Multi-element multi-scale highway traffic operation risk assessment method and device

Abstract

The invention relates to the field of traffic safety and risk assessment, in particular to a multi-element multi-scale highway traffic operation risk assessment method and device, and the method comprises the following steps: S1, determining the assessment index of each risk factor through recognizing the risk factors of highway traffic operation; s2, calculating a subjective weight and an objective weight of the evaluation index, and calculating an optimal combination weight of the evaluation index according to the subjective weight and the objective weight; s3, according to the optimal combination weight, calculating comprehensive determinacy of road traffic operation under different risk levels; and S4, comparing the comprehensive certainty degrees under different risk levels, wherein the risk level with the maximum comprehensive certainty degree is the risk level of road traffic operation. According to the method, through the steps of risk factor identification, weight calibration, cloud model analysis, risk analysis model establishment and the like, multi-dimensional information of various influence factors is fused, comprehensive risk assessment is carried out, and the influence of various risk factors on highway traffic operation can be systematically identified and quantified.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic safety and risk assessment, and in particular to a multi-factor and multi-scale highway traffic operation risk assessment method and device. Background Art

[0002] With the continuous expansion of highway traffic scale and the increase of traffic density, traffic accidents occur frequently, causing increasingly serious casualties and property losses, and effective risk analysis and management methods are urgently needed. However, the existing highway traffic risk assessment is mostly limited to a single factor or local conditions, or uses alternative indicators such as accidents and conflicts to characterize the changes in traffic operation risks, and fails to fully consider the interaction of multiple risk factors and the temporal and spatial variation characteristics of each factor, resulting in insufficient accuracy and comprehensiveness of the assessment results. This single-dimensional risk analysis method is difficult to cope with the complex and changeable real environment in the process of highway traffic operation.

[0003] The risk of highway traffic operation is often the result of multiple factors, involving disasters (such as natural disasters such as rainstorms and earthquakes), environment (such as weather conditions, visibility), vehicles (vehicle types, vehicle conditions, etc.), roads (geometric shape, sight distance, key structure conditions, road surface and subgrade conditions, layout of facilities along the road, etc.) and traffic flow characteristics (flow, density, traffic composition, saturation) and other aspects. These factors not only affect each other, but also have different spatiotemporal scale variation characteristics. In order to comprehensively and effectively evaluate the operational risks of highway traffic, a comprehensive analysis method must be adopted to simultaneously consider the role and weight of various risk factors at multiple scales and dimensions, accurately identify risk points and issue early warnings. Summary of the invention

[0004] The method of the present invention constructs a risk assessment system based on a cloud model, quantifies and measures the risk status of road traffic with cloud droplet certainty, integrates multi-dimensional information of various influencing factors, and proposes a multi-factor and multi-scale highway traffic operation risk assessment method and device, which can systematically identify and quantify the impact of various risk factors on highway traffic operation, and improve the accuracy and reliability of risk assessment.

[0005] In order to achieve the above objectives, the following technical solutions are proposed: A multi-factor and multi-scale highway traffic operation risk assessment method comprises the following steps: S1. Identify the risk factors of highway traffic operation and determine the evaluation indicators of each risk factor; S2. Calculate the subjective weight and objective weight of the evaluation indicators, and calculate the optimal combination weight of the evaluation indicators based on the subjective weight and the objective weight; S3. Calculate the comprehensive certainty of highway traffic operation at different risk levels based on the optimal combination weights; S4. Compare the comprehensive certainties under different risk levels. The risk level of highway traffic operation is the one with the largest comprehensive certainty.

[0006] Preferably, the calibration method of the subjective weight is: S21, establishing a judgment matrix according to the evaluation index, and calculating a weight coefficient according to the judgment matrix; S22. Determine the rationality of the weight coefficient through consistency test: calculate the ratio of the consistency index and the random consistency index. When the ratio is less than 0.1, the weight coefficient and the judgment matrix pass the consistency test. The judgment matrix after the consistency test is the subjective weight.

[0007] Preferably, the objective weight is calculated as follows: Establish a decision matrix based on the evaluation indicators included in the evaluation object and the attributes of each evaluation indicator; The decision matrix is ​​dimensionless processed to obtain a standardized decision matrix; the positive ideal solution and the negative ideal solution are calculated according to the standardized decision matrix, and the relative error matrix is ​​calculated according to the positive ideal solution and the negative ideal solution; The weights are calculated using the angle cosine formula according to the relative error matrix, and the calculated weights are normalized to obtain objective weights.

[0008] Preferably, the optimal combination weight is calculated according to the minimum discriminant information principle, and the determination target of the optimal combination weight is: Restrictions on the combination weights: The formula for the combined weight is: Among them, F is the target, W is j is the j-th attribute combination weight, W 1j is the normalized subjective weight of the jth attribute, W 2j is the objective weight of the j-th attribute after normalization, and n and j are integers greater than 1.

[0009] Preferably, the specific steps of the method in S3 are: The road traffic operation risks are divided into five levels from low to high risk: very low risk, low risk, medium risk, high risk and very high risk; The cloud model is used to calculate the key parameters of the cloud model for each risk factor. The key parameters of the cloud model include the expected value Ex of the average level of each risk factor, the entropy value En reflecting the fluctuation range of the risk factor, and the super entropy value He of the entropy value uncertainty; Calculate the degree of certainty of each risk factor based on the key parameters of the cloud model; On the basis of the calculation of the certainty of each risk factor, weighting is performed according to the optimal combination weight to calculate the comprehensive certainty under different risk levels.

[0010] Preferably, the expected value Ex of the average level of each risk factor satisfies x~N(Ex, En' ２ ), and the entropy value En reflecting the fluctuation range of risk factors satisfies En'~N(En,He ２ ).

[0011] Preferably, the degree of certainty of each risk factor is calculated as follows: in, The risk assessment index i Under the indicator j The degree of certainty of x i For the i The measured values ​​of the evaluation indicators, Ex ij It is i The element j The expected value of the attribute, En ij For the i The element j The entropy value of the attribute.

[0012] Preferably, the calculation formula of the key parameters of the cloud model is: Among them, Ex ij It is i The element j The expected value of the attribute, En ij For the i The element j The entropy value of the attribute, He ij For the i The element j The super entropy value of the attribute, V min For different risk levels i The element j The lower boundary value of the attribute risk indicator threshold, V max For different risk levels i The element j The upper boundary value of the attribute risk indicator threshold, k is a constant.

[0013] Preferably, the comprehensive certainty is calculated as follows: in, For the j Wi is the comprehensive certainty at the i-th level, and Wi is the combined weight of the i-th risk indicator.

[0014] Based on the same concept, a multi-factor and multi-scale highway traffic operation risk assessment device is also proposed, characterized in that it includes at least one processor and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the multi-factor and multi-scale highway traffic operation risk assessment methods described above.

[0015] Compared with the prior art, the present invention has the following beneficial effects: the method of the present invention can integrate multiple risk factors at multiple scales, fully consider the changes and interactions of relevant factors in time and space, and ensure the comprehensiveness and dynamism of risk assessment. Quantitative means are used in all aspects of risk analysis to make the analysis process more objective and accurate. At the same time, through the application of cloud models, managers can intuitively observe the risk level of the degree of certainty, so as to timely identify and evaluate potential risks in road operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a multi-factor and multi-scale highway traffic operation risk assessment method in Example 1; Figure 2 is a flowchart of subjective weight calculation in Example 1; Figure 3 is the objective weight calculation flow chart in Example 1; Figure 4 This is the risk analysis modeling flow chart based on the cloud model in Example 1. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below in conjunction with test examples and specific implementation methods. However, this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the content of the present invention belong to the scope of the present invention.

[0018] Example 1 A multi-factor and multi-scale highway traffic operation risk assessment method and device, the flow chart is as follows Figure 1 As shown, the following steps are included: S1. Identify the risk factors of highway traffic operation and determine the evaluation indicators of each risk factor; S2. Calculate the subjective weight and objective weight of the evaluation indicators, and calculate the optimal combination weight of the evaluation indicators based on the subjective weight and the objective weight; S3. Calculate the comprehensive certainty of highway traffic operation at different risk levels based on the optimal combination weights; S4. Compare the comprehensive certainties under different risk levels. The risk level of highway traffic operation is the one with the largest comprehensive certainty.

[0019] As a specific implementation example, according to the steps of "risk factor identification - risk factor weight calibration - establishing a risk analysis model - determining risk assessment results", the fault tree model is first used to identify various risk factors that affect the risk of highway traffic operation. Then, the hierarchical analysis method, TOPSIS method, and minimum discriminant information principle are used to determine the optimal combination weights of each risk factor. Subsequently, the cloud model is used to analyze the highway traffic operation risk, and the certainty of each risk factor and the comprehensive certainty of the operation risk at different levels are output. Finally, the risk level of highway traffic operation is determined based on the principle of maximum certainty.

[0020] This method comprehensively considers multiple dimensions such as road infrastructure, traffic operation status, driver characteristics, vehicle performance and environmental characteristics. By constructing a risk assessment system based on a cloud model, the cloud droplet certainty is used to quantify and measure the risk status of road traffic.

[0021] Furthermore, the specific implementation process of the present invention is as follows: Step 1: Identification of risk factors Relying on the fault tree analysis method, with "highway traffic operation risk" as the top event, corresponding to the key components of road traffic (people, vehicles, roads, and environment), it is divided into intermediate events such as traffic operation status, drivers, vehicles, roads, and environment, and is refined layer by layer to quantifiable basic event evaluation indicators. Each basic event is a risk factor. On the basis of risk factor identification, each risk factor is divided into risk source indicators and the threshold of each indicator is determined. The risk factor fault tree is shown in Table 1.

[0022] Table 1 Risk factor identification table based on fault tree Step 2: Risk factor weighting The analytic hierarchy process and TOPSIS method are used to calculate the subjective weight and objective weight of the indicators, and the optimal combination weight of each evaluation indicator is calculated based on the minimum discriminant information principle.

[0023] 1) Subjective weight The subjective weight calibration process is as follows: Figure 2 shown.

[0024] First, establish the judgment matrix A based on the risk factors determined in step 1. , the element a of the judgment matrix ij The 1-9 scale method is used to obtain the value, and the meaning of the scale value is shown in Table 2.

[0025] Table 2 Meaning of judgment matrix scale values Scale meaning 1 <![CDATA[Indicating that two elements a i and a j have the same importance compared to each other]]> 3 <![CDATA[Indicating that compared with two elements a i and a j it is slightly more important]]> 5 <![CDATA[Indicating that compared with two elements a i and a j it is significantly more important]]> 7 <![CDATA[Indicating that compared with two elements a i and a j it has strong importance]]> 9 <![CDATA[Indicating that compared with two elements a i and a j is of extreme importance]]> 2、4、6、8 Indicates the intermediate value of the adjacent judgment mentioned above The reciprocal of the scale 1 to 9 <![CDATA[If the importance ratio of factor i to factor j is a ij , then the importance ratio of factor j to factor i is a ji = 1 / a ij > For the constructed judgment matrix A, find its maximum eigenvalue λ max The corresponding eigenvector ω is then weighted using the normalized square root method.

[0026] Afterwards, the weight coefficient ω obtained by the matrix A is judged by consistency test i Is it reasonable?

[0027] The smaller the consistency index CI of the judgment matrix is ​​and the closer it is to 0, the more reliable the weight coefficient of the judgment matrix is. The CI calculation formula is as follows: Where: n is the order of the judgment matrix.

[0028] The random consistency index RI is introduced to measure the consistency index CI of the judgment matrix. The ratio of the consistency index CI to the random consistency index RI is the consistency ratio CR. When the consistency ratio CR is less than 0.1, the weight distribution is considered to be reasonable and the judgment matrix passes the consistency test. The calculation formula is as follows: Among them, the average random consistency index RI is obtained from Table 3: Table 3 Random consistency index RI When the consistency ratio CR of the judgment matrix is ​​less than 0.1, the judgment matrix passes the consistency test, indicating that the weight distribution of each indicator factor is reasonable and the result is available; otherwise, the judgment matrix needs to be re-established until the consistency requirements are met.

[0029] Therefore, the matrix after consistency evaluation is the subjective weight .

[0030] 2) Objective weight The TOPSIS method is used to obtain the objective weight of the evaluation index. The calculation process is as follows: Figure 3 shown.

[0031] First, a judgment matrix is ​​established based on the evaluation indicators and attributes of each indicator, and a decision matrix is ​​established. .

[0032] Where: b ij is the j-th attribute evaluation index value of the i-th element in the total target set.

[0033] The decision matrix B established by square sum normalization iPerform dimensionless processing and establish a standardized decision matrix after the processing is completed .

[0034] Where: Z ij is the j-th attribute evaluation index value of the ith element in the total target set after normalization.

[0035] The standardized decision matrix can determine the positive ideal solution and negative ideal solution , and its calculation formula is as follows: Compute the relative error matrix of positive and negative ideal solutions : Where: is the positive ideal solution corresponding to i The element j Attribute positive relative error value, is the negative ideal solution corresponding to i The element j Attribute negative relative error value.

[0036] Based on the results of the positive and negative ideal solutions, the angle cosine formula is used to determine the weight, and the calculated weight results are normalized to obtain the objective weight .

[0037] Weight determination: Normalization: Where: W 2j is the objective weight of the jth attribute after normalization, w j For the j The initial objective weight of each attribute.

[0038] 3) Combination weight The minimum discriminant information principle is used to effectively combine the subjective and objective weights.

[0039] Combined weights determine the target: Restrictions: The above optimization problem is solved by the Lagrange multiplier method to obtain the combined weight W=(W1,W2,…,W j )(j=1,2,…n): Among them, F is the target, W is j is the j-th attribute combination weight, W1j is the normalized subjective weight of the jth attribute, W 2j is the objective weight of the j-th attribute after normalization, and n and j are integers greater than 1.

[0040] Step 3: Risk Analysis Modeling The cloud model is used to analyze the highway traffic operation risk and establish a highway traffic operation risk analysis model. The risk analysis modeling process is as follows: Figure 4 shown.

[0041] 1) Determine the risk assessment index level standard According to the relationship between the factors affecting highway traffic operation risks and traffic safety, highway traffic operation risks are divided into five levels: extremely low risk, low risk, medium risk, high risk, and extremely high risk. The risk characteristics of each level are shown in Table 4.

[0042] Table 4 Risk level classification table According to the risk level classification table, construct the comment set V = {v1, v2, v3, v4, v5}, where V i (i=1,2,3…,n) represents different levels of evaluation.

[0043] 2) Preprocessing of basic data on risk factors The actual value of each risk factor is collected and corresponds to the proposed risk assessment parameters. According to the characteristics of different indicators, different indicators are standardized according to the process of "raw data extraction - abnormal data elimination - key indicator calculation - risk source parameter arrangement".

[0044] 3) Calculation of key parameters of each risk factor For each risk factor identified, the reverse cloud model is used to generate the digital features of the cloud model of each risk factor using the binomial constraint method according to the risk assessment set, and the indicator features of the risk factor are calculated.

[0045] The key parameters of the cloud model include the expected value (Ex) reflecting the central tendency or average level of each risk factor, the entropy value (En) reflecting the uncertainty or fluctuation range of the risk factor, and the super entropy value (He) reflecting the uncertainty of the entropy value. i Under the indicator j The evaluation score range of each level is [V min ,V max ],but Where: Ex ij It is i The element j The expected value of the attribute, En ijFor the i The element j The entropy value of the attribute, He ij For the i The element j The super entropy value of the attribute, V min For different risk levels i The element j The lower boundary value of the attribute risk indicator threshold, V max For different risk levels i The element j The upper boundary value of the attribute risk index threshold, k is a constant, and is the entropy value He ij The uncertainty measure is based on En ij The value range is [0.01,0.1], and k≤ En ij .

[0046] 4) Clarify the degree of certainty of risk factors The calculation process of the risk factor certainty is the cloud droplet generation process. Through the expected value, entropy value and super entropy value, cloud droplets reflecting the road operation status can be generated. Each cloud droplet represents the relationship between the quantitative data of a risk factor and the qualitative concept (risk level).

[0047] If the cloud distribution expectation of a risk factor satisfies x~N(Ex, En' ２ ), and the entropy value satisfies En'~N(En,He ２ ), the calculation formula of the certainty of the risk factor is: in, The risk assessment index i Under the indicator j The degree of certainty of x i For the i The measured values ​​of the evaluation indicators, Ex ij It is i The element j The expected value of the attribute, En ij For the i The element j The entropy value of the attribute.

[0048] 5) Comprehensive certainty calculation The final risk index is calculated with comprehensive certainty as an indicator. Based on the calculation of the certainty of each risk factor, the comprehensive certainty at different levels is calculated by weighting according to the weight. The calculation formula of comprehensive certainty is: In the formula, The risk assessment index i Under the indicator j The level of certainty, For the j The comprehensive certainty at each level, W i is the combined weight of the ith risk indicator.

[0049] Step 4: Determine the risk level According to the calculation results of the comprehensive certainty at different levels in step 3, the risk level of highway traffic operation is judged according to the principle of maximum certainty. The level with the maximum comprehensive certainty is the risk level of the evaluated section.

[0050] The following examples are used to verify the beneficial effects of the present invention: Taking the traffic operation risk analysis of a key section of a certain highway (water-crossing road surface, length of about 2 km) as an example, the application of the present invention is described. The section is 3428 meters above sea level, with a design speed of 60 km / h and a speed limit of 40 km / h. The geological disaster here is mainly landslides. Based on the disaster survey and the data collected on the spot, such as altitude, driving time, vehicle type, traffic volume, and road factors, the traffic operation risk factors in this scenario are first identified, as shown in Table 5.

[0051] Table 5 Identified traffic operation risk indicators On this basis, according to the hierarchical analysis method and TOPSIS method proposed in step 2, the combined weights of the evaluation indicators are calculated, and the results are shown in Table 6.

[0052] Table 6 Evaluation index combination weight values Combined with the combined weight values ​​of each evaluation index, the cloud model parameters are calibrated, and the cloud model characteristic values ​​(expected Ex, entropy En, and super entropy He) of each evaluation index belonging to the risk level are calculated through the reverse cloud generator of the cloud model. The results are shown in Table 7.

[0053] Table 7 Calculation results of key parameters of cloud model for each risk assessment index The traffic operation risk level is divided into 5 levels: low (level I), medium-low (level II), medium (level III), medium-high (level IV), and high (level V). Based on the calculation results of the indicators actually collected in Table 4 and the characteristic values ​​of the cloud model indicators calculated in Table 6, the certainty of each evaluation indicator at different risk levels is calculated, as shown in Table 8.

[0054] Table 8 Evaluation index cloud level certainty Substitute the calculation results into the comprehensive certainty calculation formula of the risk level in step 3 to obtain the comprehensive certainty of the evaluated road section under the five levels, as shown in Table 9.

[0055] Table 9 Comprehensive certainty under five risk levels The results show that the comprehensive certainty value under level III risk is the highest, and it can be determined that the traffic operation risk of the evaluated section is level three.

[0056] Compared with the actual situation, the assessed section is a flooded road section. When there is water on the flooded road, the vehicle speed decreases, the road capacity decreases, and the driving behavior is more cautious. However, the section does not have water accumulation for a long time. The degree of water accumulation and the depth of water will change dynamically with the intensity of rainfall and the efficiency of the drainage system, and its traffic operation status is also changing dynamically. It can be considered that there is a certain operating risk in the assessed section, but the risk is within a controllable range. The assessment results are consistent with the actual situation.

[0057] The core innovation of the present invention lies in its multi-factor, multi-scale comprehensive analysis framework, which can effectively handle complex and changeable traffic operation environments. The method realizes the identification and accurate assessment of highway traffic operation risks, provides timely and reliable risk warnings and decision-making support for traffic managers, and helps to take reasonable risk prevention measures to reduce accident rates and economic losses. The present invention is applicable to the field of highway traffic safety management, especially in high-risk sections and complex road conditions. It has significant application value. The present invention can not only perform real-time risk identification and analysis of road traffic operation status, infrastructure status and environmental changes, but also provide managers with a scientific basis to take effective risk disposal and prevention measures in a timely manner, and minimize the damage to the economy and property caused by high-risk events. This multi-factor, multi-scale risk assessment method has greatly improved the scientificity and effectiveness of road traffic safety management.

[0058] Finally, it should be noted that the embodiments described in detail above are only the best practices of the invention and cannot be used to limit the scope of rights of the invention. Equivalent replacement of the technical solutions recorded in the aforementioned embodiments does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the invention, and they should all be included in the scope of the claims and description of the invention.

Claims

1. A multi-factor and multi-scale highway traffic operation risk assessment method, characterized in that: The following steps are involved: S1. Identify the risk factors of highway traffic operation and determine the evaluation indicators of each risk factor; S2. Calculate the subjective weight and objective weight of the evaluation indicators, and calculate the optimal combination weight of the evaluation indicators based on the subjective weight and the objective weight; S3. Calculate the comprehensive certainty of highway traffic operation at different risk levels based on the optimal combination weights; S4. Compare the comprehensive certainties under different risk levels. The risk level of highway traffic operation is the one with the largest comprehensive certainty.

2. A multi-factor and multi-scale highway traffic operation risk assessment method as claimed in claim 1, characterized in that: The calibration method of the subjective weight is: S21, establishing a judgment matrix according to the evaluation index, and calculating a weight coefficient according to the judgment matrix; S22. Determine the rationality of the weight coefficient through consistency test: calculate the ratio of the consistency index and the random consistency index. When the ratio is less than 0.1, the weight coefficient and the judgment matrix pass the consistency test. The judgment matrix after the consistency test is the subjective weight.

3. A multi-factor and multi-scale highway traffic operation risk assessment method as claimed in claim 2, characterized in that: The objective weight is calculated as follows: S31, establishing a decision matrix according to the evaluation indicators included in the evaluation object and the attributes of each evaluation indicator; S32, performing dimensionless processing on the decision matrix to obtain a standardized decision matrix; calculating a positive ideal solution and a negative ideal solution according to the standardized decision matrix, and calculating a relative error matrix according to the positive ideal solution and the negative ideal solution; S33. Calculate the weights using the angle cosine formula according to the relative error matrix, normalize the calculated weights, and obtain objective weights.

4. A multi-factor and multi-scale highway traffic operation risk assessment method as claimed in claim 1, characterized in that: The optimal combination weight is calculated according to the minimum discriminant information principle, and the optimal combination weight is determined as follows: Restrictions on the combination weights: The formula for the combined weight is: Among them, F is the target, W is j is the j-th attribute combination weight, W 1j is the normalized subjective weight of the jth attribute, W 2j is the objective weight of the j-th attribute after normalization, and n and j are integers greater than 1.

5. A multi-factor and multi-scale highway traffic operation risk assessment method as claimed in claim 1, characterized in that: The specific steps of the method described in S3 are: S51. The highway traffic operation risks are divided into five levels from low to high: very low risk, low risk, medium risk, high risk and very high risk; S52, using the cloud model to calculate the key parameters of the cloud model for each risk factor, the key parameters of the cloud model include the expected value Ex of the average level of each risk factor, the entropy value En reflecting the fluctuation range of the risk factor, and the super entropy value He of the entropy value uncertainty; S53. Calculate the degree of certainty of each risk factor based on the key parameters of the cloud model; S54. Based on the calculation of the degree of certainty of each risk factor, weighting is performed according to the optimal combination weight to calculate the comprehensive degree of certainty under different risk levels.

6. A multi-factor and multi-scale highway traffic operation risk assessment method as claimed in claim 5, characterized in that: The expected value Ex of the average level of each risk factor satisfies x~N(Ex, En' ２ ), and the entropy value En reflecting the fluctuation range of risk factors satisfies En'~N(En,He ２ ).

7. A multi-factor and multi-scale highway traffic operation risk assessment method as claimed in claim 5, characterized in that: The calculation method of the certainty of each risk factor is as follows: in, The risk assessment index i Under the indicator j The degree of certainty of x i For the i The measured values ​​of the evaluation indicators, Ex ij It is i The element j The expected value of the attribute, En ij For the i The element j The entropy value of the attribute.

8. A multi-factor and multi-scale highway traffic operation risk assessment method as claimed in claim 5, characterized in that: The calculation formula of the key parameters of the cloud model is: Among them, Ex ij It is i The element j The expected value of the attribute, En ij For the i The element j The entropy value of the attribute, He ij For the i The element j The super entropy value of the attribute, V min For different risk levels i The element j The lower boundary value of the attribute risk indicator threshold, V max For different risk levels i The element j The upper boundary value of the attribute risk indicator threshold, k is a constant.

9. A multi-factor and multi-scale highway traffic operation risk assessment method as claimed in claim 5, characterized in that: The comprehensive certainty is calculated as follows: in, For the j Wi is the comprehensive certainty at the i-th level, and Wi is the combined weight of the i-th risk indicator.

10. A multi-factor and multi-scale highway traffic operation risk assessment device, characterized in that: It includes at least one processor and a memory that is communicatively connected to the at least one processor; the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a multi-factor and multi-scale highway traffic operation risk assessment method as described in any one of claims 1 to 9.

Images