety risk, cost risk, schedule risk, and quality risk; the second-level indicators are the refinement and clarification of specific risk factors within the framework of the first-level indicators. For example, under the first-level indicator of safety risk, the second-level indicators can include insufficient safety training for construction personnel and the lack of safety protection equipment. By constructing this multi-level system consisting of first-level and second-level indicators, the overall picture of construction project risks can be presented more clearly and comprehensively, facilitating subsequent risk assessment and management.

[0070] S103: Based on the preset scaling rules, the relative importance of the indicators at the same level in the multi-level risk indicator system is quantified, a judgment matrix is ​​constructed, and the weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization.

[0071] For example, a scaling method is used to quantitatively score the relative importance of indicators at the same level in a multi-level risk indicator system and construct a judgment matrix.

[0072] Specifically, the secondary indicator evaluation results can be obtained by multiplying the weight vector of each indicator with the fuzzy relationship matrix. Then, the evaluation results of the secondary indicators are used as a new fuzzy matrix and combined with the weights of the primary indicators in the multi-level risk indicator system to calculate the final risk level.

[0073] For example, the preset scaling rules generally adopt the 1-9 scaling method, which provides a standard scale for the quantitative evaluation of the relative importance of different indicators. 1 represents that the two indicators are equally important. The larger the value, the greater the difference in importance between the indicators. 9 represents extreme importance, and 2, 4, 6, and 8 are the intermediate values ​​of adjacent importance. Using this scaling method, the relative importance of indicators at the same level in the multi-level risk indicator system, such as secondary indicators, is scored, and then a judgment matrix is ​​constructed. After the matrix is ​​constructed, the product of the elements in each row is calculated, the product result is raised to the nth power (n is the matrix order), and the resulting vector is normalized to obtain the weight of each indicator at this level. These weight values ​​accurately reflect the difference in importance of each indicator and provide a quantitative basis for subsequent risk assessment.

[0074] S104: Define the risk level domain, conduct risk level assessment for each secondary indicator in the multi-level risk indicator system based on historical project data and industry standards, calculate the support rate of each risk level, and form a fuzzy relationship matrix.

[0075] It can be understood that multiple risk levels of different degrees can be defined to form a risk level domain.

[0076] Specifically, we first clarify the domain of risk levels, that is, set multiple risk levels of varying degrees, generally including five levels: very low, low, medium, high, and very high, as a standard framework for measuring the degree of risk. Then, we fully explore and utilize the risk information in historical project data, and in combination with industry-wide standards, specifications, and guidelines, conduct in-depth analysis and evaluation of each secondary indicator in the multi-level risk indicator system to determine the likelihood of it belonging to each risk level. By statistically analyzing the support rate of each secondary indicator at different risk levels (that is, the proportion of the frequency of being assessed as a certain risk level to the total number of assessments), these support rates are arranged in order, and finally a fuzzy relationship matrix is ​​formed. This matrix intuitively shows the fuzzy correspondence between each secondary indicator and different risk levels, providing key data support for comprehensive risk assessment.

[0077] Optionally, in some implementations, the fuzzy relationship matrix is ​​subjected to a consistency check. If the consistency requirement is not met, the risk level of the secondary indicators in the multi-level risk indicator system is reassessed based on historical project data and industry standards.

[0078] Understandably, the fuzzy relationship matrix is ​​derived from the statistical risk level assessment of secondary indicators, and its consistency reflects the coordination and rationality of the risk level assessment results. An inconsistent matrix implies logical contradictions in the experts' (or assessment data) judgments on each risk level, potentially rendering the final risk level assessment unreliable. For example, when assessing the risk of "construction delay," if the majority of the data favors "high risk," but some data categorizes it as "low risk," the matrix will become inconsistent.

[0079] Therefore, after the fuzzy relationship matrix is ​​formed, it is tested through specific mathematical methods (such as calculating the consistency index, random consistency index, and calculating the consistency ratio). If the consistency ratio exceeds the preset threshold, the matrix is ​​judged to not meet the consistency requirements. At this time, it is necessary to re-evaluate the risk level of the secondary indicators in the multi-level risk indicator system based on historical project data and industry standards, re-calculate the support rate of each risk level, and form a new fuzzy relationship matrix until the consistency requirements are met, thereby providing a reliable data basis for the subsequent accurate calculation of risk levels.

[0080] S105: Based on the weights of each indicator and the fuzzy relationship matrix, a comprehensive evaluation calculation is performed to determine the risk level of the construction project as a whole or at each stage.

[0081] As you can understand, the previously determined weight vectors for each indicator are combined with the constructed fuzzy relationship matrix. Through matrix operations, the evaluation results for the secondary indicators are first derived. These results reflect the comprehensive performance of each secondary indicator at different risk levels. Next, the evaluation results of the secondary indicators are used as a new fuzzy matrix and further calculated based on the weights of the primary indicators in the multi-level risk indicator system. This series of comprehensive evaluation and calculations ultimately allows for a precise determination of the risk level for the construction project as a whole or for each specific stage, providing project managers with a clear and unambiguous basis for developing scientific and rational risk response strategies.

[0082] Optionally, in some embodiments, the method further comprises:

[0083] S106: According to the determined risk level and the preset strategy library, the corresponding risk response strategy is matched and generated.

[0084] It can be understood that according to the level of risk, the strategies in the strategy library are divided into emergency response strategies, key prevention and control strategies and routine monitoring strategies; if the determined risk level is high risk or very high risk, the emergency response strategy will be matched first from the strategy library; if it is medium risk, the key prevention and control strategy will be matched; if it is low risk or very low risk, the routine monitoring strategy will be matched.

[0085] Of course, the feasibility of the generated risk response strategies can be evaluated based on the actual resource situation, cost budget and time constraints of the construction project.

[0086] Understandably, resource availability (such as manpower, equipment, and material reserves), cost budgets (funding allocation), and time constraints (project duration and key milestones) constitute realistic constraints on project execution. A feasibility assessment compares the generated risk response strategies with these constraints, analyzing whether the strategies meet the project's actual capacity in terms of resource consumption, cost expenditure, and time commitment. For example, if the strategy for addressing the risk of "delay" is to double the construction workforce, but the project's actual manpower reserves are insufficient, this strategy is not feasible.

[0087] If the risk response strategy is not feasible, an alternative strategy will be selected from the strategy library and regenerated according to the preset priority rules.

[0088] As you can understand, the strategy library stores a variety of response strategies for different risk scenarios. Preset priority rules prioritize each strategy based on factors such as effectiveness, resource requirements, and cost-effectiveness. When the currently generated strategy is not feasible, the system prioritizes alternative strategies that both effectively address the risk and meet the project's actual constraints based on the priority rules. For example, when addressing the risk of "material price fluctuations," if the preferred strategy of "large-scale pre-stocking" is unfeasible due to insufficient funds, the next highest priority strategy of "signing price lock-in agreements with suppliers" will be selected.

[0089] This application proposes an AI-based construction project risk prediction and decision-making optimization method. By decomposing a construction project into multiple stages, identifying the risk factors in each stage, constructing a multi-level risk indicator system, determining the weight of each indicator, forming a fuzzy relationship matrix, and then determining the risk level, and generating corresponding risk response strategies, it can achieve effective prediction of construction project risks and decision-making optimization.

[0090] This application proposes an AI-based construction project risk prediction and decision optimization system, which is characterized by being configured to:

[0091] Break down construction projects into phases based on the work breakdown structure and identify risk factors for each phase;

[0092] Construct a multi-level risk indicator system based on risk factors, which includes primary indicators and secondary indicators;

[0093] Based on the preset scaling rules, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix. The weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization.

[0094] Define the risk level domain, evaluate the risk level of each secondary indicator in the multi-level risk indicator system based on historical project data and industry standards, calculate the support rate of each risk level, and form a fuzzy relationship matrix;

[0095] Based on the weights of each indicator and the fuzzy relationship matrix, a comprehensive evaluation calculation is performed to determine the risk level of the construction project as a whole or at each stage.

[0096] Based on the same inventive concept, this application proposes an AI-based construction project risk prediction and decision-making optimization system, which is configured to:

[0097] Based on the preset scaling rules, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix. The weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization, including:

[0098] The scaling method is used to quantitatively score the relative importance of indicators at the same level in the multi-level risk indicator system and construct a judgment matrix.

[0099] In some embodiments, the system is configured to:

[0100] Based on the preset scaling rules, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix. The weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization, including:

[0101] By multiplying the weight vector of each indicator with the fuzzy relationship matrix, the secondary indicator evaluation results are obtained;

[0102] The evaluation results of the secondary indicators are used as a new fuzzy matrix, and the final risk level is calculated in combination with the weights of the primary indicators in the multi-level risk indicator system.

[0103] In some embodiments, the system is configured to:

[0104] Define the risk level domain, evaluate the risk level of each secondary indicator in the multi-level risk indicator system based on historical project data and industry standards, calculate the support rate of each risk level, and form a fuzzy relationship matrix, including:

[0105] Define multiple risk levels of different degrees to form the risk level domain.

[0106] In some embodiments, the system is configured to:

[0107] Define the risk level domain, evaluate the risk level of each secondary indicator in the multi-level risk indicator system based on historical project data and industry standards, calculate the support rate of each risk level, and form a fuzzy relationship matrix, including:

[0108] The fuzzy relationship matrix is ​​checked for consistency. If the consistency requirement is not met, the risk level of the secondary indicators in the multi-level risk indicator system is re-evaluated based on historical project data and industry standards. In conjunction with the second aspect, in some embodiments, the system is configured as follows:

[0109] According to the determined risk level and the preset strategy library, the corresponding risk response strategy is matched and generated.

[0110] In some embodiments, the system is configured to:

[0111] Based on the determined risk level and the preset strategy library, the corresponding risk response strategies are matched and generated, including:

[0112] According to the risk level, the strategies in the strategy library are divided into emergency response strategies, key prevention and control strategies, and routine monitoring strategies;

[0113] If the determined risk level is high risk or very high risk, the emergency response strategy will be matched first from the strategy library; if it is medium risk, the key prevention and control strategy will be matched; if it is low risk or very low risk, the conventional monitoring strategy will be matched.

[0114] Based on the specific secondary indicators that lead to risk levels in the multi-level risk indicator system, targeted strategies are further screened among the matched strategy types.

[0115] In some embodiments, the system is configured to:

[0116] Based on the determined risk level and the preset strategy library, the corresponding risk response strategies are matched and generated, including:

[0117] Conduct feasibility assessment on the generated risk response strategies based on the actual resource situation, cost budget and time constraints of the construction project;

[0118] If the risk response strategy is not feasible, an alternative strategy will be selected from the strategy library and regenerated according to the preset priority rules.

[0119] This application proposes an AI-based construction project risk prediction and decision-making optimization system, which breaks down construction projects into multiple stages, identifies risk factors at each stage, constructs a multi-level risk indicator system, determines the weight of each indicator, forms a fuzzy relationship matrix, and then determines the risk level and generates corresponding risk response strategies, thereby achieving effective prediction of construction project risks and decision-making optimization.

[0120] Based on the same inventive concept, an embodiment of the present application further provides an electronic device, the electronic device comprising:

[0121] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the automatic overheating protection method for a universal testing machine based on an embodiment of the present application.

[0122] In addition, to achieve the above-mentioned purpose, an embodiment of the present application further proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the automatic overheating protection method based on a universal testing machine according to an embodiment of the present application.

[0123] The following is a detailed introduction to the various components of electronic equipment:

[0124] The processor is the control center of an electronic device and can be a single processor or a collective term for multiple processing elements. For example, the processor is one or more central processing units (CPUs), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement an embodiment of the present invention, such as one or more microprocessors (digital signal processors, DSPs) or one or more field programmable gate arrays (FPGAs).

[0125] Optionally, the processor can perform various functions of the electronic device by running or executing a software program stored in the memory, and calling data stored in the memory.

[0126] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0127] Alternatively, the memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but is not limited thereto. The memory may be integrated with the processor or may exist independently and be coupled to the processor via an interface circuit of the electronic device, and this is not specifically limited in the embodiments of the present invention.

[0128] A transceiver is used to communicate with network devices or terminal devices.

[0129] Optionally, the transceiver may include a receiver and a transmitter, wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0130] Optionally, the transceiver may be integrated with the processor, or may exist independently and be coupled to the processor via an interface circuit of the router, which is not specifically limited in the embodiment of the present invention.

[0131] In addition, the technical effects of the electronic device can refer to the technical effects of the data transmission method in the above method embodiment, and will not be repeated here.

[0132] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0133] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DRRAM).

[0134] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available media can be magnetic media (such as floppy disks, hard disks, tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0135] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0136] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0137] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0138] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

Claims

1. An AI-based construction project risk prediction and decision optimization method, characterized by: The method comprises: Break down construction projects into phases based on the work breakdown structure and identify risk factors for each phase; Constructing a multi-level risk indicator system based on the risk factors, wherein the multi-level risk indicator system includes primary indicators and secondary indicators; Based on a preset scaling rule, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix, and the weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization processing; Define the risk level domain, evaluate the risk level of each secondary indicator in the multi-level risk indicator system based on historical project data and industry standards, calculate the support rate of each risk level, and form a fuzzy relationship matrix; Based on the weights of the various indicators and the fuzzy relationship matrix, a comprehensive evaluation calculation is performed to determine the risk level of the construction project as a whole or at each stage.

2. The AI-based construction project risk prediction and decision optimization method according to claim 1 is characterized in that: Based on the preset scaling rules, the relative importance of the indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix. The weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization, including: The scaling method is used to quantitatively score the relative importance of indicators at the same level in the multi-level risk indicator system to construct the judgment matrix.

3. The AI-based construction project risk prediction and decision optimization method according to claim 2 is characterized in that: Based on the preset scaling rules, the relative importance of the indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix. The weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization, including: The secondary index evaluation result is obtained by multiplying the weight vector of each index by the fuzzy relationship matrix; The evaluation results of the secondary indicators are used as a new fuzzy matrix, and the final risk level is calculated in combination with the weights of the primary indicators in the multi-level risk indicator system.

4. The AI-based construction project risk prediction and decision optimization method according to claim 1 is characterized in that: Define the risk level domain, and based on historical project data and industry standards, perform a risk level assessment on each secondary indicator in the multi-level risk indicator system. Calculate the support rate of each risk level to form a fuzzy relationship matrix, including: A plurality of risk levels of different degrees are defined to form the risk level domain.

5. The AI-based construction project risk prediction and decision optimization method according to claim 4 is characterized in that: Define the risk level domain, and based on historical project data and industry standards, perform a risk level assessment on each secondary indicator in the multi-level risk indicator system. Calculate the support rate of each risk level to form a fuzzy relationship matrix, including: The fuzzy relationship matrix is ​​subjected to a consistency check. If the consistency requirement is not met, the risk level of the secondary indicators in the multi-level risk indicator system is reassessed based on historical project data and industry standards.

6. The AI-based construction project risk prediction and decision optimization method according to claim 1 is characterized in that: The method further comprises: According to the determined risk level and the preset strategy library, the corresponding risk response strategy is matched and generated.

7. The AI-based construction project risk prediction and decision optimization method according to claim 6 is characterized in that: According to the determined risk level and the preset strategy library, the corresponding risk response strategy is matched and generated, including: According to the risk level, the strategies in the strategy library are divided into emergency response strategies, key prevention and control strategies and routine monitoring strategies; If the determined risk level is high risk or very high risk, the emergency response strategy is matched first from the strategy library; if it is medium risk, the key prevention and control strategy is matched; if it is low risk or very low risk, the conventional monitoring strategy is matched. Based on the specific secondary indicators that lead to the risk level in the multi-level risk indicator system, targeted strategies are further screened from the matched strategy types.

8. The AI-based construction project risk prediction and decision optimization method according to claim 6 is characterized in that: According to the determined risk level and the preset strategy library, the corresponding risk response strategy is matched and generated, including: Conduct feasibility assessment on the generated risk response strategies based on the actual resource situation, cost budget and time constraints of the construction project; If the risk response strategy is not feasible, an alternative strategy is selected from the strategy library according to the preset priority rules and regenerated.

9. An AI-based construction project risk prediction and decision optimization system, characterized by: The system is configured to: Break down construction projects into phases based on the work breakdown structure and identify risk factors for each phase; Constructing a multi-level risk indicator system based on the risk factors, wherein the multi-level risk indicator system includes primary indicators and secondary indicators; Based on a preset scaling rule, the relative importance of indicators at the same level in the multi-level risk indicator system is quantified to construct a judgment matrix, and the weight of each indicator is determined by calculating the product of the elements in each row of the judgment matrix and performing normalization processing; Define the risk level domain, evaluate the risk level of each secondary indicator in the multi-level risk indicator system based on historical project data and industry standards, calculate the support rate of each risk level, and form a fuzzy relationship matrix; Based on the weights of the various indicators and the fuzzy relationship matrix, a comprehensive evaluation calculation is performed to determine the risk level of the construction project as a whole or at each stage.

10. An electronic device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method proposed in any one of claims 1 to 8.

Images