Road reconstruction and extension traffic safety risk factor intelligent identification method and system

Abstract

The invention provides a highway reconstruction and extension traffic safety risk factor intelligent identification method and system, and relates to the technical field of traffic engineering, and the method comprises the steps: obtaining a traffic accident data set during a highway reconstruction and extension project, the traffic accident data set comprising various types of risk factor data; performing data enhancement and balance on a small number of types of risk factor data in the traffic accident data set by using an SMOTE algorithm; determining the factor weight of each traffic safety risk factor through an FAHP algorithm; constructing a weighted association rule mining algorithm by introducing the factor weight; and analyzing the risk factor data in the enhanced and balanced traffic accident data set through a weighted association rule mining algorithm, and identifying traffic safety risk factors. According to the method, more critical cause factors of serious accident data and the interaction relation of the cause factors are considered, so that related research results are more effectively applied to reduce the severity of traffic accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic engineering, and in particular to a method and system for intelligently identifying traffic safety risk factors in highway reconstruction and expansion. Background Art

[0002] In recent years, with the increasing number of highway reconstruction and expansion projects, the traffic organization form of the reconstruction and expansion construction area often adopts the method of opening to traffic while construction, which makes the passing vehicles and construction personnel, construction machinery, etc. on the same plane, forming a complex and dangerous traffic environment. Compared with ordinary sections, the incidence and severity of traffic accidents in the reconstruction and expansion construction area have increased significantly. Therefore, analyzing the complex interaction relationship between traffic accident factors during the highway reconstruction and expansion project is the basis and prerequisite for formulating traffic safety improvement measures and ensuring construction and operation safety.

[0003] However, in traditional technical solutions, due to the deficiencies in the quality and quantity of traffic accident data during the highway reconstruction and expansion projects, the accident severity data showed an obvious imbalance, and the proportion of accidents with higher severity levels in the data was low, resulting in subsequent traffic accident factor analysis results often tending to record more minor accidents, thereby ignoring the more critical causal factors of serious accidents and their interactions, making it difficult to effectively apply relevant research results to reduce the severity of traffic accidents. Summary of the invention

[0004] In order to solve the problem that in traditional technical solutions, due to the insufficiency of quality and quantity of traffic accident data during highway reconstruction and expansion projects, the accident severity data presents an obvious imbalance, and the proportion of accidents with higher severity levels in the data is low, resulting in subsequent traffic accident factor analysis results often tending to record more minor accidents, thereby ignoring the more critical causal factors of serious accidents and their interactive relationships, making it difficult for relevant research results to be effectively applied to reduce the severity of traffic accidents, the present invention provides a method and system for intelligent identification of traffic safety risk factors in highway reconstruction and expansion.

[0005] The technical solution provided by the embodiment of the present invention is as follows:

[0006] First aspect:

[0007] An embodiment of the present invention provides a method for intelligently identifying traffic safety risk factors for highway reconstruction and expansion, comprising:

[0008] S1: Obtain a traffic accident dataset during the highway reconstruction and expansion project, wherein the traffic accident dataset includes multiple types of risk factor data;

[0009] S2: Use the SMOTE algorithm to perform data enhancement and balancing on the minority types of risk factor data in the traffic accident dataset;

[0010] S3: Determine the factor weights of each traffic safety risk factor through the FAHP algorithm;

[0011] S4: constructing a weighted association rule mining algorithm by introducing the factor weights;

[0012] S5: Through the weighted association rule mining algorithm, the risk factor data in the enhanced and balanced traffic accident data set is analyzed to identify traffic safety risk factors.

[0013] Second aspect:

[0014] An intelligent identification system for traffic safety risk factors in highway reconstruction and expansion provided by an embodiment of the present invention includes: a memory and one or more processors;

[0015] One or more application programs are stored in the memory, and the one or more application programs are suitable for being executed by the one or more processors to implement the above-mentioned method for intelligently identifying traffic safety risk factors in highway reconstruction and expansion.

[0016] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0017] In the present invention, by using the SMOTE algorithm, data enhancement and balance are performed on a few types of risk factor data in the traffic accident data set, thereby avoiding the phenomenon that the traffic accident data during the highway reconstruction and expansion project are insufficient in quality and quantity, making the accident severity data present an obvious balance, and increasing the proportion of accidents with higher severity levels in the data, thereby avoiding the subsequent traffic accident cause analysis results often tending to record more minor accidents. By introducing the factor weights, a weighted association rule mining algorithm is constructed, and the risk factor data in the enhanced and balanced traffic accident data set is analyzed through the weighted association rule mining algorithm to identify traffic safety risk factors, taking into account the more critical causal factors of serious accidents and their interactive relationships, so that the relevant research results can be more effectively applied to reducing the severity of traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1A schematic diagram of a flow chart of a method for intelligently identifying traffic safety risk factors for highway reconstruction and expansion provided by an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of the structure of an intelligent identification system for traffic safety risk factors in highway reconstruction and expansion provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0022] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0023] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0024] Reference Manual Attached Figure 1 , showing a flow chart of a method for intelligently identifying traffic safety risk factors for highway reconstruction and expansion provided by an embodiment of the present invention.

[0025] The embodiment of the present invention provides a method for intelligently identifying traffic safety risk factors for highway reconstruction and expansion, which can be implemented by a device for intelligently identifying traffic safety risk factors for highway reconstruction and expansion, and the device for intelligently identifying traffic safety risk factors for highway reconstruction and expansion can be a terminal or a server. The processing flow of the method for intelligently identifying traffic safety risk factors for highway reconstruction and expansion can include the following steps:

[0026] S1: Obtain a traffic accident dataset during the highway reconstruction and expansion project. The traffic accident dataset includes various types of risk factor data.

[0027] Optionally, the risk factor data is divided into minor accident data, general accident data and serious accident data.

[0028] In actual applications, accident data of different severity levels may be unbalanced, causing the analysis results to be biased towards the category with a large number of accidents.

[0029] For example, the data of severe accidents is much smaller than that of general accidents. In this case, the data of severe accidents are minority type data, while the data of general accidents are majority type data.

[0030] In the present invention, by classification processing, the influence of each category can be better balanced and the influence of data bias on the analysis results can be reduced. By analyzing risk factor data of different categories, resources can be allocated and priorities can be set more reasonably. For example, serious accidents may require higher attention and resource investment, while minor accidents may be intervened through lower-cost measures.

[0031] S2: Use the SMOTE algorithm to enhance and balance the minority risk factor data in the traffic accident dataset.

[0032] Among them, the SMOTE (Synthetic Minority Over-sampling Technique) algorithm is a technology used to process unbalanced data sets. It balances the data set by synthesizing new minority class samples based on existing minority class samples and their neighboring data points, thereby increasing the number of minority class samples in the data set, reducing the classifier's bias towards majority class samples, and improving the performance and generalization ability of the classification model.

[0033] Specifically, the SMOTE technology is used to expand the number of minority risk factor data by inserting new synthetic accident data between the minority risk factor data to reach an order of magnitude similar to that of the majority risk factor data, thereby achieving risk factor data balance.

[0034] In a possible implementation manner, S2 is specifically:

[0035] According to the following formula, the SMOTE algorithm is used to enhance and balance the data of a few types of risk factors in the traffic accident dataset:

[0036]

[0037] in, represents synthetic accident data, M represents general accident data, N represents severe accident data, and x M,N represents the original accident data, which includes the original general accident data and the original severe accident data. λ represents the degree of similarity between the synthetic accident data and the original accident data. kM,N Represents the kth adjacent accident data of the original accident data.

[0038] In the present invention, there may be a situation in the traffic accident data set where the minority type risk factor data is far less than the majority type risk factor data. This imbalance will cause the classifier to be biased towards the majority class samples and ignore the minority class samples during the training process. The SMOTE algorithm balances the data set by generating synthetic minority class samples, thereby reducing this bias and improving the model's recognition ability for the minority class. An unbalanced data set may cause the model to make inaccurate predictions about the minority class or ignore the minority class. The SMOTE algorithm synthesizes new minority class samples to make the data set more balanced and reduce the deviation caused by sample imbalance.

[0039] S3: Determine the factor weights of each traffic safety risk factor through the FAHP algorithm.

[0040] Among them, the FAHP algorithm (Fuzzy Analytic Hierarchy Process) is a hierarchical analysis method based on fuzzy mathematics theory, which is used to determine the weights of factors in complex decision-making problems. It constructs a pairwise comparison judgment matrix, calculates the fuzzy weights using the geometric mean method, defuzzifies the weights using the centroid method, and finally performs normalization processing to obtain the weights of each factor in the decision-making, so as to help decision makers make accurate trade-offs and decisions.

[0041] Optionally, traffic safety risk factors include road reconstruction and expansion, traffic, construction, environment and driver factors.

[0042] It should be noted that the FAHP algorithm is used to deal with the fuzziness of the importance division of various traffic safety risk factors in the process of weight allocation.

[0043] In a possible implementation, S3 specifically includes sub-steps S301 to S304:

[0044] S301: Using triangular fuzzy numbers, construct a pairwise comparison judgment matrix:

[0045]

[0046] in, represents the pairwise comparison judgment matrix, Indicates traffic safety risk factor A i and traffic safety risk factors A j The comparison results are as follows: It is represented by a triple l ij Indicates traffic safety risk factor A i Relative to traffic safety risk factor A j The fuzzy lower bound value, m ij Indicates traffic safety risk factor A iRelative to traffic safety risk factor A j The fuzzy median, u ij Indicates traffic safety risk factor A i Relative to traffic safety risk factor A j The fuzzy upper bound of .

[0047] S302: According to the pairwise comparison judgment matrix, the fuzzy weights of each traffic safety risk factor are determined using the geometric mean method:

[0048]

[0049] in, represents the fuzzy weight of each traffic safety risk factor, P represents the total number of traffic safety risk factors, and n represents the traffic safety risk factor A i and traffic safety risk factors A j The total number of comparison results.

[0050] It should be noted that for each traffic safety risk factor A i , the fuzzy weights are calculated using the geometric mean method.

[0051] S303: Defuzzifying the fuzzy weights using the centroid method to obtain defuzzified weights of various traffic safety risk factors.

[0052] In a possible implementation manner, S303 specifically includes:

[0053] According to the following formula, the fuzzy weight is defuzzified using the centroid method to obtain the defuzzified weight of each traffic safety risk factor:

[0054]

[0055] Among them, W i represents the defuzzified weight of each traffic safety risk factor, l i Indicates traffic safety risk factor A i The fuzzy lower limit weight, m i Indicates traffic safety risk factor A i The fuzzy median weight, u i Indicates traffic safety risk factor A i The fuzzy upper limit weight of .

[0056] S304: Normalize the defuzzified weights to determine the weights of each traffic safety risk factor:

[0057]

[0058] Among them, W i ′represents the factor weight of each traffic safety risk factor, W i represents the defuzzified weight of each traffic safety risk factor, n ′ Represents the total number of defuzzification weights.

[0059] In the present invention, the FAHP algorithm comprehensively considers the relative importance of various factors by constructing a pairwise comparison judgment matrix. This method can more comprehensively evaluate the impact of different factors, so that the final weights can more accurately reflect the actual role of each factor in traffic safety risks. Through the calculation and defuzzification of fuzzy weights, the FAHP algorithm converts subjective evaluations into quantitative weight values, which can provide clear data support for decision makers and help make more objective decisions. The normalization processing step of FAHP can ensure that the sum of the weights of all factors is 1, which helps to compare and analyze the relative importance of each factor in practical applications and avoid misunderstandings caused by the absolute size of the weight values.

[0060] S4: By introducing factor weights, a weighted association rule mining algorithm is constructed.

[0061] It should be noted that in the frequent item set generation stage of the Apriori association rule mining algorithm, the traffic accident causal factors with factor weights are introduced to construct a weighted association rule mining algorithm.

[0062] Furthermore, constraints on the latter terms of the association rules are set. According to the causal relationship between traffic safety risk factors and the severity of traffic accidents, each traffic safety risk factor is constrained in the former term of the rule, and the accident severity index is directionally constrained in the latter term of the rule.

[0063] It should be noted that the antecedent of the rule is the condition that leads to the result, and the consequent of the rule is the result caused by the antecedent of the rule.

[0064] Among them, the Apriori association rule mining algorithm is a classic data mining algorithm used to discover frequently occurring item sets and association rules in a data set. The algorithm is based on two key concepts: support and confidence. First, candidate item sets are iteratively generated, and their support is calculated, and item sets below the set threshold are filtered out to obtain frequent item sets. Then, by generating association rules and calculating their confidence, rules below the set threshold are filtered out to obtain strong association rules, which helps analyze association patterns and rules in the data.

[0065] Furthermore, when generating candidate item sets, three indicators, namely weighted support, weighted confidence and lift, are calculated for each item set.

[0066] In the present invention, by introducing factor weights, the rule mining process can be adjusted according to the importance of each traffic safety risk factor. This weighting mechanism makes the mining of association rules more in line with the actual situation and can more accurately reflect the role of each factor in the accident. The introduction of weights and causal constraints makes the generated rules more interpretable. For example, through the relationship between the traffic safety risk factors in the antecedent of the rule and the severity of the accident in the posterior of the rule, it is possible to more intuitively understand which factors have a greater impact on the severity of the accident, thereby improving the practical application value of the rules.

[0067] S5: Through the weighted association rule mining algorithm, the risk factor data in the enhanced and balanced traffic accident data set is analyzed to identify traffic safety risk factors.

[0068] In a possible implementation, S5 specifically includes sub-steps S501 to S504:

[0069] S501: Calculate the weighted support of each association rule in the candidate item set through the weighted association rule mining algorithm, and prune the item sets below the set minimum support threshold to obtain frequent item sets.

[0070] It should be noted that those skilled in the art can set the minimum support threshold value according to actual needs, and the present invention does not limit this.

[0071] In a possible implementation manner, S501 specifically includes:

[0072] The weighted support of each association rule in the candidate set is calculated according to the following formula:

[0073]

[0074] Among them, WSupport(·) represents weighted support, A→B represents association rules, A represents the rule antecedent, B represents the rule consequent, T represents the transaction set, t represents the transaction, and count(Total) represents the total number of transactions in the transaction database.

[0075] Among them, weighted support represents the weighted probability of item set A and item set B appearing in all transactions. The transaction set represents the traffic accident data set. The item set contains several traffic safety risk factors related to traffic accidents. The transaction represents a traffic accident record in the database.

[0076] S502: Calculate the weighted confidence of each association rule in the frequent item set, and retain the association rules that are higher than the set minimum confidence threshold as strong association rules.

[0077] It should be noted that those skilled in the art can set the minimum confidence threshold according to actual needs, and the present invention does not limit this.

[0078] In a possible implementation manner, S502 specifically includes:

[0079] The weighted confidence of each association rule in the frequent item set is calculated according to the following formula:

[0080]

[0081] Where WConfidence(·) represents the weighted confidence.

[0082] The weighted confidence represents the weighted conditional probability that the consequent of the rule will also occur when the antecedent of the rule occurs.

[0083] S503: Calculate the lift of each strong association rule, and retain the strong association rules that are higher than a set minimum lift threshold.

[0084] It should be noted that those skilled in the art can set the minimum boost threshold value according to actual needs, and the present invention does not limit this.

[0085] In a possible implementation manner, S503 specifically includes:

[0086] According to the following formula, the lift of each strong association rule is calculated:

[0087]

[0088] Among them, Lift(·) represents the lifting degree.

[0089] The lift represents the ratio of the weighted confidence of the association rule to the weighted support of the rule's consequent. If the lift is greater than 1, it indicates that there is a positive correlation between the rule's antecedent and the rule's consequent.

[0090] S504: Using strong association rules, analyze the risk factor data in the enhanced and balanced traffic accident data set to identify traffic safety risk factors.

[0091] In the present invention, the calculation of weighted support, weighted confidence and lift enables the mined association rules to more accurately reflect the relationship between various traffic safety risk factors. This method can help identify which combinations of factors have a significant impact on the occurrence and severity of accidents, thereby improving the understanding of traffic safety risks. By setting the minimum support, minimum confidence and minimum lift thresholds, irrelevant or low-impact item sets and rules can be effectively filtered out. This screening process ensures the reliability and effectiveness of the analysis results and avoids the influence of interference factors on the results. By analyzing strong association rules, it is possible to identify which combinations of factors have a significant impact on the severity of accidents. This information can be used to optimize traffic safety intervention measures and formulate more effective prevention strategies, thereby reducing the risk of accidents.

[0092] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0093] In the present invention, by using the SMOTE algorithm, data enhancement and balance are performed on a few types of risk factor data in the traffic accident data set, thereby avoiding the phenomenon that the traffic accident data during the highway reconstruction and expansion project are insufficient in quality and quantity, making the accident severity data present an obvious balance, and increasing the proportion of accidents with higher severity levels in the data, thereby avoiding the subsequent traffic accident cause analysis results often tending to record more minor accidents. By introducing the factor weights, a weighted association rule mining algorithm is constructed, and the risk factor data in the enhanced and balanced traffic accident data set is analyzed through the weighted association rule mining algorithm to identify traffic safety risk factors, taking into account the more critical causal factors of serious accidents and their interactive relationships, so that the relevant research results can be more effectively applied to reducing the severity of traffic accidents.

[0094] Reference Manual Attached Figure 2 , showing a schematic structural diagram of a system for intelligent identification of traffic safety risk factors for highway reconstruction and expansion provided by the present invention.

[0095] The present invention further provides a highway reconstruction and expansion traffic safety risk factor intelligent identification system 30, comprising: a memory 303 and one or more processors 301.

[0096] The memory 303 stores one or more application programs, and the one or more application programs are suitable for being executed by the one or more processors 301 to implement the intelligent identification method for traffic safety risk factors in highway reconstruction and expansion described in the method embodiment.

[0097] The intelligent identification system 30 for traffic safety risk factors in highway reconstruction and expansion includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, through a bus 302.

[0098] The structure of the intelligent identification system 30 for traffic safety risk factors in highway reconstruction and expansion does not constitute a limitation on the embodiment of the present invention.

[0099] Processor 301 may be a CPU, a general purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0100] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI bus or an EISA bus, etc. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0101] The memory 303 can be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an EEPROM, a CD-ROM or other optical disk storage, an optical disk storage (including a compressed optical disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0102] It should be noted that the intelligent identification system 30 for traffic safety risk factors in highway reconstruction and expansion can implement the above-mentioned intelligent identification method for traffic safety risk factors in highway reconstruction and expansion, and can achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0103] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0104] In the present invention, by using the SMOTE algorithm, data enhancement and balance are performed on a few types of risk factor data in the traffic accident data set, thereby avoiding the phenomenon that the traffic accident data during the highway reconstruction and expansion project are insufficient in quality and quantity, making the accident severity data present an obvious balance, and increasing the proportion of accidents with higher severity levels in the data, thereby avoiding the subsequent traffic accident cause analysis results often tending to record more minor accidents. By introducing the factor weights, a weighted association rule mining algorithm is constructed, and the risk factor data in the enhanced and balanced traffic accident data set is analyzed through the weighted association rule mining algorithm to identify traffic safety risk factors, taking into account the more critical causal factors of serious accidents and their interactive relationships, so that the relevant research results can be more effectively applied to reducing the severity of traffic accidents.

[0105] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program can be loaded and executed by a processor according to the computing resource aggregation method based on pooled memory as described in the first aspect.

[0106] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0107] There are a few points to note:

[0108] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0109] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0110] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0111] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for intelligently identifying traffic safety risk factors for highway reconstruction and expansion, characterized in that: include: S1: Obtain a traffic accident dataset during the highway reconstruction and expansion project, wherein the traffic accident dataset includes multiple types of risk factor data; S2: Use the SMOTE algorithm to perform data enhancement and balancing on the minority types of risk factor data in the traffic accident dataset; S3: Determine the factor weights of each traffic safety risk factor through the FAHP algorithm; S4: constructing a weighted association rule mining algorithm by introducing the factor weights; S5: Through the weighted association rule mining algorithm, the risk factor data in the enhanced and balanced traffic accident data set is analyzed to identify traffic safety risk factors.

2. The intelligent identification method for traffic safety risk factors in highway reconstruction and expansion according to claim 1 is characterized in that: The risk factor data are divided into minor accident data, general accident data and serious accident data.

3. The intelligent identification method for traffic safety risk factors in highway reconstruction and expansion according to claim 2 is characterized in that: The S2 is specifically: According to the following formula, the SMOTE algorithm is used to enhance and balance the minority types of risk factor data in the traffic accident dataset: in, represents synthetic accident data, M represents general accident data, N represents severe accident data, and x M,N represents the original accident data, which includes the original general accident data and the original severe accident data. λ represents the degree of similarity between the synthetic accident data and the original accident data. kM,N Represents the kth adjacent accident data of the original accident data.

4. The intelligent identification method for traffic safety risk factors in highway reconstruction and expansion according to claim 1 is characterized in that: The S3 specifically includes: S301: Using triangular fuzzy numbers, construct a pairwise comparison judgment matrix: in, represents the pairwise comparison judgment matrix, Indicates traffic safety risk factor A i and traffic safety risk factors A j The comparison results are as follows: It is represented by a triple l ij Indicates traffic safety risk factor A i Relative to traffic safety risk factor A j The fuzzy lower bound value, m ij Indicates traffic safety risk factor A i Relative to traffic safety risk factor A j The fuzzy median, u ij Indicates traffic safety risk factor A i Relative to traffic safety risk factor A j The fuzzy upper bound of ; S302: According to the pairwise comparison judgment matrix, the fuzzy weight of each traffic safety risk factor is determined using the geometric mean method: in, represents the fuzzy weight of each traffic safety risk factor, P represents the total number of traffic safety risk factors, and n represents the traffic safety risk factor A i and traffic safety risk factors A j The total number of comparison results; S303: Defuzzifying the fuzzy weights using a gravity center method to obtain defuzzified weights of various traffic safety risk factors; S304: normalizing the defuzzified weights to determine the factor weights of each traffic safety risk factor: Among them, W i ′ represents the factor weight of each traffic safety risk factor, W i represents the defuzzified weight of each traffic safety risk factor, and n′ represents the total number of defuzzified weights.

5. The intelligent identification method for traffic safety risk factors in highway reconstruction and expansion according to claim 4 is characterized in that: The S303 is specifically: According to the following formula, the fuzzy weight is defuzzified using the centroid method to obtain the defuzzified weight of each traffic safety risk factor: Among them, W i represents the defuzzified weight of each traffic safety risk factor, l i Indicates traffic safety risk factor A i The fuzzy lower limit weight, m i Indicates traffic safety risk factor A i The fuzzy median weight, u i Indicates traffic safety risk factor A i The fuzzy upper limit weight of .

6. The intelligent identification method for traffic safety risk factors in highway reconstruction and expansion according to claim 1 is characterized in that: The S5 specifically includes: S501: Calculate the weighted support of each association rule in the candidate item set through the weighted association rule mining algorithm, and prune the item sets below the set minimum support threshold to obtain frequent item sets; S502: Calculate the weighted confidence of each association rule in the frequent item set, and retain the association rules that are higher than the set minimum confidence threshold as strong association rules; S503: Calculate the lift of each strong association rule, and retain the strong association rules that are higher than the set minimum lift threshold; S504: Using the strong association rule, the risk factor data in the enhanced and balanced traffic accident data set is analyzed to identify traffic safety risk factors.

7. The intelligent identification method for traffic safety risk factors in highway reconstruction and expansion according to claim 6 is characterized in that: The S501 is specifically as follows: The weighted support of each association rule in the candidate set is calculated according to the following formula: Among them, WSupport(·) represents weighted support, A→B represents association rules, A represents the rule antecedent, B represents the rule consequent, T represents the transaction set, t represents the transaction, and count(Total) represents the total number of transactions in the transaction database.

8. The intelligent identification method for traffic safety risk factors in highway reconstruction and expansion according to claim 6 is characterized in that: The S502 is specifically as follows: The weighted confidence of each association rule in the frequent item set is calculated according to the following formula: Where WConfidence(·) represents the weighted confidence.

9. The intelligent identification method for traffic safety risk factors in highway reconstruction and expansion according to claim 6 is characterized in that: The S503 is specifically as follows: According to the following formula, the lift of each strong association rule is calculated: Among them, Lift(·) represents the lifting degree.

10. An intelligent identification system for traffic safety risk factors in highway reconstruction and expansion, characterized in that: include: memory and one or more processors; One or more applications are stored in the memory, and the one or more applications are suitable for being executed by the one or more processors to implement the intelligent identification method for traffic safety risk factors in highway reconstruction and expansion as described in any one of claims 1 to 9.

Images