Low-altitude flight risk assessment method and device, electronic equipment and storage medium

Abstract

The invention discloses a low-altitude flight risk assessment method and device, electronic equipment and a storage medium, and the method comprises the steps: determining an initial weight corresponding to a multi-level index in a multi-level risk index system, and the multi-level index comprises a comprehensive risk index, a multi-dimensional risk index and a basic risk source index; based on the current flight state information, adjusting an initial weight corresponding to the multi-level index to obtain a combined weight adaptive to the current flight environment; determining a target index from the multi-level indexes, and obtaining an original value associated with the target index; and performing risk assessment based on the original value and the combined weight to obtain a risk assessment result. According to the method, the risk index weight can be dynamically adjusted according to the current flight environment, and the real-time performance and accuracy of risk assessment are improved.

Description

Technical Field

[0001] This invention relates to the field of low-altitude flight technology, and in particular to a method, apparatus, electronic device, and storage medium for risk assessment of low-altitude flight. Background Technology

[0002] With the gradual opening of low-altitude airspace and the rapid development of drone technology, urban low-altitude aircraft are rapidly becoming more widespread in logistics, emergency rescue and other fields. However, low-altitude aircraft face many potential risk factors when operating in complex environments, such as building obstruction, electromagnetic interference, sudden weather changes, and high density of dynamic obstacles in dense areas, which can easily lead to flight safety issues. Therefore, it is necessary to conduct risk assessments on the flight status of low-altitude aircraft.

[0003] Traditional low-altitude flight risk assessment methods are closely coupled with application scenarios, making them unable to adapt to changes in the dynamic environment. They also have low accuracy in identifying potential environmental risks and cannot assess risks in a timely and accurate manner. Summary of the Invention

[0004] In view of the above problems, this application provides a risk assessment method for low-altitude flight, which can dynamically adjust the weight of risk indicators according to the current flight environment, thereby improving the real-time performance and accuracy of risk assessment.

[0005] Firstly, this application provides a risk assessment method for low-altitude flight. The method includes: determining the initial weights corresponding to the multi-level indicators in a multi-level risk indicator system, wherein the multi-level indicators include comprehensive risk indicators, multi-dimensional risk indicators, and basic risk source indicators; adjusting the initial weights corresponding to the multi-level indicators based on the current flight status information to obtain combined weights adapted to the current flight environment; determining the target indicator from the multi-level indicators and obtaining the original value associated with the target indicator; and conducting a risk assessment based on the original value and the combined weights to obtain the risk assessment result.

[0006] In the technical solution of this application embodiment, the initial weights corresponding to the multi-level indicators in the multi-level risk indicator system are first determined. Then, based on the current flight status information, the initial weights corresponding to the multi-level indicators are adjusted to obtain the combined weights adapted to the current flight environment. Next, the target indicator is determined from the multi-level indicators, and the original value associated with the target indicator is obtained. Based on the original value and the combined weights, a risk assessment is performed to obtain the risk assessment result. The risk indicator weights can be dynamically adjusted according to the current flight environment, thereby improving the real-time performance and accuracy of the risk assessment.

[0007] In some embodiments, the multi-dimensional risk indicators include at least one of technical risk indicators, environmental risk indicators, operational risk indicators, and management risk indicators, and each of these indicators corresponds to at least one basic risk source indicator. When the target indicator is a comprehensive risk indicator, the original value associated with the target indicator includes the original value corresponding to the basic risk source indicator. When the target indicator is any one of technical risk indicators, environmental risk indicators, operational risk indicators, and management risk indicators, this indicator corresponds to at least one basic risk source indicator, and the original value associated with the target indicator includes the original value corresponding to at least one basic risk source indicator.

[0008] In some embodiments, risk assessment is performed based on the original values ​​and combined weights to obtain risk assessment results, including: determining the comprehensive membership degree of the target indicator to the risk level based on the original values ​​and combined weights; and obtaining the risk assessment result of the target indicator if the comprehensive membership degree meets a first preset condition.

[0009] In some embodiments, determining the comprehensive membership degree of the target indicator to the risk level based on the original value and the combined weights includes: obtaining the preliminary membership degree of the target indicator to the risk level based on the original value and the gray cloud parameter of the risk level, wherein the gray cloud parameter includes at least one of expectation, entropy, and hyperentropy; and correcting the preliminary membership degree based on the combined weights to obtain the comprehensive membership degree of the target indicator to the risk level.

[0010] In some embodiments, the initial weights include subjective weights and objective weights; based on the current flight status information, the initial weights corresponding to the multi-level indicators are adjusted to obtain a combined weight adapted to the current flight environment, including: based on the current flight status information, adjusting the subjective and objective weights corresponding to the multi-level indicators; and obtaining the combined weights based on the adjusted subjective and objective weights.

[0011] In some embodiments, based on current flight status information, the subjective and objective weights corresponding to multi-level indicators are adjusted, including: comparing the importance of indicators at the same level pairwise based on multi-dimensional risk indicators and / or basic risk source indicators to obtain a judgment matrix for indicators at the same level; performing geometric mean processing and normalization processing on the judgment matrix to obtain a subjective weight vector; obtaining subjective weights based on the subjective weight vector; normalizing the original values ​​and obtaining the information entropy corresponding to the multi-level indicators based on the normalized original values; obtaining an objective weight vector based on the information entropy; and determining objective weights based on the objective weight vector.

[0012] In some embodiments, a combined weight is obtained based on the adjusted subjective weight and objective weight, including: normalizing the subjective weight and objective weight to obtain the initial weight; standardizing the original value and calculating the comprehensive grey relational degree of the corresponding multi-level indicators based on the standardized original value; and correcting the initial weight based on the comprehensive grey relational degree to obtain the combined weight.

[0013] On the other hand, this application provides a risk assessment device for low-altitude flight. The device includes: a determination module, used to determine the initial weights corresponding to the multi-level indicators in a multi-level risk indicator system, wherein the multi-level indicators include comprehensive risk indicators, multi-dimensional risk indicators, and basic risk source indicators; an adjustment module, used to adjust the initial weights corresponding to the multi-level indicators based on the current flight status information to obtain combined weights adapted to the current flight environment; an acquisition module, used to determine the target indicator from the multi-level indicators and acquire the original value associated with the target indicator; and an assessment module, used to perform risk assessment based on the original value and the combined weights to obtain the risk assessment result.

[0014] On the other hand, this application provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method of any of the above embodiments.

[0015] On the other hand, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method of any of the above embodiments.

[0016] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiments below. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0018] Figure 1 A flowchart of a risk assessment method for low-altitude flight according to an embodiment of this application is shown;

[0019] Figure 2 This paper illustrates a schematic diagram of the safety evaluation process for low-altitude flights in densely populated urban areas, according to an embodiment of this application.

[0020] Figure 3This paper illustrates a schematic diagram of the safety risk assessment index system for low-altitude flight in densely populated urban areas, as described in an embodiment of this application.

[0021] Figure 4 This paper illustrates a diagram showing the comparison of indicator weights in an embodiment of this application.

[0022] Figure 5 A schematic diagram of a comprehensive risk assessment according to an embodiment of this application is shown;

[0023] Figure 6 A block diagram of a low-altitude flight risk assessment device according to an embodiment of this application is shown;

[0024] Figure 7 A schematic diagram of an electronic device according to an embodiment of this application is shown. Detailed Implementation

[0025] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0027] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0028] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0029] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0030] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0031] In the description of the embodiments of this application, the technical terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0032] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0033] With the gradual opening of low-altitude airspace and the rapid development of drone technology, urban low-altitude aircraft are rapidly becoming more widespread in logistics, emergency rescue and other fields. However, low-altitude aircraft face many potential risk factors when operating in complex environments, such as building obstruction, electromagnetic interference, sudden weather changes, and high density of dynamic obstacles in dense areas, which can easily lead to flight safety issues. Therefore, it is necessary to conduct risk assessments on the flight status of low-altitude aircraft.

[0034] Traditional low-altitude flight risk assessment methods are closely coupled with application scenarios, making them unable to adapt to changes in the dynamic environment. They also have low accuracy in identifying potential environmental risks and cannot assess risks in a timely and accurate manner.

[0035] Traditional assessment methods rely on static weights (such as the experience of a single expert) and cannot dynamically respond to environmental changes, nor can they quantify uncertain impacts. Currently, the main risk assessment methods in engineering include: combined weight-fuzzy evaluation method; fuzzy Bayesian network method, etc.

[0036] The relevant technologies have the following main drawbacks:

[0037] (1) The weight allocation is singular and cannot adapt to changes in the dynamic environment.

[0038] The main reasons are: over-reliance on expert experience or purely data-driven approaches without integrating subjective and objective information; and the resulting combined weights are static and cannot adapt to changes in the dynamic environment.

[0039] (2) Insufficient quantification of uncertainty

[0040] The main reasons are: traditional methods, such as the combined weighting-fuzzy comprehensive evaluation method, only obtain the membership function through mathematical formulas, which is insufficient for handling uncertainty; while Bayesian network methods require preset probability distributions and cannot dynamically capture instantaneous disturbances.

[0041] (3) Weak dynamic adaptability

[0042] Main reason: Static models cannot reflect the impact of changes in external factors on the risk chain and the assessment of the overall risk level.

[0043] In view of this, this application proposes a risk assessment method for low-altitude flight, which can dynamically adjust the weights of risk indicators according to the current flight environment, thereby improving the real-time performance and accuracy of risk assessment.

[0044] In the technical solution of this application embodiment, the initial weights corresponding to the multi-level indicators in the multi-level risk indicator system are first determined. Then, based on the current flight status information, the initial weights corresponding to the multi-level indicators are adjusted to obtain the combined weights adapted to the current flight environment. Next, the target indicator is determined from the multi-level indicators, and the original value associated with the target indicator is obtained. Based on the original value and the combined weights, a risk assessment is performed to obtain the risk assessment result. The risk indicator weights can be dynamically adjusted according to the current flight environment, thereby improving the real-time performance and accuracy of the risk assessment.

[0045] Figure 1 A flowchart of a risk assessment method for low-altitude flight according to an embodiment of this application is shown.

[0046] like Figure 1 As shown, the low-altitude flight risk assessment method 100 provided in this application includes steps S110 to S140.

[0047] Step S110: Determine the initial weights of the multi-level indicators in the multi-level risk indicator system. The multi-level indicators include comprehensive risk indicators, multi-dimensional risk indicators, and basic risk source indicators.

[0048] For example, a multi-level risk indicator system can be constructed based on the following principles:

[0049] Systematic Principle: Low-altitude flight safety risk assessment involves numerous factors, primarily including risks across four dimensions: technology, environment, operation, and management. It should be ensured that indicators cover all core risk sources. Simultaneously, a three-tiered structure of "target layer - criterion layer - indicator layer" is adopted, progressively refining risk factors at each level. Specifically, the target layer can be, for example, a comprehensive risk level (comprehensive risk indicator), the criterion layer can correspond to a four-dimensional risk classification (multi-dimensional risk indicator), and the indicator layer can be specific, quantifiable risk sources (basic risk source indicators).

[0050] Scientific principle: The selected risk indicators should have clear physical meaning and measurability, avoiding subjective assumptions. At the same time, relying on historical accident data, real-time monitoring data, and expert experience ensures the objectivity and operability of the indicators.

[0051] Dynamism principle: For example, subjective and objective weights can be combined through a combination weighting method, and the weights of indicators can be dynamically adjusted in combination with changes in the environment. That is, the weights of the indicator system can be updated regularly according to new risk scenarios.

[0052] Practicality principle: The indicator system should conform to engineering practice, be concise and clear, and minimize overlap between indicators. At the same time, indicator data should be easily accessible, and each indicator should have a defined risk level threshold to support rapid decision-making.

[0053] Continuous improvement principle: Optimize indicator design through case verification and field testing.

[0054] Based on the above principles, a scientific risk indicator system (a multi-level risk indicator system) can be constructed. This system uses safety risk level as the target layer (first-level indicator, i.e., comprehensive risk indicator), the criterion layer (second-level indicator, i.e., multi-dimensional risk indicator) includes factors such as technical performance, environmental adaptability, operational standardization, and safety management, and the indicator layer covers risk source indicators (basic risk source indicators) based on the corresponding dimensions of the criterion layer. The initial weights corresponding to the multi-level indicators can include, for example, the subjective weights and objective weights of each indicator, and combine the subjective and objective weights to obtain a combined weight. It should be noted that the initial weights of each indicator refer to the weights of the criterion layer and the indicator layer, that is, the weights of each indicator in the multi-dimensional risk indicator and the basic risk source indicator. The comprehensive risk indicator mainly represents the comprehensive goal of risk assessment.

[0055] Step S120: Based on the current flight status information, adjust the initial weights corresponding to the multi-level indicators to obtain a combined weight that is suitable for the current flight environment.

[0056] For example, the current flight status information may include objective scenario information related to the current flight environment and safety risk factors, or flight data of the aircraft. For example, based on the current flight status information, the subjective weights and objective weights (initial weights) corresponding to the multi-level indicators can be adjusted, and the advantages of subjective and objective weights can be combined to obtain a combined weight that is suitable for the current flight environment.

[0057] Step S130: Determine the target indicator from the multi-level indicators and obtain the original value associated with the target indicator.

[0058] For example, the target indicator may represent any indicator determined from multiple levels of indicators as a risk assessment target, and the original value may include, for example, the measured value associated with the target indicator during a flight mission, which may be a real-time value or a historical value from a historical mission.

[0059] Step S140: Perform a risk assessment based on the original values ​​and combined weights to obtain the risk assessment results.

[0060] For example, risk assessment can be carried out by dynamically adjusting the combined weights of multi-level indicators based on the original values ​​associated with the target indicator, thereby strengthening the impact of important indicators on the risk level and obtaining the risk assessment result. The risk assessment result can be, for example, the risk level of the target indicator determined by assessing the target indicator against multiple risk levels.

[0061] In the technical solution of this application embodiment, the initial weights corresponding to the multi-level indicators in the multi-level risk indicator system are first determined. Then, based on the current flight status information, the initial weights corresponding to the multi-level indicators are adjusted to obtain the combined weights adapted to the current flight environment. Next, the target indicator is determined from the multi-level indicators, and the original value associated with the target indicator is obtained. Based on the original value and the combined weights, a risk assessment is performed to obtain the risk assessment result. The risk indicator weights can be dynamically adjusted according to the current flight environment, thereby improving the real-time performance and accuracy of the risk assessment.

[0062] In one example, the risk assessment method for low-altitude flight can be based on the principle of indicator system construction, to build a multi-level risk assessment indicator system, and to dynamically adjust the indicator weights based on the flight environment through a combination weighting method, and to dynamically quantify the uncertainty of risk through a gray cloud model, thereby calculating the comprehensive risk level. The following is a detailed explanation.

[0063] Figure 2 A schematic diagram of the safety evaluation process for low-altitude flight in densely populated urban areas, according to an embodiment of this application, is shown.

[0064] like Figure 2 As shown, the risk assessment for low-altitude flights in densely populated urban areas can be divided into three steps:

[0065] The first step is to construct a risk assessment indicator system. First, by identifying risk factors and selecting assessment indicators, an assessment indicator system is constructed, and the risk levels of these indicators are divided. For example, risk levels can be divided into three categories: low risk (Level I), medium risk (Level II), and high risk (Level III). Different risk ranges can be set by referring to past flight experience data.

[0066] The second step is to determine the combined weights of the evaluation indicators. Subjective weights are calculated using AHP (Analytic Hierarchy Process), which involves comparing the importance of each indicator at the same level to construct a judgment matrix, thereby calculating subjective weights and performing consistency checks. Objective weights are calculated using the entropy weight method, which involves standardizing the original data (original values) and then calculating the information entropy of each indicator to determine the entropy weights, thus obtaining the objective weights. Finally, the multiplicative integration method is used to combine the advantages of subjective and objective weights, resulting in a combined weight.

[0067] The third step is the safety risk assessment of the gray cloud model. First, the gray cloud parameters for the risk level are determined, then the membership matrix and the comprehensive gray relational degree are calculated, the combined weights are corrected, and the comprehensive risk membership degree is calculated based on the corrected combined weights and membership matrix, thereby obtaining the comprehensive risk rating.

[0068] The following provides a detailed explanation of each step in the above process, starting with... Figure 3 This paper describes an example of a multi-level risk indicator system and elaborates on the original values ​​associated with the target indicators based on the multi-level risk indicator system.

[0069] Figure 3 A schematic diagram of the safety risk assessment index system for low-altitude flight in densely populated urban areas, according to an embodiment of this application, is shown.

[0070] For example, such as Figure 3 As shown, the multi-dimensional risk indicators include at least one of the following: technical risk indicators, environmental risk indicators, operational risk indicators, and management risk indicators. Each of these indicators corresponds to at least one basic risk source indicator. When the target indicator is a comprehensive risk indicator, the original value associated with the target indicator includes the original value corresponding to the basic risk source indicator. When the target indicator is any one of the following: technical risk indicators, environmental risk indicators, operational risk indicators, and management risk indicators, that indicator corresponds to at least one basic risk source indicator, and the original value associated with the target indicator includes the original value corresponding to at least one basic risk source indicator.

[0071] Specifically, please refer to Figure 3 A multi-level risk indicator system can be divided into three layers: target layer (comprehensive risk indicators), criterion layer (multi-dimensional risk indicators), and indicator layer (basic risk source indicators). Comprehensive risk indicators may include, for example, the safety risk level of low-altitude flight in densely populated urban areas. Multi-dimensional risk indicators may include, for example, technical performance, environmental adaptability, operational standardization, and safety management. The indicator layer may include basic risk source indicators that refine the risk sources for each multi-dimensional risk indicator. For example, technical performance indicators could correspond to navigation and positioning accuracy, battery life degradation rate, communication link stability, sensor response latency, and hardware redundancy. Other multi-dimensional risk indicators are similar. Figure 3 As shown, each corresponds to at least one basic risk source indicator, which will not be elaborated here.

[0072] When the target indicator is a comprehensive risk indicator, i.e. when assessing the comprehensive risk level, the original values ​​associated with the risk factors based on the comprehensive risk indicator can include the original values ​​corresponding to all basic risk source indicators under the multi-dimensional risk indicators of the criteria layer. When the target indicator is any multi-dimensional risk indicator, such as when rating the risk of a technical performance indicator, the original values ​​associated with it can include the original values ​​corresponding to the basic risk source indicators of that indicator, i.e., the original values ​​of each indicator such as navigation and positioning accuracy, battery life attenuation rate, communication link stability, sensor response delay, and hardware redundancy. The method for corresponding the original values ​​of other indicators is similar and will not be elaborated here.

[0073] It should be noted that there can be multiple raw values ​​for each indicator, meaning that indicator measurements can be collected from multiple flight missions to improve the accuracy of risk assessment.

[0074] In the technical solution of this application embodiment, when the target indicator is determined to be a comprehensive risk indicator, the original value associated with the target indicator includes the original value corresponding to the basic risk source indicator. When the target indicator is any multi-dimensional risk indicator, the original value associated with the target indicator includes the original value corresponding to at least one basic risk source indicator. Thus, the measured values ​​of the current flight environment are collected based on a multi-level risk indicator system to conduct risk assessment, thereby improving the accuracy of risk level determination.

[0075] Next, based on the current environmental risks and aircraft data, the initial weights of the multi-level indicators are adjusted. For example, the subjective and objective weights of the multi-level indicators can be adjusted, thereby combining and assigning weights to the multi-level indicators based on the subjective and objective weights, resulting in combined weights. The following is a detailed explanation.

[0076] For example, the initial weights include subjective weights and objective weights; based on the current flight status information, the initial weights corresponding to the multi-level indicators are adjusted to obtain a combined weight that is adapted to the current flight environment. For example, firstly, based on the current flight status information, the subjective and objective weights corresponding to the multi-level indicators are adjusted; based on the adjusted subjective and objective weights, a combined weight is obtained.

[0077] First, we will explain how to calculate subjective weights and objective weights.

[0078] For example, based on the current flight status information, the subjective and objective weights corresponding to the multi-level indicators are adjusted. For instance, firstly, based on multi-dimensional risk indicators or basic risk source indicators, the importance of indicators at the same level is compared pairwise to obtain the judgment matrix of indicators at the same level; then, the judgment matrix is ​​processed by geometric mean and normalization to obtain the subjective weight vector; and finally, the subjective weight is obtained based on the subjective weight vector.

[0079] Specifically, the Analytic Hierarchy Process (AHP) was used to calculate subjective weights. To avoid the subjective influence of expert judgment, judgment matrices from 10 experts were collected and normalized using the geometric mean method. The main process is as follows:

[0080] ① Construct the judgment matrix

[0081] The importance of indicators at the same level in the criterion or indicator layer is compared pairwise using a 1-9 scale, where 1 indicates that two factors are equally important, and 9 indicates that one factor is significantly more important than the other. A judgment matrix A = (a ij ) n×n Satisfying: a ij =1 / a ji (i≠j), a ii =1, n is the index number, a ji This indicates the importance of the i-th indicator relative to the j-th indicator.

[0082] ② Weight Calculation and Consistency Check

[0083] a) Weight Calculation

[0084] The geometric mean method is used to solve for the eigenvectors, eliminating the influence of extreme values. The geometric mean of each row of the judgment matrix is ​​normalized to obtain the subjective weight vector. The subjective weight of each indicator is shown in formula (1):

[0085]

[0086] Where n is the number of indicators, and the denominator is the normalization coefficient, ensuring

[0087] b) Consistency check

[0088] To avoid logical contradictions in the judgment, it is necessary to calculate the largest eigenvalue λ of the judgment matrix. max The consistency ratio (CR) is used to verify the consistency of the matrix.

[0089] For example, the original values ​​are normalized, and the information entropy corresponding to the multi-level indicators is obtained based on the normalized original values; the objective weight vector is obtained based on the information entropy; and the objective weight is determined based on the objective weight vector.

[0090] Specifically, the entropy weight method is used to calculate the objective weights. After standardizing the original data (original values), the entropy weights are calculated; the main process is as follows:

[0091] ① Data standardization processing

[0092] Let the original data matrix be X = (x ij ) m×n Where m is the sample size (original index quantity), which refers to the frequency of flight mission-related indicators, and n is the number of indicators. To eliminate the influence of dimensions, range standardization is used to normalize the original values.

[0093] For positive indices, i.e., the larger the original value, the better, the normalized original value r... ij As in formula (2):

[0094]

[0095] For negative indices, i.e., the smaller the original value, the better, the normalized original value r ij As in formula (3):

[0096]

[0097] Where, r ij The original value after normalization, max x j Let x be the maximum original value of the j-th indicator. j x is the minimum original value of the j-th indicator. ij This is the original value.

[0098] ② Information entropy calculation

[0099] The information entropy e of the j-th indicator j It can be defined as formula (4):

[0100]

[0101] Among them, probability This represents the prior probability of the i-th sample value (original value) under the j-th indicator, when p ijWhen = 0, p is defined as follows: ij lnp ij =0, entropy value e j ∈[0,1], when all sample values ​​are exactly the same, e j =1, the data dispersion is the lowest, and the weight approaches 0.

[0102] ③ Determine the entropy weight

[0103] The objective weight vector can be calculated using entropy. The objective weight vector is shown in formula (5):

[0104]

[0105] Among them, 1-e j The coefficient of variation is the difference coefficient. The larger the value, the more information the indicator provides and the higher the weight allocation.

[0106] For example, based on the adjusted subjective and objective weights, a combined weight is obtained. For instance, firstly, the subjective and objective weights are normalized to obtain initial weights. Then, the original values ​​are standardized, and based on the standardized original values, the comprehensive grey relational degree of the corresponding multi-level indicators is calculated. Finally, based on the comprehensive grey relational degree, the initial weights are corrected to obtain the combined weight.

[0107] Specifically, the initial weights are calculated using the multiplicative ensemble method. The main process is as follows:

[0108] Based on the adjusted subjective and objective weights, a product normalization method is used for combined weighting to integrate the advantages of subjective and objective weights and increase the robustness of the risk assessment results, as shown in formula (6):

[0109]

[0110] in, Let j be the combined weight of the j-th indicator. Let j be the subjective weight of the j-th indicator. Let be the objective weight of the j-th indicator.

[0111] It should be noted that the initial weight can represent the historical combined weight obtained based on historical flight status information through subjective and objective weights. Therefore, the initial weight can be adjusted based on the current flight status information to obtain the current combined weight.

[0112] Figure 4 A schematic diagram showing the comparison of indicator weights in an embodiment of this application is illustrated.

[0113] like Figure 4As shown in the figure, the horizontal axis represents the basic risk source indicators, and the vertical axis represents the adjusted weights of the indicators. The blue bars represent the subjective weights of each indicator, the gray bars represent the objective weights of each indicator, and the orange bars represent the combined weights of each indicator based on a combination of subjective and objective weights.

[0114] In the technical solution of this application embodiment, for the current flight environment, based on multi-dimensional risk indicators or basic risk source indicators, pairwise importance comparisons are performed on indicators of the same level to obtain a judgment matrix for indicators of the same level. Then, the judgment matrix is ​​processed by geometric mean and normalization to obtain a subjective weight vector, thereby obtaining subjective weights. The original values ​​are normalized, and based on the normalized original values, the information entropy corresponding to the multi-level indicators is obtained. Then, based on the information entropy, an objective weight vector is obtained to determine the objective weights. The adjusted subjective weights and objective weights are combined to obtain the combined weights. Thus, the initial weights of the multi-level indicators are adjusted by combining expert experience and objective data, reducing the bias of a single weighting method and improving the rationality and robustness of weight allocation.

[0115] For example, based on the original values ​​and combined weights, the comprehensive membership degree of the target indicator to the risk level can be determined. For instance, firstly, based on the original values ​​and the gray cloud parameters of the risk level, the preliminary membership degree of the target indicator to the risk level is obtained, wherein the gray cloud parameters include at least one of expectation, entropy, and hyperentropy; then, based on the combined weights, the preliminary membership degree is corrected to obtain the comprehensive membership degree of the target indicator to the risk level.

[0116] Specifically, the uncertainty in risk assessment can be quantified using a gray cloud model, the impact of highly correlated indicators can be strengthened, and weights can be adjusted to improve the accuracy of risk assessment results. The main process is as follows:

[0117] a) Determination of gray cloud parameters for risk level.

[0118] Utilizing the constructed safety risk indicator system and risk classification, such as low risk (Level I), medium risk (Level II), and high risk (Level III), and based on the risk range of different levels [C] min C max ] Calculate the gray cloud parameters for each risk level to achieve risk rating for each indicator, as shown in formula (7):

[0119]

[0120] Where Ex is the expectation, En is the entropy, He is the hyperentropy, and C is the hyperentropy. min C represents the minimum value of the risk range. max The maximum value of the risk range is given by k, which is an empirical coefficient (usually 0.1 ≤ k ≤ 0.3), determined by the volatility of historical data.

[0121] a) Calculate the membership matrix of the index.

[0122] If the measured value (original value) of the j-th indicator is x j Calculate its membership degree μ for each risk level. jk (x) is used to determine which risk level the indicator is most likely to belong to. Taking a positive indicator as an example, its membership function (preliminary membership) is shown in formula (8):

[0123]

[0124] Where N is the number of Monte Carlo simulations, and k is the risk level (e.g., k can be 1, 2, or 3). The random entropy generated for the i-th simulation. Monte Carlo simulations can be performed by collecting measured values ​​from multiple tasks for each metric, allowing for simulation sampling and improving the accuracy of the simulation results. The number of simulations can be up to 1000.

[0125] A membership matrix can be constructed based on the membership degrees calculated from the original values ​​of each target indicator. Then, based on the combined weights, the initial membership degrees can be corrected to strengthen the influence of highly correlated indicators, thereby obtaining the comprehensive membership degree of the target indicator for the risk level.

[0126] In the technical solution of this application embodiment, the initial membership degree of the target indicator to the risk level is obtained based on the original value and the gray cloud parameters of the risk level. By introducing the hyperentropy parameter to generate the whitening weight function, the bandwidth of the membership function is dynamically adjusted, which can effectively quantify the fuzziness and randomness in risk assessment and enhance the adaptability of the gray cloud model. Then, based on the combined weight, the initial membership degree is corrected to obtain the comprehensive membership degree of the target indicator to the risk level. The combined weight is dynamically optimized to strengthen the influence of highly correlated indicators and improve the accuracy of risk assessment results.

[0127] For example, before calculating the comprehensive membership degree, the original values ​​are first standardized based on the initial weights, and the comprehensive grey relational degree of the corresponding multi-level indicators is calculated based on the standardized original values; then the initial weights are corrected based on the comprehensive grey relational degree to obtain the combined weights.

[0128] Specifically, the process of correcting the combined weights through grey relational analysis is as follows:

[0129] ① Construct a standardized decision matrix

[0130] The original value matrix associated with the target indicator is X = (x ij ) m×n Where m is the number of original values, n is the number of indicators (multi-level indicators, i.e., basic risk source indicators) corresponding to the original values, and x ijLet be the original value of the i-th sample on the j-th indicator. For each basic risk source indicator, the original values ​​can be collected from multiple tasks, i.e., m. The original value matrix is ​​standardized, and the standardized matrix is ​​denoted as Y = (y ij ) m×n , satisfy y ij ∈[[0,1] or y ij ∈[-1,1],y ij These are the original values ​​after standardization.

[0131] For the obtained standardized matrix, the maximum original value of each index is used to determine the positive ideal sequence. And determine the negative ideal sequence by taking the minimum original value of each indicator.

[0132] ② Calculate the grey relational coefficient

[0133] For each standardized raw value, calculate its distance from the positive ideal sequence and the negative ideal sequence to determine its similarity to the two sequences, as shown in formula (9):

[0134]

[0135] Where, γ ij ρ is the grey relational coefficient of the original value, and ρ is the resolution coefficient, ρ = 0.5.

[0136] ③ Calculate the comprehensive grey relational degree

[0137] Based on the grey relational coefficient of each indicator (all original values), the comprehensive grey relational degree is calculated to characterize the chain influence relationship between different indicators, as shown in formula (10):

[0138]

[0139] Among them, GRG j Let be the comprehensive grey relational degree of the j-th indicator.

[0140] ④ Dynamically adjust the combined weights

[0141] The combined weights are adjusted based on the comprehensive grey relational degree to enhance the impact of high-relational indicators on risk assessment, as shown in formula (11):

[0142] w j ′=w j ·(1+GRG j (11)

[0143] Among them, w j ′ represents the adjusted combined weight of the j-th indicator, w j Let be the combined weight of the j-th term.

[0144] The corrected combined weights are then normalized to obtain the normalized corrected combined weights. As shown in formula (12):

[0145]

[0146] In the technical solution of this application embodiment, real-time data is standardized, and the comprehensive grey relational degree of the corresponding multi-level indicators is calculated based on the original values ​​after standardization. Then, the combined weights are dynamically optimized based on the comprehensive grey relational degree to strengthen the influence of highly correlated indicators and improve the accuracy of risk chain propagation analysis, thereby improving the accuracy of comprehensive risk assessment.

[0147] For example, risk assessment is performed based on the original values ​​and combined weights to obtain risk assessment results. For instance, firstly, based on the original values ​​and combined weights, the comprehensive membership degree of the target indicator to the risk level is determined; then, if the comprehensive membership degree meets the first preset condition, the risk assessment result of the target indicator is obtained.

[0148] Specifically, for example, the target indicators can be comprehensively evaluated and graded based on their comprehensive membership degree, as follows:

[0149] ① Combining the corrected combined weights Membership degree μ with each basic risk source indicator jk Calculate the comprehensive membership degree u of the target indicator for each risk level. k As shown in formula (13):

[0150]

[0151] ② Risk Level Determination

[0152] Calculate the comprehensive membership degree of the target indicator at each risk level, such as the comprehensive membership degree at low risk (Level I), medium risk (Level II), and high risk (Level III). Based on the principle of maximum membership degree (first preset condition), the final risk level (risk assessment result) of the target indicator can be determined, as shown in formula (14):

[0153]

[0154] Among them, Risk Level is the risk level with the highest overall membership degree of the target indicator, that is, the target indicator has the highest probability of belonging to this risk level.

[0155] Figure 5 A schematic diagram illustrating a comprehensive risk assessment of an embodiment of this application is shown.

[0156] like Figure 5As shown, taking the target indicator of low-altitude flight safety risk level in densely populated urban areas as an example, the orange part in the figure represents the scoring probability (comprehensive membership degree) of the target indicator in low risk (Level I) with a value of 0.1077, the purple part represents the scoring probability of the target indicator in medium risk (Level II) with a value of 0.6778, and the blue part represents the scoring probability of the target indicator in high risk (Level III) with a value of 0.2405. According to the principle of maximum membership degree, the comprehensive level of low-altitude flight safety risk in densely populated urban areas can be determined to be medium risk (Level II).

[0157] In the technical solution of this application embodiment, the comprehensive membership degree of the target indicator with respect to the risk level is first determined based on the original value and combined weight. Then, when the comprehensive membership degree meets the first preset condition, the risk assessment result of the target indicator is obtained. Thus, by combining the comprehensive membership degree matrix and the maximum membership degree principle with environmental changes, the risk level of the target indicator is assessed and adjusted in real time to achieve the dynamism and real-time nature of risk assessment.

[0158] Next, the irreplaceable nature of the method in this application will be explained:

[0159] (1) Weight allocation method replacement

[0160] Fuzzy Hierarchical Analysis (FAHP): It can replace the traditional AHP and use fuzzy mathematics to handle the uncertainty of expert judgment. However, it relies on preset fuzzy membership functions, cannot dynamically integrate objective data, and is less adaptable than the combined weighting method of this scheme.

[0161] (2) Uncertainty quantification model replacement

[0162] Monte Carlo simulation: It simulates the probability distribution of risk through random sampling, but it has high computational complexity and relies on preset distribution assumptions. It cannot respond to dynamic changes in real time and is less flexible than the gray cloud model.

[0163] (3) Dynamic weight adjustment substitution

[0164] Neural network adaptive algorithms dynamically adjust weights through machine learning, but the model has poor interpretability and high training costs, making it difficult to meet the needs of rapid decision-making in engineering.

[0165] Figure 6 A block diagram of a low-altitude flight risk assessment device according to an embodiment of this application is shown.

[0166] This application provides a risk assessment device 600 for low-altitude flight, the device 600 including:

[0167] The determination module 610 is used to determine the initial weights corresponding to the multi-level indicators in the multi-level risk indicator system. The multi-level indicators include comprehensive risk indicators, multi-dimensional risk indicators, and basic risk source indicators.

[0168] The adjustment module 620 is used to adjust the initial weights of multi-level indicators based on the current flight status information to obtain a combined weight that is suitable for the current flight environment.

[0169] The acquisition module 630 is used to determine the target indicator from the multi-level indicators and obtain the raw value associated with the target indicator.

[0170] The assessment module 640 is used to perform risk assessment based on the original values ​​and combined weights to obtain the risk assessment results.

[0171] For example, the multi-dimensional risk indicators include at least one of the following: technical risk indicators, environmental risk indicators, operational risk indicators, and management risk indicators. Each of these indicators corresponds to at least one basic risk source indicator. When the target indicator is a comprehensive risk indicator, the original value associated with the target indicator includes the original value corresponding to the basic risk source indicator. When the target indicator is any one of the following: technical risk indicators, environmental risk indicators, operational risk indicators, and management risk indicators, this indicator corresponds to at least one basic risk source indicator, and the original value associated with the target indicator includes the original value corresponding to at least one basic risk source indicator.

[0172] For example, the assessment module 640 is further configured to: determine the comprehensive membership degree of the target indicator to the risk level based on the original value and the combined weight; and obtain the risk assessment result of the target indicator if the comprehensive membership degree meets the first preset condition.

[0173] For example, determining the comprehensive membership degree of the target indicator to the risk level based on the original value and the combined weight includes: obtaining the preliminary membership degree of the target indicator to the risk level based on the original value and the gray cloud parameter of the risk level, wherein the gray cloud parameter includes at least one of expectation, entropy, and hyperentropy; and correcting the preliminary membership degree based on the combined weight to obtain the comprehensive membership degree of the target indicator to the risk level.

[0174] For example, the initial weights include subjective weights and objective weights; the adjustment module 620 is also used to: adjust the subjective weights and objective weights corresponding to the multi-level indicators based on the current flight status information; and obtain the combined weights based on the adjusted subjective weights and objective weights.

[0175] For example, based on the current flight status information, the subjective and objective weights corresponding to multi-level indicators are adjusted, including: comparing the importance of each indicator at the same level based on multi-dimensional risk indicators and / or basic risk source indicators to obtain a judgment matrix for the same level indicators; performing geometric mean processing and normalization processing on the judgment matrix to obtain a subjective weight vector; obtaining the subjective weight based on the subjective weight vector; normalizing the original values ​​and obtaining the information entropy corresponding to the multi-level indicators based on the normalized original values; obtaining the objective weight vector based on the information entropy; and determining the objective weight based on the objective weight vector.

[0176] For example, based on the adjusted subjective weights and objective weights, a combined weight is obtained, including: normalizing the subjective weights and objective weights to obtain initial weights; standardizing the original values ​​and calculating the comprehensive grey relational degree of the corresponding multi-level indicators based on the standardized original values; and correcting the initial weights based on the comprehensive grey relational degree to obtain the combined weight.

[0177] Figure 7 A schematic diagram of an electronic device according to an embodiment of this application is shown.

[0178] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method in any of the above embodiments.

[0179] like Figure 7 As shown, for ease of understanding, an embodiment of this application illustrates a specific electronic device 700.

[0180] Electronic device 700 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 700 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0181] like Figure 7As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 702 or a computer program loaded from storage unit 708 into random access memory (RAM) 703. RAM 703 may also store various programs and data required for the operation of electronic device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 504. Input / output (I / O) interface 705 is also connected to bus 704.

[0182] Multiple components in electronic device 700 are connected to I / O interface 705. These components include: input unit 706, such as a keyboard or mouse; output unit 707, such as various types of displays or speakers; storage unit 708, such as a disk or optical disk; and communication unit 709, such as a network interface card (NIC), modem, or wireless transceiver. Communication unit 709 allows electronic device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0183] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods described above. For example, in some embodiments, any one or more of the methods described above can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of any one or more of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform any one or more of the methods described above by any other suitable means (e.g., by means of firmware).

[0184] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method in any of the above embodiments.

[0185] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this application, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0186] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0187] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no structural conflict, the various technical features mentioned in the embodiments can be combined in any way. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A risk assessment method for low-altitude flight, characterized in that, The method includes: Determine the initial weights corresponding to the multi-level indicators in the multi-level risk indicator system, wherein the multi-level indicators include comprehensive risk indicators, multi-dimensional risk indicators and basic risk source indicators; Based on the current flight status information, the initial weights corresponding to the multi-level indicators are adjusted to obtain a combined weight that is suitable for the current flight environment. The target indicator is determined from the multi-level indicators, and the original value associated with the target indicator is obtained; Risk assessment is performed based on the original values ​​and the combined weights to obtain the risk assessment results.

2. The risk assessment method for low-altitude flight according to claim 1, characterized in that, The multi-dimensional risk indicators include at least one of the following: technical risk indicators, environmental risk indicators, operational risk indicators, and management risk indicators. Each of the following indicators corresponds to at least one basic risk source indicator. When the target indicator is the comprehensive risk indicator, the original value associated with the target indicator includes the original value corresponding to the basic risk source indicator; When the target indicator is any one of the technical risk indicator, the environmental risk indicator, the operational risk indicator, and the management risk indicator, each of these indicators corresponds to at least one basic risk source indicator, and the original value associated with the target indicator includes the original value corresponding to the at least one basic risk source indicator.

3. The risk assessment method for low-altitude flight according to claim 1, characterized in that, The risk assessment based on the original value and the combined weights, to obtain the risk assessment result, includes: Based on the original values ​​and the combined weights, the comprehensive membership degree of the target indicator with respect to the risk level is determined; When the comprehensive membership degree meets the first preset condition, the risk assessment result of the target indicator is obtained.

4. The risk assessment method for low-altitude flight according to claim 3, characterized in that, The determination of the comprehensive membership degree of the target indicator to the risk level based on the original value and the combined weight includes: Based on the original value and the gray cloud parameter of the risk level, the preliminary membership degree of the target indicator to the risk level is obtained, wherein the gray cloud parameter includes at least one of expectation, entropy, and hyperentropy. Based on the combined weights, the initial membership degree is corrected to obtain the comprehensive membership degree of the target indicator for the risk level.

5. The risk assessment method for low-altitude flight according to claim 1, characterized in that, The initial weights include subjective weights and objective weights; The step of adjusting the initial weights corresponding to the multi-level indicators based on the current flight status information to obtain a combined weight adapted to the current flight environment includes: Based on the current flight status information, adjust the subjective weights and objective weights corresponding to the multi-level indicators; The combined weight is obtained based on the adjusted subjective weight and the objective weight.

6. The risk assessment method for low-altitude flight according to claim 5, characterized in that, Based on the current flight status information, adjust the subjective weights and objective weights corresponding to the multi-level indicators, including: Based on the multi-dimensional risk indicators and / or the basic risk source indicators, pairwise importance comparisons are performed on indicators at the same level to obtain the judgment matrix of the indicators at the same level. The judgment matrix is ​​subjected to geometric averaging and normalization to obtain the subjective weight vector; The subjective weights are obtained based on the subjective weight vector. The original values ​​are normalized, and the information entropy corresponding to the multi-level indicators is obtained based on the normalized original values. Based on the information entropy, an objective weight vector is obtained; The objective weights are determined based on the objective weight vector.

7. The risk assessment method for low-altitude flight according to claim 6, characterized in that, Based on the adjusted subjective weights and objective weights, the combined weights are obtained, including: The subjective weights and the objective weights are normalized to obtain the initial weights; The original values ​​are standardized, and the comprehensive grey relational degree of the corresponding multi-level indicators is calculated based on the standardized original values. Based on the comprehensive grey relational degree, the initial weights are corrected to obtain the combined weights.

8. A risk assessment device for low-altitude flight, characterized in that, The device includes: The determination module is used to determine the initial weights corresponding to the multi-level indicators in the multi-level risk indicator system, wherein the multi-level indicators include comprehensive risk indicators, multi-dimensional risk indicators and basic risk source indicators; The adjustment module is used to adjust the initial weights corresponding to the multi-level indicators based on the current flight status information, so as to obtain a combined weight that is adapted to the current flight environment. The acquisition module is used to determine the target indicator from the multi-level indicators and acquire the original value associated with the target indicator; The assessment module is used to perform risk assessment based on the original values ​​and the combined weights to obtain the risk assessment results.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images