A method for constructing a flight risk assessment model
By building a flight risk assessment model, obtaining the risk assessment index system and matrix, establishing a hierarchical structure, and determining the impact relationship between the human risk factors of dispatched personnel, it solves the complexity of the human risk assessment of dispatched personnel in aviation safety, and realizes the aviation safety effective control.
Patent Information
- Application Number
- CN202411368693.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2024-12-20
- Estimated Expiration
- 2044-09-29
AI Technical Summary
The prior art is difficult to effectively evaluate and control the human risk factors of dispatched personnel in aviation safety, resulting in an increase in aviation safety incidents.
By building a flight risk assessment model, obtaining a risk assessment index system, building a risk relationship assessment matrix, normalizing and standardizing, establishing a hierarchical structure, determining the flight risk assessment set and reachable matrix, establishing a multi-level risk transition model, and detecting and improving measure.
It realizes an accurate assessment of the human risk factors of dispatched personnel, reduces aviation safety issues, provides a risk control strategy, and is suitable for complex flight systems.
Smart Images
Figure CN118863557B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and in particular to a method for constructing a flight risk assessment model. Background Art
[0002] At present, in the face of the continuous expansion of the number of aircraft and the scale of routes, the increasing airspace tension and the increasingly complex operating environment, flight dispatchers, as the core personnel of aviation operation control, are subject to more and more interference factors, and the rate of unsafe incidents caused by unsafe human behavior is increasing. As the core of airline operation risk control, dispatchers are an important part of ensuring aviation safety. They play an irreplaceable and important role in complex flight systems. The human factors of dispatchers directly determine the operational safety status of civil aviation flights. Therefore, how to objectively and accurately evaluate the human risk factors of dispatchers and provide risk control strategies to reduce aviation safety issues is a problem that needs to be solved urgently. Summary of the invention
[0003] The purpose of the present invention is to provide a method and system for constructing a flight risk assessment model to solve the above-mentioned problems existing in the prior art.
[0004] In a first aspect, an embodiment of the present invention provides a method for constructing a flight risk assessment model, comprising:
[0005] Obtaining a risk assessment indicator system; constructing a risk relationship evaluation matrix according to the risk assessment indicator system; the risk assessment indicator system is a structure including multiple risk assessment indicators constructed through human factor analysis and classification system model; the risk relationship evaluation matrix is used to determine the mutual influence relationship between multiple risk assessment indicators in the risk assessment indicator system;
[0006] The risk relationship evaluation matrix is normalized and standardized to obtain the standardized hesitant fuzzy direct influence matrix;
[0007] Based on the normalized hesitant fuzzy direct impact matrix, a hierarchical structure stage is constructed to obtain a flight risk assessment set; the flight risk assessment set includes a flight risk impact degree, a flight risk affected degree, a flight risk intermediate degree, and a flight risk cause degree;
[0008] Based on the normalized hesitant fuzzy direct influence matrix, a flight risk reachability matrix is obtained; the flight risk reachability matrix represents a matrix that limits the degree of mutual influence between risk assessment indicators;
[0009] Based on the flight risk reachability matrix, the relationship between multiple risk assessment indicators is found to obtain a multi-level hierarchical risk model;
[0010] According to the flight risk assessment set and the risk multi-level hierarchical model, corresponding improvement measures are detected and improvement measure signals are sent.
[0011] Optionally, the relationship between multiple risk assessment indicators is found based on the flight risk reachability matrix to obtain a multi-level hierarchical risk model, including:
[0012] Based on the flight risk reachability matrix, performing inter-level division to obtain multiple flight risk reachability sets;
[0013] Based on the flight risk reachable matrix, inter-level division is performed to obtain multiple flight risk prior sets; one risk assessment indicator corresponds to one flight risk reachable set and one flight risk prior set;
[0014] The flight risk reachable set and the flight risk antecedent set corresponding to the same flight risk reachable set are intersected to obtain a repeated impact set; the values in the repeated impact set represent risk assessment indicators that affect other risk assessment indicators and are affected by other risk assessment indicators;
[0015] If the repeated impact set is the same as the flight risk reachable set, marking the risk assessment indicator corresponding to the flight risk reachable set to obtain a first marked risk assessment indicator;
[0016] The values of a row and a column corresponding to the risk assessment index corresponding to the flight risk reachable set in the flight risk reachable matrix are set to 0 to obtain a new flight risk reachable matrix;
[0017] Repeat the flight risk reachability matrix and arrange the risk assessment indicators in the order of testing to obtain a risk arrangement set;
[0018] According to the risk arrangement set and the first marked risk assessment index, hierarchical decomposition is performed to obtain a risk multi-level hierarchical model.
[0019] Optionally, the hierarchical structure stage is constructed based on the normalized hesitant fuzzy direct impact matrix to obtain a flight risk assessment set, including:
[0020] Each row of the normalized hesitant fuzzy direct influence matrix is added, and the influence of the risk assessment index corresponding to each row on other risk assessment indexes is detected to obtain the flight risk influence degree;
[0021] Each column of the normalized hesitant fuzzy direct influence matrix is added, and the influence of other risk assessment indicators on the risk assessment indicator corresponding to each column is detected to obtain the flight risk influence degree;
[0022] Based on the flight risk influence degree and the flight risk influenced degree, the flight risk centrality and the flight risk cause degree are obtained.
[0023] Optionally, obtaining a flight risk reachability matrix based on the normalized hesitant fuzzy direct impact matrix includes:
[0024] The normalized hesitant fuzzy direct impact matrix is added to the unit matrix to obtain the flight risk overall impact matrix; the flight risk overall impact matrix increases the impact of the risk assessment index reaching and receiving the same risk assessment index;
[0025] If the value in the flight risk overall impact matrix is greater than the overall impact threshold, the value in the flight risk overall impact matrix is set to 1; if the value in the flight risk overall impact matrix is less than or equal to the overall impact threshold, the value in the flight risk overall impact matrix is set to 0 to obtain the flight risk reachable matrix.
[0026] Optionally, the flight risk reachability matrix is divided into different levels to obtain a plurality of flight risk reachability sets, including:
[0027] Obtain the value of each row in the flight risk reachable matrix to obtain multiple first flight risk reachable sets; a row in the first flight risk reachable matrix corresponds to one first flight risk reachable set;
[0028] Obtaining a risk assessment indicator corresponding to a value not equal to 0 in the first flight risk reachable set as a reachable risk assessment indicator;
[0029] A flight risk reachable set is constructed by taking multiple reachable risk assessment indicators as elements.
[0030] Optionally, the flight risk reachability matrix is divided into different levels to obtain a plurality of flight risk precedent sets, including:
[0031] Obtain the value of each column in the flight risk reachable matrix to obtain multiple first flight risk advance sets; one column in the first flight risk reachable matrix corresponds to one first flight risk advance set;
[0032] Obtaining a risk assessment indicator corresponding to a value not equal to 0 in the first flight risk reachable set as a prior risk assessment indicator;
[0033] A flight risk advance set is constructed using multiple advance risk assessment indicators as elements.
[0034] Optionally, obtaining the flight risk centrality and the flight risk cause degree based on the flight risk influence degree and the flight risk influenced degree includes:
[0035] The flight risk influence degree is added to the flight risk influence degree to obtain the flight risk centrality; the flight risk centrality is used to indicate the importance of the risk assessment index in the entire risk assessment index system;
[0036] The flight risk cause degree is obtained by subtracting the flight risk impact degree from the flight risk impact degree.
[0037] Optionally, if the flight risk cause degree is greater than 0, the corresponding risk assessment indicator is used as the cause risk assessment indicator; the cause risk assessment indicator indicates that the risk assessment indicator has an impact on other risk assessment indicators;
[0038] If the flight risk cause degree is less than 0, the corresponding risk assessment indicator is used as the result risk assessment indicator; the result risk assessment indicator indicates the influence of other risk assessment indicators.
[0039] Optionally, the risk relationship evaluation matrix is normalized and standardized to obtain a standardized hesitant fuzzy direct influence matrix, including:
[0040] Normalize the risk relationship evaluation matrix to obtain the normalized hesitant fuzzy direct influence matrix;
[0041] The hesitant fuzzy direct influence matrix is normalized to obtain the normalized hesitant fuzzy direct influence matrix.
[0042] Optionally, detecting corresponding improvement measures according to the flight risk assessment set and the risk multi-level hierarchical model, and sending an improvement measure signal includes:
[0043] Obtaining a user surface risk indicator; the user surface risk indicator is an indicator of the risk of the user;
[0044] Find multiple user deep risk indicators corresponding to the user surface risk indicators according to the risk multi-level hierarchical model;
[0045] According to the flight risk assessment set, multiple user causal risk indicators having an influencing relationship with the user surface risk indicators are found;
[0046] According to the multiple user deep risk indicators and the multiple user causal risk indicators, the corresponding improvement measure numbers are found, and the improvement measure numbers are sent.
[0047] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects:
[0048] The embodiment of the present invention also provides a method for constructing a flight risk assessment model, the method comprising: obtaining a risk assessment indicator system; constructing a risk relationship evaluation matrix according to the risk assessment indicator system; the risk assessment indicator system is a structure including multiple risk assessment indicators constructed by human factor analysis and classification system model; the risk relationship evaluation matrix is used to determine the mutual influence relationship between multiple risk assessment indicators in the risk assessment indicator system; normalizing and normalizing the risk relationship evaluation matrix to obtain a normalized hesitant fuzzy direct influence matrix; based on the normalized hesitant fuzzy direct influence matrix, constructing a hierarchical structure stage to obtain a flight risk assessment set; the flight risk assessment set includes a flight risk influence degree, a flight risk affected degree, a flight risk intermediate degree and a flight risk cause degree; based on the normalized hesitant fuzzy direct influence matrix, obtaining a flight risk reachable matrix; the flight risk reachable matrix represents a matrix with a large degree of mutual influence between restricted risk assessment indicators; based on the flight risk reachable matrix, finding the relationship between multiple risk assessment indicators to obtain a risk multi-level hierarchical model; according to the flight risk assessment set and the risk multi-level hierarchical model, detecting corresponding improvement measures and sending improvement measures signals.
[0049] In the present invention, the causal relationship between multiple risk assessment indicators and the influence and affected state of each risk assessment indicator in the risk assessment indicator system are determined, and a multi-level hierarchical model of risk is set to detect the unclear relationship between multiple risk assessment indicators and transform it into a clear and visible hierarchical structure. It is particularly suitable for analysis such as the risk assessment of dispatchers, which has many variables, complex relationships and unclear structures. It can not only determine the influence relationship strength between the risk factors of dispatchers at a micro perspective, but also sort out the hierarchical relationship of the influence of the risk factors of dispatchers at a macro perspective. In this way, the risk factors of dispatchers can be evaluated more accurately, achieving the technical effect of reducing aviation safety issues. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] Figure 1 The present invention provides a flowchart of a method for constructing a flight risk assessment model.
[0051] Figure 2 It is a structural schematic diagram of a risk assessment index system in a flight risk assessment model construction method provided by an embodiment of the present invention.
[0052] Figure 3 It is a structural schematic diagram of a risk multi-level hierarchical model in a flight risk assessment model construction method provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0053] The present invention will be described in detail below in conjunction with the accompanying drawings.
[0054] Example
[0055] like Figure 1 As shown, an embodiment of the present invention provides a method for constructing a flight risk assessment model, the method comprising:
[0056] S101: Acquire a risk assessment indicator system; construct a risk relationship evaluation matrix according to the risk assessment indicator system; the risk assessment indicator system is a structure including multiple risk assessment indicators constructed through human factor analysis and classification system model; the risk relationship evaluation matrix is used to determine the mutual influence relationship between multiple risk assessment indicators in the risk assessment indicator system.
[0057] Among them, the risk assessment indicator system is as follows: Figure 2 As shown, the risk assessment index represents an index for evaluating the human actions of the flight dispatcher. Represents risk assessment indicators, such as The dispatcher's professional knowledge level is insufficient. Indicates that an item on the test sheet is missing.
[0058] The value of the first column of the second row of the risk relationship evaluation matrix is 0.75, indicating that right The influence degree is 0.75, that is, the influence degree of insufficient professional knowledge of the dispatcher on missing items on the inspection list is 0.75.
[0059] Among them, the Human Factors Analysis and Classification System (HFACS) model.
[0060] S102: Normalize and standardize the risk relationship evaluation matrix to obtain a standardized hesitant fuzzy direct influence matrix.
[0061] The normalized hesitant fuzzy direct impact matrix is used to comprehensively judge the direct impact and indirect impact of each factor in the risk assessment index system.
[0062] The values in the normalized hesitant fuzzy direct impact matrix represent the impact and related relationships among multiple risk assessment indicators.
[0063] S103: Based on the normalized hesitant fuzzy direct impact matrix, a hierarchical structure stage is constructed to obtain a flight risk assessment set; the flight risk assessment set includes a flight risk impact degree, a flight risk affected degree, a flight risk intermediate degree, and a flight risk cause degree.
[0064] S104: Based on the normalized hesitant fuzzy direct influence matrix, a flight risk reachability matrix is obtained; the flight risk reachability matrix represents a matrix that limits the degree of mutual influence between risk assessment indicators.
[0065] The flight risk reachability matrix uses an overall impact threshold to limit the degree of mutual influence between risk assessment indicators.
[0066] S105: Based on the flight risk reachability matrix, find the relationship between multiple risk assessment indicators to obtain a risk multi-level hierarchical model.
[0067] The risk multi-level hierarchical model is as follows: Figure 3 shown. express Figure 2 The risk assessment indicators described. For the first layer, For the second layer, For the third layer, For the fourth floor, It is the 5th floor. Represents the root layer, Represents the middle layer, Indicates the surface.
[0068] S106: Detect corresponding improvement measures according to the flight risk assessment set and the risk multi-level hierarchical model, and send an improvement measure signal.
[0069] Optionally, the relationship between multiple risk assessment indicators is found based on the flight risk reachability matrix to obtain a risk multi-level recursive order model, including:
[0070] Based on the flight risk reachability matrix, performing inter-level division to obtain multiple flight risk reachability sets;
[0071] Based on the flight risk reachable matrix, inter-level division is performed to obtain multiple flight risk advance sets; one risk assessment indicator corresponds to one flight risk reachable set and one flight risk advance set.
[0072] The flight risk reachable set and the flight risk antecedent set corresponding to the same flight risk reachable set are intersected to obtain a repeated impact set; the values in the repeated impact set represent risk assessment indicators that affect other risk assessment indicators and are affected by other risk assessment indicators;
[0073] If the repeated impact set is the same as the flight risk reachable set, the risk assessment index corresponding to the flight risk reachable set is marked to obtain the highest risk assessment index.
[0074] The highest risk assessment indicator indicates a risk assessment indicator whose influence degree by other risk assessment indicators is less than the influence threshold and whose influence degree on other risk assessment indicators is greater than the influence threshold. In this embodiment, the influence threshold is 0.25 and the influence threshold is 0.75.
[0075] The values of a row and a column corresponding to the risk assessment index corresponding to the flight risk reachable set in the flight risk reachable matrix are set to 0 to obtain a new flight risk reachable matrix;
[0076] Repeat the flight risk reachability matrix and arrange the risk assessment indicators in the order of testing to obtain a risk arrangement set;
[0077] According to the risk arrangement set and the first marked risk assessment index, hierarchical decomposition is performed to obtain a risk multi-level hierarchical model.
[0078] The highest risk assessment index is used as the root layer, and is sorted according to the sorting order in the risk arrangement set, and the remaining elements are analyzed until all elements are assigned to the corresponding levels. In this embodiment, the classification is performed by determining the number of overlaps between the repeated impact set and the wind direction flight risk reachable set.
[0079] Optionally, the hierarchical structure stage is constructed based on the normalized hesitant fuzzy direct impact matrix to obtain a flight risk assessment set, including:
[0080] Each row of the normalized hesitant fuzzy direct influence matrix is added, and the influence of the risk assessment index corresponding to each row on other risk assessment indexes is detected to obtain the flight risk influence degree.
[0081] The calculation method of the flight risk impact degree is as follows:
[0082]
[0083] Among them, the Indicates the flight risk impact, To normalize the hesitant fuzziness directly affects the numbering of the rows of the matrix, is the index of the column of the normalized hesitant fuzzy direct influence matrix, n represents the number of rows of the normalized hesitant fuzzy direct influence matrix, represents the normalized hesitant fuzzy direct influence matrix.
[0084] Each column of the normalized hesitant fuzzy direct influence matrix is added, and the influence of other risk assessment indicators on the risk assessment indicator corresponding to each column is detected to obtain the flight risk influence degree.
[0085] The calculation method of the flight risk impact degree is as follows:
[0086]
[0087] Among them, the Indicates the degree to which flight risk is affected. To normalize the hesitant fuzziness directly affects the numbering of the rows of the matrix, is the index of the column of the normalized hesitant fuzzy direct influence matrix, n represents the number of rows of the normalized hesitant fuzzy direct influence matrix, represents the normalized hesitant fuzzy direct influence matrix.
[0088] Optionally, obtaining a flight risk overall impact matrix and a flight risk reachability matrix based on the normalized hesitant fuzzy direct impact matrix includes:
[0089] The normalized hesitant fuzzy direct impact matrix is added to the unit matrix to obtain the flight risk overall impact matrix; the flight risk overall impact matrix increases the impact of risk assessment indicators reaching and receiving the same risk assessment indicators.
[0090] The overall impact matrix of flight risk is shown in the following method:
[0091] H = I + T
[0092] Wherein, H represents the flight risk overall impact matrix, I represents the unit matrix, and T represents the normalized hesitant fuzzy direct impact matrix. The unit matrix represents a matrix in which the values of the elements on the main diagonal are all 1, and the values of the elements at other positions are all 0. The size of the unit matrix is equal to the size of the normalized hesitant fuzzy direct impact matrix, which is equal to the overall impact matrix.
[0093] If the value in the flight risk overall impact matrix is greater than the overall impact threshold, the value in the flight risk overall impact matrix is set to 1; if the value in the flight risk overall impact matrix is less than or equal to the overall impact threshold, the value in the flight risk overall impact matrix is set to 0 to obtain the flight risk reachable matrix.
[0094] The flight risk reachability matrix represents a matrix after removing risk assessment indicators whose impact is less than that of other risk assessment indicators.
[0095] In this embodiment, the overall impact threshold is 0.01.
[0096] Optionally, the flight risk reachability matrix is divided into different levels to obtain a plurality of flight risk reachability sets, including:
[0097] Obtain the value of each row in the flight risk reachable matrix to obtain multiple first flight risk reachable sets; a row in the first flight risk reachable matrix corresponds to one first flight risk reachable set;
[0098] Obtaining a risk assessment indicator corresponding to a value not equal to 0 in the first flight risk reachable set as a reachable risk assessment indicator;
[0099] A flight risk reachable set is constructed by taking multiple reachable risk assessment indicators as elements;
[0100] Optionally, the flight risk reachability matrix is divided into different levels to obtain a plurality of flight risk precedent sets, including:
[0101] Obtain the value of each column in the flight risk reachable matrix to obtain multiple first flight risk advance sets; one column in the first flight risk reachable matrix corresponds to one first flight risk advance set;
[0102] Obtaining a risk assessment indicator corresponding to a value not equal to 0 in the first flight risk reachable set as a prior risk assessment indicator;
[0103] A flight risk advance set is constructed using multiple advance risk assessment indicators as elements.
[0104] Optionally, obtaining the flight risk centrality and the flight risk cause degree based on the flight risk influence degree and the flight risk influenced degree includes:
[0105] The flight risk centrality is obtained by adding the flight risk influence degree to the flight risk influence degree. The flight risk centrality is used to indicate the importance of the risk assessment index in the entire risk assessment index system.
[0106] The calculation method of the flight risk centrality is as follows:
[0107]
[0108] Among them, the represents the flight risk centrality, The row numbers of the normalized hesitant fuzzy direct influence matrix are used to represent the risk assessment index. Indicates the flight risk impact, It represents the impact degree of flight risk, n is the number of rows of the normalized hesitant fuzzy direct impact matrix, and represents the number of risk assessment indicators.
[0109] The flight risk centrality includes a comprehensive judgment of the flight risk influence and the flight risk influence.
[0110] The flight risk cause degree is obtained by subtracting the flight risk impact degree from the flight risk impact degree.
[0111] The calculation method of the flight risk cause degree is as follows:
[0112]
[0113] Among them, the Indicates the degree of flight risk cause, The row numbers of the normalized hesitant fuzzy direct influence matrix are used to represent the risk assessment index. Indicates the flight risk impact, It represents the impact degree of flight risk, n is the number of rows of the normalized hesitant fuzzy direct impact matrix, and represents the number of risk assessment indicators.
[0114] Optionally, if the flight risk cause degree is greater than 0, the corresponding risk assessment indicator is used as the cause risk assessment indicator; the cause risk assessment indicator indicates that the risk assessment indicator has an impact on other risk assessment indicators.
[0115] If the flight risk cause degree is less than 0, the corresponding risk assessment indicator is used as the result risk assessment indicator; the result risk assessment indicator indicates the influence of other risk assessment indicators.
[0116] Optionally, the risk relationship evaluation matrix is normalized and standardized to obtain a standardized hesitant fuzzy direct influence matrix, including:
[0117] The risk relationship evaluation matrix is normalized to obtain the normalized hesitant fuzzy direct influence matrix.
[0118] In this embodiment, the HFWA operator is used for normalization to obtain the hesitant fuzzy direct influence matrix.
[0119] The hesitant fuzzy direct influence matrix is normalized to obtain the normalized hesitant fuzzy direct influence matrix.
[0120] Among them, the hesitant fuzzy direct influence matrix is normalized by the following method:
[0121]
[0122] in, represents a normalized hesitant fuzzy direct influence matrix with n rows and n columns, where n is a natural number greater than 0. Indicates that the normalized hesitant fuzzy directly affects the first Line The value of the column, It means that the hesitant fuzziness directly affects the value of the i-th row and j-th column in the matrix.
[0123] in, , and is a natural number.
[0124] Optionally, the obtaining of a user surface risk indicator; the user surface risk indicator is an indicator of risk for the user;
[0125] Find multiple user deep risk indicators corresponding to the user surface risk indicators according to the risk multi-level hierarchical model;
[0126] According to the flight risk assessment set, multiple user causal risk indicators having an influencing relationship with the user surface risk indicators are found;
[0127] According to the multiple user deep risk indicators and the multiple user causal risk indicators, the corresponding improvement measure numbers are found, and the improvement measure numbers are sent.
[0128] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages can be utilized to realize the content of the present invention described herein, and the description of the above specific languages is for disclosing the best mode of the present invention.
[0129] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.
[0130] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the apparatus according to an embodiment of the present invention. The present invention may also be implemented as a device or device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.
Claims
1. A method for constructing a flight risk assessment model, characterized in that: include: Obtain risk assessment indicator system; According to the risk assessment indicator system, construct a risk relationship evaluation matrix; The risk assessment index system is a structure including multiple risk assessment indicators constructed through human factor analysis and classification system model; The risk relationship evaluation matrix is used to determine the relationship between the multiple risk assessment indicators in the risk assessment indicator system; The risk relationship evaluation matrix is normalized and standardized to obtain the standardized hesitant fuzzy direct influence matrix; Based on the normalized hesitant fuzzy direct impact matrix, a hierarchical structure stage is constructed to obtain a flight risk assessment set; the flight risk assessment set includes a flight risk impact degree, a flight risk affected degree, a flight risk intermediate degree, and a flight risk cause degree; Based on the normalized hesitant fuzzy direct influence matrix, a flight risk reachability matrix is obtained; the flight risk reachability matrix represents a matrix that limits the degree of mutual influence between risk assessment indicators; Based on the flight risk reachability matrix, the relationship between multiple risk assessment indicators is found to obtain a multi-level hierarchical risk model; According to the flight risk assessment set and the risk multi-level hierarchical model, detecting corresponding improvement measures and sending improvement measure signals; Based on the flight risk reachability matrix, the relationship between multiple risk assessment indicators is found to obtain a risk multi-level hierarchical model, including: Based on the flight risk reachability matrix, performing inter-level division to obtain multiple flight risk reachability sets; Based on the flight risk reachable matrix, inter-level division is performed to obtain multiple flight risk prior sets; one risk assessment indicator corresponds to one flight risk reachable set and one flight risk prior set; The flight risk reachable set and the flight risk antecedent set corresponding to the same flight risk reachable set are intersected to obtain a repeated impact set; the values in the repeated impact set represent risk assessment indicators that affect other risk assessment indicators and are affected by other risk assessment indicators; If the repeated impact set is the same as the flight risk reachable set, marking the risk assessment indicator corresponding to the flight risk reachable set to obtain a first marked risk assessment indicator; The values of a row and a column corresponding to the risk assessment index corresponding to the flight risk reachable set in the flight risk reachable matrix are set to 0 to obtain a new flight risk reachable matrix; Repeat the flight risk reachability matrix and arrange the risk assessment indicators in the order of testing to obtain a risk arrangement set; According to the risk arrangement set and the first marked risk assessment index, hierarchical decomposition is performed to obtain a risk multi-level hierarchical model.
2. A flight risk assessment model construction method according to claim 1, characterized in that: The above-mentioned hierarchical structure stage is constructed based on the normalized hesitant fuzzy direct impact matrix to obtain a flight risk assessment set, including: Each row of the normalized hesitant fuzzy direct influence matrix is added, and the influence of the risk assessment index corresponding to each row on other risk assessment indexes is detected to obtain the flight risk influence degree; Each column of the normalized hesitant fuzzy direct influence matrix is added, and the influence of other risk assessment indicators on the risk assessment indicator corresponding to each column is detected to obtain the flight risk influence degree; Based on the flight risk influence degree and the flight risk influenced degree, the flight risk centrality and the flight risk cause degree are obtained.
3. The method for constructing a flight risk assessment model according to claim 1, characterized in that: The flight risk reachability matrix is obtained based on the normalized hesitant fuzzy direct impact matrix, including: The normalized hesitant fuzzy direct impact matrix is added to the unit matrix to obtain the flight risk overall impact matrix; the flight risk overall impact matrix increases the impact of the risk assessment index reaching and receiving the same risk assessment index; If the value in the flight risk overall impact matrix is greater than the overall impact threshold, the value in the flight risk overall impact matrix is set to 1; if the value in the flight risk overall impact matrix is less than or equal to the overall impact threshold, the value in the flight risk overall impact matrix is set to 0 to obtain the flight risk reachable matrix.
4. The method for constructing a flight risk assessment model according to claim 1, characterized in that: The flight risk reachable matrix is based on which inter-level division is performed to obtain a flight risk reachable set, including: Obtain the value of each row in the flight risk reachable matrix to obtain multiple first flight risk reachable sets; a row in the first flight risk reachable matrix corresponds to one first flight risk reachable set; Obtaining a risk assessment indicator corresponding to a value not equal to 0 in the first flight risk reachable set as a reachable risk assessment indicator; A flight risk reachable set is constructed by taking multiple reachable risk assessment indicators as elements.
5. The method for constructing a flight risk assessment model according to claim 1, characterized in that: The flight risk reachable matrix is based on which the level division is performed to obtain a flight risk precedent set, including: Obtain the value of each column in the flight risk reachable matrix to obtain multiple first flight risk advance sets; one column in the first flight risk reachable matrix corresponds to one first flight risk advance set; Obtaining a risk assessment indicator corresponding to a value not equal to 0 in the first flight risk reachable set as a prior risk assessment indicator; A flight risk advance set is constructed using multiple advance risk assessment indicators as elements.
6. The method for constructing a flight risk assessment model according to claim 1, characterized in that: The obtaining of the flight risk centrality and the flight risk cause degree based on the flight risk influence degree and the flight risk influenced degree includes: The flight risk influence degree is added to the flight risk influence degree to obtain the flight risk centrality; the flight risk centrality is used to indicate the importance of the risk assessment index in the entire risk assessment index system; The flight risk cause degree is obtained by subtracting the flight risk impact degree from the flight risk impact degree.
7. A method for constructing a flight risk assessment model according to claim 5, characterized in that: If the flight risk cause degree is greater than 0, the corresponding risk assessment index is used as the cause risk assessment index; The cause risk assessment indicator indicates that the corresponding risk assessment indicator has an impact on other risk assessment indicators; If the flight risk cause degree is less than 0, the corresponding risk assessment index is used as the result risk assessment index; The result risk assessment indicator indicates the influence of other risk assessment indicators.
8. The method for constructing a flight risk assessment model according to claim 1, characterized in that: The risk relationship evaluation matrix is normalized and standardized to obtain a standardized hesitant fuzzy direct impact matrix, including: Normalize the risk relationship evaluation matrix to obtain the normalized hesitant fuzzy direct influence matrix; The hesitant fuzzy direct influence matrix is normalized to obtain the normalized hesitant fuzzy direct influence matrix.
9. The method for constructing a flight risk assessment model according to claim 1, characterized in that: The detecting corresponding improvement measures according to the flight risk assessment set and the risk multi-level hierarchical model and sending an improvement measure signal includes: Obtaining a user surface risk indicator; the user surface risk indicator is an indicator of the risk of the user; Find multiple user deep risk indicators corresponding to the user surface risk indicators according to the risk multi-level hierarchical model; According to the flight risk assessment set, multiple user causal risk indicators having an influencing relationship with the user surface risk indicators are found; According to the multiple user deep risk indicators and the multiple user causal risk indicators, the corresponding improvement measure numbers are found, and the improvement measure numbers are sent.