Urban rail transit construction safety coupling risk factor identification method and system

Abstract

The invention provides a safety coupling risk factor identification method and system for urban rail transit construction, and belongs to the technical field of building construction safety risk identification, and the method comprises the steps: building a risk factor set containing five types of personnel, equipment, materials, management and environment based on building construction historical accident data; performing quantification processing on accident causes and consequence loss, and establishing a risk factor-accident consequence data matrix; introducing an improved Apriori association rule mining algorithm of an accident consequence weight, and identifying a coupling relationship among risk factors through a weighted support degree, a weighted confidence degree and a weighted lifting degree; and mapping the association rules obtained by mining into a complex network, and measuring the importance of the risk factors in the network by using the node degree and the proximity centrality to realize the identification and sorting of the construction safety coupling risk factors. According to the method, the occurrence frequency of risk factors and the severity of accident consequences are considered at the same time, key coupling risks and hub risk factors are identified, and a scientific basis is provided for construction safety risk management and control and decision making.

Description

Technical Field

[0001] This invention relates to the field of building construction safety risk identification technology, specifically to a method and system for identifying coupled risk factors in urban rail transit construction safety. Background Technology

[0002] Construction safety in urban rail transit remains a critical challenge for the industry globally. Despite significant progress in safety management systems, accidents continue to occur, often not due to a single cause but rather stemming from complex couplings and interactions among multiple risk factors. Traditional risk analysis relies primarily on statistical methods and expert judgment to identify individual factors, such as human error, equipment failure, or environmental conditions. However, these methods often fail to reveal the potential correlations between these factors and the pathways of risk propagation.

[0003] To address this limitation, data-driven technologies have gained increasing attention. Association rule mining, especially the Apriori algorithm, has been effectively applied to extract frequent patterns from accident data. Meanwhile, complex network theory has become a powerful tool for characterizing system interactions and identifying critical nodes in various safety fields. In recent years, some studies have begun to attempt to integrate these two approaches. For example, some scholars have used association rule mining to generate rules and construct networks to visualize the relationships between risk factors in occupational safety and tunnel construction safety; other studies have used weighted network analysis to prioritize risks in construction projects.

[0004] Despite the progress made, significant research gaps remain. First, most current applications of association rule mining in the safety field still rely on traditional frequency-based indicators (support, confidence), neglecting the crucial dimension of accident severity. Second, while network models have been constructed, the methodology for systematically mapping association rules into weighted directed complex networks for analyzing the coupling relationships of construction risk factors remains incomplete. Few studies combine association rule mining with accident severity weights with analysis methods based on network topology centrality to quantitatively identify and rank single and coupled risk factors. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for identifying coupled risk factors in urban rail transit construction safety, so as to solve at least one of the technical problems existing in the background art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for identifying coupled risk factors in urban rail transit construction safety, including:

[0008] Construct a risk factor set and an accident dataset. Specifically, based on relevant construction safety regulations, standards, and accident reports, establish a risk factor set covering five categories of risk factors: personnel, equipment, materials, management, and environment. Collect construction accident reports, extract accident cause and consequence information, and form an accident sample dataset including risk factors and accident consequences. Establish a risk factor matrix based on the accident set. Encode the risk factors using 0-1 encoding to form a risk factor-accident sample matrix, and quantify and weight the severity of accident consequences based on casualties and economic losses.

[0009] Based on the Apriori algorithm, accident consequence weights are introduced to calculate weighted support, weighted confidence and weighted lift, and to explore the coupling relationship between risk factors.

[0010] Association rules are mapped to nodes and edges in a complex network, where nodes represent risk factors or combinations thereof, and edge weights represent weighted confidence levels. Based on node degree and proximity centrality, hub nodes and key coupled risk factors in the complex network are identified.

[0011] As a further limitation of the first aspect of the present invention, the Apriori algorithm, considering the severity of accident consequences, is used to explore the correlation between different risk factors and the coupling of risk factors; the weighted support and weighted confidence are defined as follows:

[0012] ;

[0013] ;

[0014] ;

[0015] in, Risk factors The weighted support; For the first The weight values ​​of each risk factor, For the first The number of injuries reported in accidents involving each risk factor. For the first The number of deaths reported in accidents involving each risk factor. For the first Economic losses reported in accidents involving individual risk factors. These are the weight values ​​proposed by experts; For risk factor matrix, Indicates the first One accident report.

[0016] As a further limitation of the first aspect of the present invention, a complex network is constructed based on the association rule mining results. Specifically, each association rule is regarded as an edge in the complex network, the preceding and following terms of the association rule are regarded as the starting and target nodes of the network, respectively, and the weight value of this edge is the weighted confidence of the association rule. In this way, a complex network with risk factors as nodes is constructed.

[0017] As a further limitation of the first aspect of this invention, the degree of a node is defined as the number of edges directly connected to that node. The higher the degree, the greater the importance of the node in the network, and its calculation method is as follows:

[0018] ;

[0019] ;

[0020] in, It is a node The degree, It is the set of all nodes in the network. It is an element in the adjacency matrix.

[0021] As a further definition of the first aspect of this invention, proximity centrality quantifies the overall reachability of a node in a network by measuring the reciprocal of the average shortest path length from a given node to all other nodes. Nodes with high proximity centrality are relatively close to other nodes in the network and can achieve efficient interaction with fewer intermediate steps. In complex networks, proximity centrality reflects the potential efficiency of nodes in information diffusion, influence propagation, or risk transmission. Nodes with high proximity centrality can reach other nodes faster, thus playing a key role in the global connectivity and functional integration of the network.

[0022]

[0023] It is a node The proximity centrality measure. From node To the node The shortest path length.

[0024] As a further limitation of the first aspect of the present invention

[0025] ;

[0026] Risk factors The weighted confidence level represents the weighted confidence level of risk factors. Risk factors To determine the degree of confidence, association rules can be generated by comparing the confidence level with a defined threshold size;

[0027] ;

[0028] Risk factors The weighted elevation; its significance lies in measuring risk factors. and risk factors Independence; if the degree of improvement If the value is greater than 1, then the strong association rule is usually considered correct.

[0029] Secondly, the present invention provides a system for identifying coupled risk factors in urban rail transit construction safety, comprising:

[0030] The module is used to construct risk factor sets and accident datasets. Specifically, based on relevant construction safety regulations, standards, and accident reports, a risk factor set covering five categories of risk factors—personnel, equipment, materials, management, and environment—is established. Construction accident reports are collected, and information on accident causes and consequences is extracted to form an accident sample dataset including risk factors and accident consequences. A risk factor matrix is ​​built based on the accident set. Risk factors are encoded using 0-1 encoding to form a risk factor-accident sample matrix, and the severity of accident consequences is quantitatively weighted based on casualties and economic losses.

[0031] The calculation module is used to introduce accident consequence weights on the basis of the Apriori algorithm, calculate weighted support, weighted confidence and weighted lift, and explore the coupling relationship between risk factors;

[0032] The determination module maps association rules to nodes and edges in a complex network, where nodes represent risk factors or combinations thereof, and edge weights represent weighted confidence levels. Based on node degree and proximity centrality, it identifies hub nodes and key coupled risk factors in the complex network.

[0033] Thirdly, the present invention provides a non-transitory computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the method for identifying coupled risk factors for urban rail transit construction safety as described in the first aspect.

[0034] Fourthly, the present invention provides a computer device including a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the method for identifying coupled risk factors for urban rail transit construction safety as described in the first aspect.

[0035] Fifthly, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing the method for identifying coupled risk factors in urban rail transit construction safety as described in the first aspect.

[0036] The beneficial effects of this invention are that it can simultaneously consider the frequency of occurrence of risk factors and the severity of accident consequences, identify key coupled risks and pivotal risk factors, and provide a scientific basis for construction safety risk management and decision-making.

[0037] The advantages of additional aspects of the invention will be set forth more clearly in the following description or will be learned by practice of the invention. Attached Figure Description

[0038] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a schematic diagram illustrating the process of association rule mining and mapping to complex network models as described in an embodiment of the present invention.

[0040] Figure 2 This is a schematic diagram of the complex network of risk factors for collapse accidents as described in an embodiment of the present invention.

[0041] Figure 3 This is a schematic diagram illustrating the distribution of the degree centrality of network nodes according to an embodiment of the present invention.

[0042] Figure 4 This is a schematic diagram illustrating the distribution of network nodes near centrality according to an embodiment of the present invention. Detailed Implementation

[0043] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0044] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0045] It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as here.

[0046] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, and / or groups thereof.

[0047] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0048] To facilitate understanding of the present invention, the present invention will be further explained and described below with reference to the accompanying drawings and specific embodiments. However, the specific embodiments do not constitute a limitation on the embodiments of the present invention.

[0049] Those skilled in the art should understand that the accompanying drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily essential for implementing the present invention.

[0050] This invention discloses a data-driven method for identifying coupled risk factors in construction safety. Based on historical construction accident data, this method constructs a set of risk factors covering five categories: personnel, equipment, materials, management, and environment. It quantifies the causes and consequences of accidents, establishing a risk factor-accident consequence data matrix. Building upon this, an improved Apriori association rule mining algorithm incorporating accident consequence weights is proposed. Weighted support, weighted confidence, and weighted lift are used to identify the coupling relationships between risk factors. Furthermore, the mined association rules are mapped to a complex network, utilizing node degree and proximity centrality to measure the importance of risk factors within the network, thereby identifying and ranking coupled risk factors in construction safety. This invention can simultaneously consider the frequency of risk factor occurrence and the severity of accident consequences, identifying key coupled risks and pivotal risk factors, providing a scientific basis for construction safety risk management and decision-making.

[0051] Example 1

[0052] In this embodiment 1, a system for identifying coupled risk factors in urban rail transit construction safety is first provided, including:

[0053] The module is used to construct risk factor sets and accident datasets. Specifically, based on relevant construction safety regulations, standards, and accident reports, a risk factor set covering five categories of risk factors—personnel, equipment, materials, management, and environment—is established. Construction accident reports are collected, and information on accident causes and consequences is extracted to form an accident sample dataset including risk factors and accident consequences. A risk factor matrix is ​​built based on the accident set. Risk factors are encoded using 0-1 encoding to form a risk factor-accident sample matrix, and the severity of accident consequences is quantitatively weighted based on casualties and economic losses.

[0054] The calculation module is used to introduce accident consequence weights on the basis of the Apriori algorithm, calculate weighted support, weighted confidence and weighted lift, and explore the coupling relationship between risk factors;

[0055] The determination module maps association rules to nodes and edges in a complex network, where nodes represent risk factors or combinations thereof, and edge weights represent weighted confidence levels. Based on node degree and proximity centrality, it identifies hub nodes and key coupled risk factors in the complex network.

[0056] In this embodiment, the above-described system is used to implement a method for identifying coupled risk factors in urban rail transit construction safety, including:

[0057] Step 1: Construct a risk factor set. Based on relevant construction safety regulations, standards, and accident reports, establish a risk factor set covering five categories of risk factors: personnel, equipment, materials, management, and environment.

[0058] Step 2: Construct an accident dataset. Collect construction accident reports, extract accident cause and consequence information, and form an accident sample dataset including risk factors and accident consequences. Establish a risk factor matrix based on the accident dataset. Encode risk factors using 0-1 encoding to form a risk factor-accident sample matrix, and quantify and weight the severity of accident consequences based on factors such as casualties and economic losses.

[0059] Step 3: Improve Apriori association rule mining. Based on the traditional Apriori algorithm, introduce accident consequence weights, calculate weighted support, weighted confidence, and weighted lift, and explore the coupling relationships between risk factors;

[0060] Step 4: Construct a complex network model. Map association rules to nodes and edges in a complex network, where nodes represent risk factors or combinations thereof, and edge weights represent weighted confidence scores.

[0061] Step 5: Identify key coupling risk factors. Based on node degree and proximity centrality, identify hub nodes and key coupling risk factors in complex networks:

[0062] Specifically, step 1 involves constructing a set of risk factors, including personnel, equipment, materials, environment, and management, based on the characteristics of urban rail transit construction safety, as shown in Table 1.

[0063] Table 1. Set of Safety Risk Factors for Urban Rail Transit Construction

[0064]

[0065] Step 2 specifically involves marking risk factors as 0 or 1 based on the actual records in the accident report (as shown in Table 2), and recording the severity of the consequences of each accident, specifically the number of injuries, fatalities, and economic loss.

[0066] Table 2. 0-1 Matrix of Risk Factors for Collapse Accidents

[0067]

[0068] Step 3 specifically involves proposing an Apriori algorithm that considers the severity of accident consequences to uncover the correlations and coupling of different risk factors. Weighted support and weighted confidence are defined as follows:

[0069]

[0070]

[0071]

[0072] Risk factors The weighted support; For the first The weight values ​​of each risk factor, For the first The number of injuries reported in accidents involving each risk factor. For the first The number of deaths reported in accidents involving each risk factor. For the first Economic losses reported in accidents involving individual risk factors. These are the weight values ​​proposed by experts; For risk factor matrix, Indicates the first One accident report.

[0073]

[0074] Risk factors The weighted confidence level represents the weighted confidence level of risk factors. Risk factors To determine the degree of confidence, association rules can be generated by comparing the confidence level with a defined threshold size.

[0075]

[0076] Risk factors The weighted elevation. Its significance lies in measuring risk factors. and risk factors Independence. If the degree of elevation If the value is greater than 1, the strong association rule is generally considered correct. For example, lift. Indicates risk factors The occurrence of risk factors can drive risk factors. The occurrence of:

[0077] Step 4 specifically involves constructing a complex network based on the association rule mining results. Specifically, each association rule is considered an edge in the complex network, with the preceding and following terms of the association rule serving as the starting and target nodes of the network, respectively. The weight of this edge is the weighted confidence score of the association rule, and so on, constructing a complex network with risk factors as nodes.

[0078] Step 5 specifically involves identifying key nodes in a complex network. Specifically:

[0079] The degree of a node is defined as the number of edges directly connected to that node. The higher the degree, the more important the node is in the network. The degree is calculated as follows:

[0080]

[0081]

[0082] It is a node The degree, It is the set of all nodes in the network. It is an element in the adjacency matrix.

[0083] Proximity centrality quantifies a node's overall reachability in a network by measuring the inverse of the average shortest path length from a given node to all other nodes. Nodes with high proximity centrality are relatively close to other nodes in the network, enabling efficient interaction with fewer intermediate steps. In complex networks, proximity centrality reflects a node's potential efficiency in information dissemination, influence propagation, or risk transmission. Nodes with high proximity centrality can reach other nodes faster, thus playing a crucial role in the network's global connectivity and functional integration.

[0084]

[0085] It is a node The proximity centrality measure. From node To the node The shortest path length. The weights assigned to edges in a connected network are derived from the strength of the association rules between different nodes; that is, higher weights indicate stronger associations. Therefore, when calculating node proximity centrality, it is necessary to use... The reciprocal of.

[0086] In this embodiment, step 3 utilizes an improved Apriori algorithm to uncover the correlations between risk factors, with some results shown in Table 3. Taking {NCC,ISA→X} as an example, insufficient safety awareness and illegal construction practices are significantly correlated with the occurrence of accidents.

[0087] Table 3. Mining results of the improved Apriori algorithm (partial)

[0088]

[0089] In this embodiment, a complex network is constructed based on the association rule results, such as... Figure 2 As shown, this embodiment sets up single risk factor nodes, dual risk factor nodes, and triple risk factor nodes. The dual risk factor nodes and triple risk factor nodes represent the coupling situations between different risk factors, thereby analyzing the occurrence of coupled risks.

[0090] In this embodiment, the degree centrality and proximity centrality of nodes in the network are calculated, and the importance of the nodes is evaluated. The distributions of node degree centrality and proximity centrality are as follows: Figure 3 , Figure 4 As shown.

[0091] Single-risk-factor node: LSM has the highest degree, highlighting its core role in the network. Numerous incident reports indicate that management deficiencies are one of the main factors contributing to accidents; NCC is a direct cause of many collapses because it directly damages the structure's load-bearing system and foundation, reduces construction quality, and thus weakens the structure's strength and stability; ISA primarily reflects a lack of risk awareness among construction personnel and insufficient attention to safety regulations and operating procedures.

[0092] The combination of two risk factors—LSM and NCC—significantly increases the risk of collapse accidents. LSM leads to negligence during construction and ineffective implementation of safety measures, while NCC directly undermines design and quality standards, weakening structural integrity. {LSM, AERP} ranks second among the two risk factors; LSM hinders timely identification and reduction of safety hazards, while AERP results in ineffective emergency response after an accident. Their combined effect makes the entire collapse process uncontrollable, significantly increasing the likelihood and severity of accidents. ISA leads workers to disregard safety regulations, while DST indicates a failure to effectively mitigate common risks in construction safety. The combination of these factors may lead workers to risk working in hazardous environments, resulting in accidents.

[0093] Three risk factor nodes: {ISA, IOS, LSM} and {ISA, NCC, LSM}: When workers lack safety awareness and the necessary skills to handle complex operating procedures, coupled with ineffective management, non-compliant construction practices may occur, ultimately leading to accidents; {IRI, AERP, NCC}: When workers engage in non-compliant operations and fail to accurately identify risks, and there is a lack of effective emergency plans after an accident, the lack of necessary rescue measures at the accident site exacerbates the severity of the situation, leading to more serious consequences.

[0094] Example 3

[0095] This embodiment 3 provides a non-transitory computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, they implement the method for identifying coupled risk factors in urban rail transit construction safety as described above. The method includes:

[0096] Construct a risk factor set and an accident dataset. Specifically, based on relevant construction safety regulations, standards, and accident reports, establish a risk factor set covering five categories of risk factors: personnel, equipment, materials, management, and environment. Collect construction accident reports, extract accident cause and consequence information, and form an accident sample dataset including risk factors and accident consequences. Establish a risk factor matrix based on the accident set. Encode the risk factors using 0-1 encoding to form a risk factor-accident sample matrix, and quantify and weight the severity of accident consequences based on casualties and economic losses.

[0097] Based on the Apriori algorithm, accident consequence weights are introduced to calculate weighted support, weighted confidence and weighted lift, and to explore the coupling relationship between risk factors.

[0098] Association rules are mapped to nodes and edges in a complex network, where nodes represent risk factors or combinations thereof, and edge weights represent weighted confidence levels. Based on node degree and proximity centrality, hub nodes and key coupled risk factors in the complex network are identified.

[0099] Example 4

[0100] This embodiment 4 provides a computer device, including a memory and a processor, wherein the processor and the memory communicate with each other, and the memory stores program instructions that can be executed by the processor. The processor calls the program instructions to execute the method for identifying coupled risk factors for urban rail transit construction safety as described above, the method including:

[0101] Construct a risk factor set and an accident dataset. Specifically, based on relevant construction safety regulations, standards, and accident reports, establish a risk factor set covering five categories of risk factors: personnel, equipment, materials, management, and environment. Collect construction accident reports, extract accident cause and consequence information, and form an accident sample dataset including risk factors and accident consequences. Establish a risk factor matrix based on the accident set. Encode the risk factors using 0-1 encoding to form a risk factor-accident sample matrix, and quantify and weight the severity of accident consequences based on casualties and economic losses.

[0102] Based on the Apriori algorithm, accident consequence weights are introduced to calculate weighted support, weighted confidence and weighted lift, and to explore the coupling relationship between risk factors.

[0103] Association rules are mapped to nodes and edges in a complex network, where nodes represent risk factors or combinations thereof, and edge weights represent weighted confidence levels. Based on node degree and proximity centrality, hub nodes and key coupled risk factors in the complex network are identified.

[0104] Example 5

[0105] This embodiment 5 provides an electronic device, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes instructions to implement the method for identifying safety coupling risk factors in urban rail transit construction as described above, the method including:

[0106] Construct a risk factor set and an accident dataset. Specifically, based on relevant construction safety regulations, standards, and accident reports, establish a risk factor set covering five categories of risk factors: personnel, equipment, materials, management, and environment. Collect construction accident reports, extract accident cause and consequence information, and form an accident sample dataset including risk factors and accident consequences. Establish a risk factor matrix based on the accident set. Encode the risk factors using 0-1 encoding to form a risk factor-accident sample matrix, and quantify and weight the severity of accident consequences based on casualties and economic losses.

[0107] Based on the Apriori algorithm, accident consequence weights are introduced to calculate weighted support, weighted confidence and weighted lift, and to explore the coupling relationship between risk factors.

[0108] Association rules are mapped to nodes and edges in a complex network, where nodes represent risk factors or combinations thereof, and edge weights represent weighted confidence levels. Based on node degree and proximity centrality, hub nodes and key coupled risk factors in the complex network are identified.

[0109] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0110] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0111] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0112] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment, whereby a series of operational steps are performed to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0113] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that, based on the technical solutions disclosed in the present invention, various modifications or variations that can be made by those skilled in the art without creative effort should be included within the scope of protection of the present invention.

Claims

1. A method for identifying coupled risk factors in urban rail transit construction safety, characterized in that, include: Construct a risk factor set and an accident dataset. Specifically, based on relevant construction safety regulations, standards, and accident reports, establish a risk factor set covering five categories of risk factors: personnel, equipment, materials, management, and environment. Collect construction accident reports, extract accident cause and consequence information, and form an accident sample dataset including risk factors and accident consequences. Establish a risk factor matrix based on the accident set. Encode the risk factors using 0-1 encoding to form a risk factor-accident sample matrix, and quantify and weight the severity of accident consequences based on casualties and economic losses. Based on the Apriori algorithm, accident consequence weights are introduced to calculate weighted support, weighted confidence and weighted lift, and to explore the coupling relationship between risk factors. Association rules are mapped to nodes and edges in a complex network, where nodes represent risk factors or combinations thereof, and edge weights represent weighted confidence levels. Based on node degree and proximity centrality, hub nodes and key coupled risk factors in the complex network are identified.

2. The method for identifying coupled risk factors in urban rail transit construction safety according to claim 1, characterized in that, The Apriori algorithm, which considers the severity of accident consequences, is used to uncover the correlations between different risk factors and the coupling of risk factors; the weighted support and weighted confidence are defined as follows: ； ； ； in, Risk factors The weighted support; For the first The weight values ​​of each risk factor, For the first The number of injuries reported in accidents involving each risk factor. For the first The number of deaths reported in accidents involving each risk factor. For the first Economic losses reported in accidents involving individual risk factors. These are the weight values ​​proposed by experts; For risk factor matrix, Indicates the first One accident report.

3. The method for identifying coupled risk factors in urban rail transit construction safety according to claim 1, characterized in that, A complex network is constructed based on the association rule mining results. Specifically, each association rule is regarded as an edge in the complex network, and the preceding and following terms of the association rule are regarded as the starting and target nodes of the network, respectively. The weight of this edge is the weighted confidence of the association rule. In this way, a complex network with risk factors as nodes is constructed.

4. The method for identifying coupled risk factors in urban rail transit construction safety according to claim 1, characterized in that, The degree of a node is defined as the number of edges directly connected to that node. The higher the degree, the more important the node is in the network. The degree is calculated as follows: ； ； in, It is a node The degree, It is the set of all nodes in the network. It is an element in the adjacency matrix.

5. The method for identifying coupled risk factors in urban rail transit construction safety according to claim 1, characterized in that, Proximity centrality quantifies the overall reachability of a node in a network by measuring the reciprocal of the average shortest path length from a given node to all other nodes. Nodes with high proximity centrality are relatively close to other nodes in a network, enabling them to interact efficiently with fewer intermediate steps. In complex networks, proximity centrality reflects the potential efficiency of nodes in information diffusion, influence propagation, or risk transmission. Nodes with high proximity centrality can reach other nodes faster, thus playing a key role in the global connectivity and functional integration of the network. It is a node The proximity centrality measure. From node To the node The shortest path length.

6. The method for identifying coupled risk factors in urban rail transit construction safety according to claim 2, characterized in that, ； Risk factors The weighted confidence level represents the weighted confidence level of risk factors. Risk factors To determine the degree of confidence, association rules can be generated by comparing the confidence level with a defined threshold size; ； Risk factors The weighted improvement degree; Its significance lies in measuring risk factors. and risk factors Independence; if the degree of improvement If the value is greater than 1, then the strong association rule is usually considered correct.

7. A system for identifying coupled risk factors in urban rail transit construction safety, characterized in that, include: The module is used to construct risk factor sets and accident datasets. Specifically, based on relevant construction safety regulations, standards, and accident reports, a risk factor set covering five categories of risk factors—personnel, equipment, materials, management, and environment—is established. Construction accident reports are collected, and information on accident causes and consequences is extracted to form an accident sample dataset including risk factors and accident consequences. A risk factor matrix is ​​built based on the accident set. Risk factors are encoded using 0-1 encoding to form a risk factor-accident sample matrix, and the severity of accident consequences is quantitatively weighted based on casualties and economic losses. The calculation module is used to introduce accident consequence weights on the basis of the Apriori algorithm, calculate weighted support, weighted confidence and weighted lift, and explore the coupling relationship between risk factors; The determination module maps association rules to nodes and edges in a complex network, where nodes represent risk factors or combinations thereof, and edge weights represent weighted confidence levels. Based on node degree and proximity centrality, it identifies hub nodes and key coupled risk factors in the complex network.

8. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, which, when executed by a processor, implement the method for identifying coupled risk factors for urban rail transit construction safety as described in any one of claims 1-6.

9. A computer device, characterized in that, The method includes a memory and a processor, the processor and the memory communicating with each other, the memory storing program instructions that can be executed by the processor, and the processor calling the program instructions to execute the method for identifying coupled risk factors for urban rail transit construction safety as described in any one of claims 1-6.

10. An electronic device, characterized in that, include: The device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions that implement the method for identifying coupled risk factors in urban rail transit construction safety as described in any one of claims 1-6.

Images