A suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method

Abstract

The present application provides a kind of suspicious unmanned aircraft induced ground target party visible privacy information disclosure risk real-time evaluation method.The method comprises the following steps: step S1: the disclosure hazard degree of ground target party visible privacy information is evaluated;Step S2: the start time of the generation process of ground target party visible privacy information is recorded as time point 0, and the time interval T2 of real-time evaluation is determined;After every T2, step S3 and step S4 are run in turn;Step S3: at time point t, the disclosure probability level of ground target party visible privacy information is evaluated for the fth time;Step S4: at time point t, the disclosure risk level of ground target party visible privacy information is evaluated for the fth time, until the generation process of ground target party visible privacy information is stopped to stop evaluation.The method of the present application fills the research gap of the evaluation of the disclosure risk of ground target party visible privacy information induced by suspicious unmanned aircraft, and the evaluation method has good rationality and feasibility.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle safety risk assessment, in particular to a suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method. BACKGROUND

[0002] Unmanned aerial vehicle accidents can be divided into active accidents caused by the intention of unmanned aerial vehicle operators and passive accidents caused by the non-intention of operators, and the two types of accidents respectively induce active safety risks and passive safety risks. The active unmanned aerial vehicle accident related party can be divided into a destruction party and a target party, and the passive unmanned aerial vehicle accident related party can be divided into a flight operation party, a flight customer party, and a third party having no direct interest in flight. According to the consequences of unmanned aerial vehicle accidents, unmanned aerial vehicle safety risks can be divided into personnel casualty risks, property loss risks and privacy information leakage risks. At present, there are unmanned aerial vehicle safety risk assessment methods for ground objects. These methods include: ground third party personnel casualty and property loss risk assessment method, ground target party personnel casualty and property loss risk assessment method, however, there is no related solution to evaluate the leakage risk of visible privacy information of the ground target party, that is, the evaluation of the leakage risk of the visible privacy information of the ground target party is completely blank.

[0003] In view of this research blank, it is extremely necessary to design a suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method. The visible privacy information refers to the privacy information that can be collected by a device based on the principle of optical imaging to form an image and record the image. SUMMARY

[0004] The present application aims to provide a suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method. The evaluation method is implemented by a risk evaluation party. In the case of a suspicious unmanned aerial vehicle appearing in the airspace around a ground object, the risk evaluation party assumes that the suspicious unmanned aerial vehicle may induce an active accident, and takes the suspicious unmanned aerial vehicle as a destruction party and the ground object as a ground target party, and evaluates the real-time leakage risk of the visible privacy information of the ground target party.

[0005] To this end, the present application aims to provide a suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method.

[0006] In order to achieve the above object, the technical scheme of the present application provides a suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method. The suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method comprises the following steps: step S1: evaluating the leakage harm degree level of the ground target party visible privacy information; step S2: recording the start time of the ground target party visible privacy information generation process as time point 0, and determining the time interval T2 of real-time evaluation; then every T2, that is, at time point t, steps S3 and S4 are sequentially executed; t=(f-1)×T2; f represents the number of real-time evaluations, and f is a positive integer greater than or equal to 1; step S3: at time point t, the fth real-time evaluation of the leakage probability level of the ground target party visible privacy information is performed; step S4: based on the evaluation result of the leakage harm degree level of the ground target party visible privacy information and the fth real-time evaluation result of the leakage probability level of the ground target party visible privacy information, the fth real-time evaluation of the leakage risk level of the ground target party visible privacy information is performed at time point t, until the ground target party visible privacy information generation process is stopped.

[0007] Preferably, the step S1 comprises: step S1.1: constructing a network model of an organization in which the ground target party related person is located; wherein the ground target party related person refers to a person associated with the ground target party; the ground target party related person is confirmed by a risk evaluation party; step S1.2: calculating the importance of each member in the organization in which the ground target party related person is located based on the network model; step S1.3: calculating the sorting proportion value of the importance of the ground target party related person based on the calculation result of the importance of each member in the organization in which the ground target party related person is located; and step S1.4: determining the leakage harm degree level of the ground target party visible privacy information based on the calculation result of the sorting proportion value of the importance of the ground target party related person.

[0008] Preferably, the step S3 comprises: step S3.1: at time point t, monitoring the airspace around the ground target party, and according to the monitoring result, performing steps S3.2 to S3.4, or skipping steps S3.2 and S3.3, and directly performing step S3.4; step S3.2: at time point t, calculating the identification probability of the suspicious unmanned aerial vehicle to the identity of the ground target party; step S3.3: at time point t, calculating the definition of the suspicious unmanned aerial vehicle shooting the ground target party visible privacy information; step S3.4: at time point t, calculating the leakage probability of the ground target party visible privacy information; and step S3.5: at time point t, performing the fth real-time evaluation of the leakage probability level of the ground target party visible privacy information.

[0009] Preferably, the step S1.1 specifically comprises the following steps: S1.11, determining the organization where the person related to the ground target party is located according to the daily social behavior of the person related to the ground target party; constructing a network model of the organization where the person related to the ground target party is located as a bidirectional complex network; wherein each member in the organization where the person related to the ground target party is located is modeled as a node of the bidirectional complex network; S1.12, counting the information interaction between the internal members of the organization where the person related to the ground target party is located within a certain time span; if member i sends information to member j, an edge from node i to node j is established, and the number of sent information is taken as the weight W of the edge ij ; S1.13, setting up a super node, establishing edges from the super node to other nodes in the bidirectional complex network, and setting the weight of the edge as 1; S1.14, setting the initial value of the importance S of each node in the bidirectional complex network as 1;

[0010] The step S1.2 specifically comprises:

[0011] S1.21, iteratively calculating the importance S of each node, and the iteration is ended when the importance S of each node converges; the formula corresponding to the iteration is:

[0012]

[0013] In formula (1), S j (tt) represents the importance of node j obtained in the (tt)th iteration; S i (tt+1) represents the importance of node i obtained in the (tt+1)th iteration; the S value corresponding to each member node is the importance of each member in the organization where the person related to the ground target party is located; m represents the total number of edges in the network model with node i as the terminal point; W ji represents the weight of the edge with j as the starting point and i as the terminal point; W jp represents the weight of the edge with j as the starting point and p as the terminal point; q represents the total number of edges in the network model with node j as the starting point; p represents the terminal point of the edge in the network model with node j as the starting point;

[0014] The step S1.3 specifically comprises the following steps: S1.31, arranging the importance of each member in the organization where the person related to the ground target party is located in descending order according to the calculation result of step S1.21; S1.32, taking the ranking number of the person related to the ground target party as l, and taking the total number of agency personnel as L, calculating the sorting proportion value of the importance of the person related to the ground target party; the formula corresponding to the calculation of the sorting proportion value is:

[0015]

[0016] And the step S1.4 specifically comprises: step S1.41: determining the leakage harm degree level of the visible private information of the ground target party according to the calculation result z of step S1.32; if z∈[0, 0.06), the leakage harm degree level of the visible private information of the ground target party is "serious"; if z∈[0.06, 0.125), the leakage harm degree level of the visible private information of the ground target party is "relatively serious"; if z∈[0.125, 0.25), the leakage harm degree level of the visible private information of the ground target party is "medium"; if z∈[0.25, 0.5), the leakage harm degree level of the visible private information of the ground target party is "relatively slight"; if z∈[0.5, 1], the leakage harm degree level of the visible private information of the ground target party is "slight".

[0017] Preferably, the step S3.1 specifically comprises: monitoring whether there is a suspicious UAV in the surrounding airspace of the ground target party by using a detection device; if the monitoring result is that there is a suspicious UAV, then let p t =1, and record the position of the suspicious UAV; if the monitoring result is that there is no suspicious UAV, then let p t =0; if p t =1, then continue to execute steps S3.2 to S3.4; if p t =0, then let q t =0, and skip steps S3.2 and S3.3, and directly execute step S3.4;

[0018] The step S3.2 specifically comprises: step S3.21: determining the shooting angle of the n-th suspicious UAV to the ground target party identity identification marker information surface , wherein, is the horizontal shooting angle, is the vertical shooting angle, and the ground target party identity identification marker information surface is confirmed by the risk assessment party; step S3.22: obtaining the brightness δ t of the ground target party identity identification marker information surface, the shielding ratio γ t of the ground target party identity identification marker information surface, and the environmental visibility level κ t by measurement respectively; wherein κ t ∈[0, 4], γ t ∈[0, 1]; step S3.23: according to the type of the ground target party identity identification marker, selecting to use a pre-trained ground target party identity identification probability evaluation neural network model to evaluate the ground target party identity identification probability p t n of the n-th suspicious UAV; step S3.24: obtaining the formula corresponding to the probability of the suspicious UAV identifying the ground target party at time point t as:

[0019]

[0020] In formula (3), p t represents the probability of suspicious UAV identifying the identity of the ground target party at time t; represents the probability of suspicious UAV n obtaining the ground target party identity identification at time τ; τ represents the evaluation time point identifier, and its value range is all evaluation time points from time 0 to time t; τ ∈ {0, T2, T2*2, T2*3..., t};

[0021] Step S3.25: If the ground target party does not carry an identity identification marker, but the risk assessment party infers that the suspicious UAV obtains the current ground target party identity identification through existing flight activities according to existing evidence p * , then p t can be directly assigned, that is, p t = p * ;

[0022] The step S3.3 specifically comprises: step S3.31: determining the shooting angle of the n-th suspicious UAV to the ground target party information surface Among them, represents the horizontal shooting angle, represents the vertical shooting angle; The ground target party information surface refers to the plane presenting the private information of the ground target party, which is identified by the risk assessment party; Step S3.32: Determine the ground target party brightness ρ t , the ground target party information surface shielding ratio environmental visibility level κ t ; Wherein, κ t ∈ [0, 4], Step S3.33: According to the type of ground target party, select to use the pre-trained ground target party visible private information clarity evaluation neural network model to evaluate the visible private information clarity of the n-th suspicious UAV shooting the ground target party Step S3.34: At time point t, the formula for obtaining the clarity of the visible private information of the ground target party shot by the suspicious UAV is:

[0023]

[0024] The step S3.4 specifically comprises: step S3.41: The risk assessment party estimates the estimated length T1 of the generation process of the visible private information of the ground target party according to the real-time situation; Step S3.42: Based on the estimated length T1 and formula (5), the leakage probability of the visible private information of the ground target party is calculated;

[0025]

[0026] In equation (5), T2 represents the estimated number of monitoring time points included in the visible privacy information generation process; P represents the time interval for real-time assessment. t The probability of privacy information being leaked and visible to the ground target at time t is represented by mm; mm is a variable representing an integer, with values ​​ranging from 0 to t / T2: mm∈{0,1,...,t / T2};

[0027] And step S3.5 specifically includes: Step S3.51: Based on the calculation result of step S3.42, at time point t, perform the f-th real-time assessment of the probability level of leakage of privacy information visible to the ground target; if P t If P ∈ [0, 0.1), then the f-th real-time assessment result of the probability level of privacy information leakage visible to the ground target is "slight"; if P t If P ∈ [0.1, 0.4), then the f-th real-time assessment result of the probability level of privacy information leakage visible to the ground target is "relatively minor"; if P t If P ∈ [0.4, 0.6), then the f-th real-time assessment result of the probability level of privacy information leakage visible to the ground target is "medium"; if P t If P ∈ [0.6, 0.9), then the f-th real-time assessment result of the probability level of privacy information leakage visible to the ground target is "relatively serious"; if P t If ∈[0.9,1], then the f-th real-time assessment result of the probability level of leakage of privacy information visible to the ground target is "severe".

[0028] Preferably, based on the assessment results of the leakage hazard level of the privacy information visible to the ground target obtained in step S1.41 and the fth real-time assessment results of the leakage probability level of the privacy information visible to the ground target obtained in step S3.51, and according to the risk matrix shown in Table 1, the leakage risk level of the privacy information visible to the ground target is assessed for the fth time at time point t.

[0029] Table 1 Risk Matrix

[0030]

[0031] The beneficial effects of this invention are:

[0032] (1) The suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method provided by the present application provides a specific and feasible solution for the research gap of suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk evaluation. The solution follows the risk evaluation framework, and the risk level is evaluated in real time according to the visible privacy information leakage probability and the visible privacy information leakage hazard degree, and has sufficient theoretical basis.

[0033] (2) The suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method provided by the present application solves the problem that the visible privacy information leakage hazard degree is difficult to measure. The complex network node importance evaluation algorithm is used to calculate the importance sorting proportion value of the ground target party, which is used as the evaluation basis for the visible privacy information leakage hazard degree of the ground target party. The evaluation method has good rationality and feasibility.

[0034] (3) The suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method provided by the present application establishes a ground target party visible privacy information leakage probability evaluation model according to the ground target party visible privacy information leakage accident process. The evaluation model has good rationality.

[0035] Additional aspects and advantages of the present application will become apparent in the description that follows, or will be learned by practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 A schematic flow chart of the suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method of one embodiment of the present application is shown. DETAILED DESCRIPTION

[0037] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application will be further described in detail below in combination with the drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0038] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, however, the present application can also be implemented in other ways different from those described herein, therefore, the scope of protection of the present application is not limited to the specific embodiments disclosed below.

[0039] Figure 1 A schematic flow chart of the suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method of one embodiment of the present application is shown. As shown in Figure 1 The suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method comprises:

[0040] S1: evaluate the ground target party visible privacy information leakage harm degree level;

[0041] S2: determine the time point 0 and the real-time evaluation time interval T2; the first evaluation is performed at t=0, and then S3 and S4 are sequentially run every T2, i.e. at time point t;

[0042] S3: step S3: real-time evaluation of the ground target party visible privacy information leakage probability level at time point t;

[0043] Step S4: real-time evaluation of the ground target party visible privacy information leakage risk level at time point t until the ground target party visible privacy information generation process ends and stops evaluation.

[0044] In this embodiment, the opening time of the privacy information generation process is 0, the first evaluation is performed at t=0, and then it is performed every T2 until the privacy information generation process ends and stops evaluation.

[0045] Specifically, in one embodiment of the present application, the suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method comprises: step S1: evaluating the ground target party visible privacy information leakage harm degree level; step S2: recording the opening time of the ground target party visible privacy information generation process as time point 0 and determining the real-time evaluation time interval T2; then S3 and S4 are sequentially run every T2, i.e. at time point t; t=(f-1)×T2; f represents the number of real-time evaluations, and f is a positive integer greater than or equal to 1; step S3: the fth real-time evaluation of the ground target party visible privacy information leakage probability level at time point t; step S4: based on the evaluation results of the ground target party visible privacy information leakage harm degree level and the fth real-time evaluation results of the ground target party visible privacy information leakage probability level, the fth real-time evaluation of the ground target party visible privacy information leakage risk level is performed at time point t until the ground target party visible privacy information generation process ends and stops evaluation.

[0046] In this embodiment, the suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk real-time evaluation method provided by the present application provides a specific and feasible solution for the research gap of suspicious unmanned aerial vehicle induced ground target party visible privacy information leakage risk evaluation, and the proposed solution follows the risk evaluation framework, real-time evaluates the risk level according to the visible privacy information leakage probability and the visible privacy information leakage harm degree, and has sufficient theoretical basis.

[0047] In an embodiment of the present application, the step S1 comprises: step S1.1: constructing a network model of an organization in which the ground target-related person is located; wherein the ground target-related person refers to a person associated with the ground target; the ground target-related person is confirmed by a risk assessment party; step S1.2: calculating the importance of each member in the organization in which the ground target-related person is located based on the network model; step S1.3: calculating the ranking proportion value of the importance of the ground target-related person based on the calculation result of the importance of each member in the organization in which the ground target-related person is located; and step S1.4: determining the leakage harm degree level of the visible private information of the ground target based on the calculation result of the ranking proportion value of the importance of the ground target-related person.

[0048] In an embodiment of the present application, the step S3 comprises: step S3.1: monitoring the airspace around the ground target at time point t, and performing steps S3.2 to S3.4 according to the monitoring result, or skipping steps S3.2 and S3.3 and directly performing step S3.4; step S3.2: calculating the identification probability of the suspicious UAV to the identity of the ground target at time point t; step S3.3: calculating the definition of the suspicious UAV shooting the visible private information of the ground target at time point t; step S3.4: calculating the leakage probability of the visible private information of the ground target at time point t; and step S3.5: performing the fth real-time evaluation on the leakage probability level of the visible private information of the ground target at time point t.

[0049] In an embodiment of the present application, the step S1.1 specifically comprises: step S1.11: determining the organization in which the ground target-related person is located according to the daily social behavior of the ground target-related person by the risk assessment party; constructing a network model of the organization in which the ground target-related person is located as a bidirectional complex network; wherein each member in the organization in which the ground target-related person is located is modeled as a node of the bidirectional complex network; step S1.12: statistically analyzing the information interaction between the internal members of the organization in which the ground target-related person is located within a certain time span; if member i sends information to member j, an edge from node i to node j is established, and the number of sent information is taken as the weight W of the edge; ij ; step S1.13: setting up a super node, establishing edges from the super node to other nodes in the bidirectional complex network, and setting the weight of the edge to be 1; and step S1.14: setting the initial value of the importance S of each node in the bidirectional complex network to be 1.

[0050] The step S1.2 specifically comprises:

[0051] Step S1.21: iteratively calculating the importance S of each node, and the iteration is ended when the importance S of each node converges; the iteration corresponds to the formula:

[0052]

[0053] In formula (1), S j (tt) represents the importance degree of node j calculated in the (tt)th iteration; S i (tt+1) represents the importance degree of node i calculated in the (tt+1)th iteration; the S value corresponding to each member node is the importance degree of each member in the organization where the ground target party is located; m represents the total number of edges in the network model with node i as the terminal point; W ji represents the weight of the edge with j as the starting point and i as the terminal point; W jp represents the weight of the edge with j as the starting point and p as the terminal point; q represents the total number of edges in the network model with node j as the starting point; p represents the terminal point of the edge in the network model with node j as the starting point;

[0054] The step S1.3 specifically comprises: step S1.31: according to the calculation result of step S1.21, arranging the importance degrees of each member in the organization where the ground target party is located in descending order; step S1.32: recording the ranking number of the ground target party as l, recording the total number of agency personnel as L, and calculating the sorting proportion value of the importance degree of the ground target party; the formula corresponding to the calculation of the sorting proportion value is:

[0055]

[0056] And the step S1.4 specifically comprises: step S1.41: according to the calculation result z of step S1.32, determining the leakage hazard degree level of the visible private information of the ground target party; if z∈[0, 0.06), the leakage hazard degree level of the visible private information of the ground target party is “serious”; if z∈[0.06, 0.125), the leakage hazard degree level of the visible private information of the ground target party is “relatively serious”; if z∈[0.125, 0.25), the leakage hazard degree level of the visible private information of the ground target party is “medium”; if z∈[0.25, 0.5), the leakage hazard degree level of the visible private information of the ground target party is “relatively slight”; if z∈[0.5, 1], the leakage hazard degree level of the visible private information of the ground target party is “slight”.

[0057] In an embodiment of the present application, the step S3.1 specifically comprises: monitoring whether there is a suspicious unmanned aerial vehicle in the surrounding airspace of the ground target party by using a detection device; if the monitoring result is that there is a suspicious unmanned aerial vehicle, setting p t =1, and recording the position of the suspicious unmanned aerial vehicle; if the monitoring result is that there is no suspicious unmanned aerial vehicle, setting p t =0; if p t=1, then continue with steps S3.2 to S3.4; if p t =0, then let q t =0, and skip steps S3.2 and S3.3, and directly execute step S3.4;

[0058] Step S3.2 specifically includes: Step S3.21: Determine the shooting angle of the nth suspicious drone on the ground target's identification marker information surface. in, This is a horizontal shooting angle. For the vertical shooting angle, the information surface of the ground target identification marker is confirmed by the risk assessment party; Step S3.22: The brightness δ of the information surface of the ground target identification marker is obtained by measurement. t The occlusion ratio γ of the ground target identification marker information surface t Environmental visibility level κ t ; where κ t ∈[0,4], γ t ∈[0,1]; Step S3.23: Based on the type of ground target identification marker, select a pre-trained ground target identification probability evaluation neural network model to evaluate the ground target identification probability p obtained by the nth suspicious UAV. t n Step S3.24: At time point t, the formula corresponding to the probability of a suspicious drone identifying a ground target is:

[0059]

[0060] In equation (3), p t This represents the probability that a suspicious drone can identify a ground target at time t. τ represents the probability of identifying the ground target obtained by the nth suspicious drone at time τ; τ represents the evaluation time point identifier, and its value range is all evaluation time points from time 0 to time t; τ∈{0,T2,T2*2,T2*3...,t};

[0061] Step S3.25: If the ground target does not carry identification markers, but the risk assessment party infers, based on existing evidence, the probability p that the suspicious drone obtained the current ground target's identity through existing flight activities... * Then p can be used t Direct assignment, i.e., p t =p * ;

[0062] The step S3.3 specifically comprises: step S3.31: determining the shooting angle of the nth suspicious UAV to the ground target party information surface wherein, represents the horizontal shooting angle, represents the vertical shooting angle; the ground target party information surface refers to a plane presenting the private information of the ground target party, which is determined by the risk assessment party; step S3.32: determining the ground target party brightness ρ t , the ground target party information surface shielding ratio environmental visibility level κ t ; wherein κ t ∈ [0, 4], step S3.33: according to the type of the ground target party, selecting to use a pre-trained ground target party visible private information clarity evaluation neural network model to evaluate the visible private information clarity of the ground target party shot by the nth suspicious UAV step S3.34: at time point t, the formula for obtaining the clarity of the visible private information of the ground target party shot by the suspicious UAV is:

[0063]

[0064] The step S3.4 specifically comprises: step S3.41: the risk assessment party estimates the estimated length T1 of the generation process of the visible private information of the ground target party according to the real-time situation; step S3.42: based on the estimated length T1 and formula (5), the leakage probability of the visible private information of the ground target party is calculated;

[0065]

[0066] In formula (5), is the estimated number of monitoring time points included in the generation process of the visible private information; T2 represents the real-time evaluation time interval; P t represents the leakage probability of the visible private information of the ground target party at time t; mm is an integer variable, and its value range is from 0 to an integer of t / T2: mm ∈ {0, 1,..., t / T2};

[0067] And the step S3.5 specifically comprises: step S3.51: according to the calculation result of the step S3.42, the leakage probability level of the visible private information of the ground target party is evaluated for the fth time at time point t; if P t ∈ [0, 0.1), the fth time real-time evaluation result of the leakage probability level of the visible private information of the ground target party is "slight"; if P tIf P t If P t If P t If P

[0068] In an embodiment of the present application, the risk level of the leakage of the private information visible to the ground target party is evaluated for the fth time at the time point t according to the evaluation result of the leakage harm degree level of the private information visible to the ground target party obtained in step S1.41 and the fth real-time evaluation result of the leakage probability level of the private information visible to the ground target party obtained in step S3.51, and according to the risk matrix shown in Table 1.

[0069] Table 1 Risk matrix

[0070] Embodiment 1

[0072] The real-time evaluation method of the risk of the leakage of the private information visible to the ground target party caused by the suspicious unmanned aerial vehicle will be described below with reference to an embodiment.

[0073] The implementation steps of the real-time evaluation method of the risk of the leakage of the private information visible to the ground target party caused by the suspicious unmanned aerial vehicle in the embodiment are as follows:

[0074] (1) Step S1: evaluating the leakage harm degree level of the private information visible to the ground target party.

[0075] The step S1 comprises: step S1.1: constructing a network model of the organization in which the ground target party related person is located; wherein the ground target party related person refers to a person associated with the ground target party; the ground target party related person is confirmed by a risk evaluator; step S1.2: calculating the importance of each member in the organization in which the ground target party related person is located based on the network model; step S1.3: calculating the sorting proportion value of the importance of the ground target party related person based on the calculation result of the importance of each member in the organization in which the ground target party related person is located; step S1.4: determining the leakage harm degree level of the private information visible to the ground target party based on the calculation result of the sorting proportion value of the importance of the ground target party related person.

[0076] The step S1.1 specifically comprises:

[0077] Step S1.11: the risk assessment party determines the organization to which the ground target party related person belongs according to the daily social behavior of the ground target party related person; a network model of the organization to which the ground target party related person belongs is constructed as a bidirectional complex network; wherein each member in the organization to which the ground target party related person belongs is modeled as a node of the bidirectional complex network; Step S1.12: the information interaction between the internal members of the organization to which the ground target party related person belongs within a certain time span is counted; if member i sends information to member j, an edge from node i to node j is established, and the number of sent information is taken as the weight W of the edge ij ; Step S1.13: a super node is set up, edges from the super node to other nodes in the bidirectional complex network are established, and the weights of the edges are all set to 1; Step S1.14: the initial value of the importance S of each node in the bidirectional complex network is set to 1;

[0078] The step S1.2 specifically comprises:

[0079] Step S1.21: the importance S of each node is iteratively calculated, and the iterative calculation is ended when the importance S of each node converges; the formula corresponding to the iterative calculation is:

[0080]

[0081] In formula (1), S j (tt) represents the importance of node j obtained in the (tt)th iteration calculation; S i (tt+1) represents the importance of node i obtained in the (tt+1)th iteration calculation; the S value corresponding to each member node is the importance of each member in the organization to which the ground target party related person belongs; m represents the total number of edges in the network model with node i as the terminal point; W ji represents the weight of the edge with j as the starting point and i as the terminal point; W jp represents the weight of the edge with j as the starting point and p as the terminal point; q represents the total number of edges in the network model with node j as the starting point; p represents the terminal point of the edge in the network model with node j as the starting point;

[0082] The step S1.3 specifically comprises:

[0083] Step S1.31: according to the calculation result of step S1.21, the importance of each member in the organization to which the ground target party related person belongs is arranged in descending order; Step S1.32: the ranking number of the ground target party related person is recorded as l, and the total number of agency personnel is recorded as L, and the sorting proportion value of the importance of the ground target party related person is calculated; the formula corresponding to the calculation of the sorting proportion value is:

[0084]

[0085] and the step S1.4 specifically comprises:

[0086] Step S1.41: determining the leakage harm degree level of the visible privacy information of the ground target party according to the calculation result z of step S1.32; if z∈[0, 0.06), the leakage harm degree level of the visible privacy information of the ground target party is “serious”; if z∈[0.06, 0.125), the leakage harm degree level of the visible privacy information of the ground target party is “relatively serious”; if z∈[0.125, 0.25), the leakage harm degree level of the visible privacy information of the ground target party is “medium”; if z∈[0.25, 0.5), the leakage harm degree level of the visible privacy information of the ground target party is “relatively slight”; if z∈[0.5, 1], the leakage harm degree level of the visible privacy information of the ground target party is “slight”.

[0087] (2) Step S2: recording the start time of the generation process of the visible privacy information of the ground target party as time point 0, and determining the time interval T2 of real-time evaluation; then every T2, i.e. at time point t, running step S3 and step S4 in turn; t=(f-1)×T2; f represents the number of real-time evaluations, and f is a positive integer greater than or equal to 1.

[0088] (3) Step S3: at time point t, performing the fth real-time evaluation on the leakage probability level of the visible privacy information of the ground target party.

[0089] The step S3 comprises: step S3.1: at time point t, monitoring the surrounding airspace of the ground target party, and according to the monitoring result, performing step S3.2 to step S3.4, or skipping step S3.2 and step S3.3, and directly performing step S3.4; step S3.2: at time point t, calculating the identification probability of the suspicious UAV to the identity of the ground target party; step S3.3: at time point t, calculating the definition of the suspicious UAV shooting the visible privacy information of the ground target party; step S3.4: at time point t, calculating the leakage probability of the visible privacy information of the ground target party; step S3.5: at time point t, performing the fth real-time evaluation on the leakage probability level of the visible privacy information of the ground target party.

[0090] The step S3.1 specifically comprises:

[0091] monitoring whether there is a suspicious UAV in the surrounding airspace of the ground target party by using a detection device; if the monitoring result is that there is a suspicious UAV, setting p t =1, and recording the position of the suspicious UAV; if the monitoring result is that there is no suspicious UAV, setting p t =0; if p t =1, continuing to perform step S3.2 to step S3.4; if pt = 0, let q t = 0, and skip steps S3.2 and S3.3, and directly execute step S3.4;

[0092] The step S3.2 specifically comprises:

[0093] Step S3.21: Determine the shooting angle of the n suspicious unmanned aerial vehicle to the ground target party identity identification marker information surface Wherein, is the horizontal shooting angle, is the vertical shooting angle, and the ground target party identity identification marker information surface is confirmed by the risk assessment party; Step S3.22: Obtain the brightness δ t , the shielding ratio γ t , and the environmental visibility level κ t of the ground target party identity identification marker information surface respectively by measurement; wherein, κ t ∈ [0, 4], γ t ∈ [0, 1]; Step S3.23: According to the type of ground target party identity identification marker, select to use the pre-trained ground target party identity identification probability evaluation neural network model to evaluate the ground target party identity identification probability obtained by the n suspicious unmanned aerial vehicle Step S3.24: At time point t, the formula corresponding to the probability of suspicious unmanned aerial vehicle to ground target party identity identification is:

[0094]

[0095] In formula (3), p t represents the probability of suspicious unmanned aerial vehicle to ground target party identity identification at time t; represents the ground target party identity identification probability obtained by the n suspicious unmanned aerial vehicle at τ time; τ represents the evaluation time point identifier, and its value range is all evaluation time points from time 0 to time t; τ ∈ {0, T2, T2*2, T2*3..., t};

[0096] Step S3.25: If the ground target party does not carry an identity identification marker, but the risk assessment party infers from existing evidence that the suspicious unmanned aerial vehicle obtains the current ground target party identity identification probability p * through existing flight activities, then p t can be directly assigned, that is, p t = p * ; The step S3.3 specifically comprises: Step S3.31: Determine the shooting angle of the n suspicious unmanned aerial vehicle to the ground target party information surface Wherein, representing a horizontal direction shooting angle, representing a vertical direction shooting angle; the ground target party information surface refers to a plane presenting the ground target party privacy information, which is identified by the risk assessment party; step S3.32: the ground target party brightness ρ t , the ground target party information surface shielding ratio environmental visibility level κ t ; wherein κ t ∈[0,4], step S3.33: according to the ground target party type, a pre-trained ground target party visible privacy information definition evaluation neural network model is selected to evaluate the visible privacy information definition of the nth suspicious UAV shooting ground target party step S3.34: at time point t, the formula for obtaining the definition of the visible privacy information of the suspicious UAV shooting ground target party is:

[0097]

[0098] The step S3.4, specifically includes: step S3.41: the risk assessment party estimates the estimated length T1 of the ground target party visible privacy information generation process according to the real-time situation; step S3.42: based on the estimated length T1 and formula (5), the leakage probability of the ground target party visible privacy information is calculated;

[0099]

[0100] In formula (5), is the estimated number of monitoring time points included in the visible privacy information generation process; T2 represents the real-time evaluation time interval; P t represents the leakage probability of the ground target party visible privacy information at time t; mm is an integer variable, whose value range is from 0 to the integer of t / T2: mm∈{0,1,...,t / T2};

[0101] And the step S3.5, specifically includes:

[0102] Step S3.51: according to the calculation result of the step S3.42, the leakage probability level of the ground target party visible privacy information is evaluated for the fth time at time point t; if P t ∈[0,0.1), the fth time real-time evaluation result of the leakage probability level of the ground target party visible privacy information is "slight"; if P t ∈[0.1,0.4), the fth time real-time evaluation result of the leakage probability level of the ground target party visible privacy information is "slightly slight"; if P tIf P∈[0.4, 0.6), the fth real-time evaluation result of the ground target party's visible privacy information leakage probability level is "medium"; if P t If P∈[0.6, 0.9), the fth real-time evaluation result of the ground target party's visible privacy information leakage probability level is "relatively serious"; if P t If P∈[0.9, 1], the fth real-time evaluation result of the ground target party's visible privacy information leakage probability level is "serious".

[0103] Specifically, the definition process of the horizontal direction shooting angle and the vertical direction shooting angle in the step S3.21 is as follows: assuming that the shooting target information surface is O, the center point of the shooting target on the information surface O is o, and the shooting point is u; when the surface O is perpendicular to the horizontal plane, a horizontal line l1 passing through the point o is constructed, and a ray l2 passing through the point o and being perpendicular upward is constructed, the trajectories of l1 and l2 on O are l1' and l'2 respectively, the plane passing through l1' and being perpendicular to O is O2, and the plane passing through l'2 and being perpendicular to O is O3; a ray l3 is constructed on the intersection line of the planes O2 and O3, with the point o as the starting point and the direction being the front direction of the shooting target; the straight line passing through o and u is l4; the clockwise included angle between the projection of l4 on O2 and l3 is the horizontal direction shooting angle, and the included angle between the projection of l4 on O3 and l3 is the vertical direction shooting angle.

[0104] Specifically, in the steps S3.21 and S3.31, the specific method for calculating the shooting angle of the suspicious unmanned aerial vehicle to the shooting target information surface is as follows: a radar coordinate system and a shooting target coordinate system are set, wherein the radar coordinate system takes the center point of the monitoring device as the origin, the shooting target coordinate system takes the center of the shooting target as the origin, and both coordinate systems take the north direction as the positive direction of the x axis, the east direction as the positive direction of the y axis, and the vertical upward direction as the z axis. The position information of the measurement point in the coordinate system is expressed in the format (R, α, β), wherein R represents the slant distance, i.e. the distance between the measurement point and the origin, α represents the azimuth angle of the measurement point, i.e. the clockwise included angle between the projection line of the slant distance on the horizontal plane passing through the x axis and the y axis and the x axis, and its value range is 0 to 360 degrees, and β represents the elevation angle of the measurement point, i.e. the included angle between the projection line of the slant distance on the vertical plane passing through the x axis and the z axis and the x axis, and its value range is -90 degrees to +90 degrees.

[0105] The airspace monitoring device obtains the position of the nth unmanned aerial vehicle in the radar coordinate system as (R n ,α n ,β n ), and the position of the shooting target as (R0, α0, β0). The method for calculating the position information of the nth unmanned aerial vehicle in the shooting target coordinate system is as follows:

[0106] The coordinate on the z axis is: The coordinate on the x axis is

[0107] The coordinate on the y-axis is The azimuth angle is: The elevation angle is:

[0108] The direction of the information surface of the shooting target based on the shooting target coordinate system is represented by (α ** ,β ** ), assuming that the ray l is a ray extending from the center of the shooting target, toward the front of the information surface, and perpendicular to the information surface of the shooting target, α ** is the azimuth angle of the point on the ray l, and β ** is the elevation angle of the point on the ray.

[0109] The specific calculation method of the shooting angle of the nth suspicious unmanned aerial vehicle to the information surface of the shooting target is that the horizontal shooting angle σ n is:

[0110]

[0111] The vertical shooting angle

[0112] Specifically, in step S3.23, the specific method for pre-training each type of ground target party identity recognition probability evaluation neural network model is: constructing a data set, building a neural network, training and verifying the neural network. The specific method for constructing the data set is: collecting photos of a certain type of ground target party identity recognition marker under the conditions of different shooting angles, different ground target party identity recognition marker information surface brightness, different ground target party identity recognition marker information surface occlusion ratio, and different environmental visibility levels. The horizontal shooting angle, the vertical shooting angle, the ground target party identity recognition marker information surface brightness, the ground target party identity recognition marker information surface occlusion ratio, and the environmental visibility level are used as inputs. The similarity between the photographed photo and the ground target party identity recognition marker information surface frontal photo is used as output. The specific method for building the neural network is: the neural network includes an input layer, two hidden layers, and an output layer, the input layer contains 5 nodes, the hidden layer contains 64 nodes, and the output layer contains 1 node, the neural network is a fully connected network, the activation function of each node in the hidden layer is a ReLU function, and the output layer activation function adopts a Sigmoid function. The specific method for training and verifying the neural network is: divide the data set into a training set, a test set, and a verification set in a ratio of 7:1:2; the model training adopts an Adam algorithm. In the specific implementation process, the MAE (Mean Absolute Error) is used as the loss function, the neural network is trained using the Adam algorithm, the learning rate is set to 0.001, the batch size is set to 64, and a total of 100 rounds of training are performed. The hardware platform processor used is AMD Ryzen5600, and the GPU is NVIDIARTX3060.

[0113] Specifically, in step S3.33, the specific method for pre-training the specific type of ground target visible privacy information definition evaluation neural network model is: constructing a data set, building a neural network, training and verifying the neural network. The specific method for constructing the data set is: collecting photos of a certain type of ground target under different shooting angles, different ground target brightness, different ground target information surface shielding ratios, different environmental visibility levels. The horizontal shooting angle, the vertical shooting angle, the ground target brightness, the ground target information surface shielding ratio, and the environmental visibility level are used as inputs. The photographed photos are labeled by experts, and the labeling content is the definition score, with a score range of 0 to 1, 0 indicating complete unclarity, and 1 indicating complete clarity. The labeling results are used as outputs. The specific method for building the neural network is: the neural network includes an input layer, two hidden layers, and an output layer, the input layer includes 5 nodes, the hidden layer includes 64 nodes, and the output layer includes 1 node. The neural network is a fully connected network, the activation function of each node in the hidden layer is a ReLU function, and the activation function of the output layer is a Sigmoid function. The specific method for training and verifying the neural network is: dividing the data set into a training set, a test set, and a verification set in a ratio of 7:1:2; the model training adopts the Adam algorithm. In the specific implementation process, the MAE (Mean Absolute Error) is used as the loss function, the Adam algorithm is used to train the neural network, the learning rate is set to 0.001, the batch size is set to 64, and a total of 100 rounds of training are performed. The hardware platform processor used is AMD Ryzen 5600, and the GPU is NVIDIA RTX3060.

[0114] (4) Step S4: based on the evaluation result of the leakage harm degree level of the ground target visible privacy information and the fth real-time evaluation result of the leakage probability level of the ground target visible privacy information, the fth real-time evaluation of the leakage risk level of the ground target visible privacy information is performed at time point t until the ground target visible privacy information generation process is stopped.

[0115] Further, the step S4 comprises: according to the evaluation result of the leakage harm degree level of the ground target visible privacy information obtained in step S1.41 and the fth real-time evaluation result of the leakage probability level of the ground target visible privacy information obtained in step S3.51, and according to the risk matrix shown in Table 1, the fth real-time evaluation of the leakage risk level of the ground target visible privacy information is performed at time point t.

[0116] Table 1 Risk matrix

[0117] Specific embodiment two:

[0119] The suspicious unmanned aerial vehicle triggered ground target party visible privacy information leakage risk real-time evaluation system will be demonstrated below with a specific embodiment. Based on the same suspicious unmanned aerial vehicle triggered ground target party visible privacy information leakage risk real-time evaluation method of the specific embodiment one, the specific embodiment two discloses a suspicious unmanned aerial vehicle triggered ground target party visible privacy information leakage risk real-time evaluation system, which comprises a ground target party visible privacy information leakage harm degree grade evaluation module, a ground target party visible privacy information leakage probability grade evaluation module, and a ground target party visible privacy information leakage risk grade evaluation module.

[0120] To sum up, the technical key points of the present application are as follows: 1. The present application evaluates the suspicious unmanned aerial vehicle triggered ground target party visible privacy information leakage risk, that is, the risk level is evaluated in real time according to the leakage probability of visible privacy information and the leakage harm degree of visible privacy information. 2. The present application evaluates the ground target party visible privacy information leakage harm degree grade. 3. The present application calculates the ground target party visible privacy information leakage probability. 4. The present application calculates the identification probability of the suspicious unmanned aerial vehicle to the ground target party identity. 5. The present application calculates the definition of the suspicious unmanned aerial vehicle shooting ground target party visible privacy information. 6. The present application calculates the shooting angle of the unmanned aerial vehicle to the shooting target information. 7. The present application constructs and trains the ground target party identity identification probability evaluation neural network model. 8. The present application constructs and trains the ground target party visible privacy information definition evaluation neural network model.

[0121] Therefore, it is proved that the suspicious unmanned aerial vehicle triggered ground target party visible privacy information leakage risk evaluation method and system provided by the present application completely belong to the research blank, and the evaluation method has good rationality and feasibility.

[0122] The above only describes the preferred embodiments of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for real-time assessment of the risk of privacy information leakage to ground targets caused by suspicious drones, comprising: Step S1: Assess the severity of the leakage of privacy information visible to ground targets; Step S2: Record the start time of the process for generating privacy information visible to the ground target as time point 0, and determine the real-time evaluation time interval. T 2; then every... T 2. At the point in time t Run steps S3 and S4 sequentially; ; f Represents the number of real-time assessments. f It is a positive integer greater than or equal to 1; Step S3: At time point t The system monitors suspicious drones in the airspace surrounding a ground target, calculates the probability of the suspicious drone identifying the ground target and the clarity of the visible private information captured by the suspicious drone, and then calculates the probability of leakage of the visible private information of the ground target based on the identification probability and clarity. The system then assigns a level to the probability of leakage of the visible private information of the ground target. f Secondary real-time assessment; Step S4: Based on the leakage hazard level assessment results and leakage probability level assessment results, at the time point... t The risk level of leakage of privacy information visible to ground targets is determined. f The process of generating privacy information is continuously evaluated in real time until the ground target can see the end of the privacy information generation process. Step S1 includes: Step S1.1: Construct a network model of the organizations to which the stakeholders of the ground target party belong; stakeholders of the ground target party refer to people who are associated with the ground target party; stakeholders of the ground target party are identified by the risk assessment party; Step S1.1 specifically includes: Step S1.11: The risk assessment party determines the organization to which the relevant individuals of the ground target belong based on their daily social behavior; constructs a network model of the organization as a bidirectional complex network; each member of the organization is a node in the bidirectional complex network; Step S1.12: Statistically analyze the information exchange among members within the organization over a certain time span; if members i To members j Send information and establish nodes i Pointing to node j The edges are defined, and the number of messages sent is used as the weight of the edge. ; Step S1.13: Set up a super node, establish edges from the super node to other nodes in the bidirectional complex network, and set the weight of each edge to 1; Step S1.14: Determine the importance of each node in the bidirectional complex network. s The initial values ​​are all 1; Step S1.2: Calculate the importance of each member in the organization based on the network model; Step S1.2 specifically includes: Step S1.21: Assess the importance of each node s The values ​​are calculated iteratively, when each s Once the values ​​converge, the iterative calculation ends; the iterative calculation formula is: （1） In equation (1), Represents a node j In the The importance of each iteration is calculated; Represents a node i In the The importance of each iteration calculation; the corresponding importance of each member node. s The value represents the importance of each member; m The network model is represented by nodes. i The total number of edges ending at the destination; Indicates the starting point is j The destination is i The weight of the edge; Indicates the starting point is j The destination is p The weight of the edge; q The network model is represented by nodes. j The total number of edges originating from the starting point; p The network model is represented by nodes. j The endpoint of the edge starting from the origin; Step S1.3: Based on the importance calculation results of each member, calculate the ranking ratio of the importance of relevant persons of the ground target party; Step S1.4: Determine the leakage hazard level based on the calculation results of the sorting ratio value.

2. The method for real-time assessment of the risk of privacy information leakage to ground targets caused by suspicious drones according to claim 1, characterized in that, Step S3 includes: Step S3.1: At time point t Monitor the airspace surrounding the ground target, and based on the monitoring results, execute steps S3.2 to S3.4, or skip steps S3.2 and S3.3 and directly execute step S3.4; Step S3.2: At time point t Calculate the probability that a suspicious drone can identify the identity of a ground target. Step S3.3: At time point t Calculate the clarity of private information visible to ground targets captured by suspicious drones; Step S3.4: At time point t Calculate the probability of privacy information being leaked to ground targets; Step S3.5: At time point t The probability level of privacy information leakage visible to ground targets is determined. f Secondary real-time assessment; Step S3.1 specifically includes: Use detection equipment to monitor the airspace surrounding the ground target for the presence of suspicious drones; if the monitoring results indicate the presence of suspicious drones, then... And record the location of the suspicious drone; if the monitoring result shows that there is no suspicious drone, then... ;if If so, continue with steps S3.2 to S3.4; if Then let And skip steps S3.2 and S3.3, and directly execute step S3.4; Step S3.2 specifically includes: Step S3.21: Determine the first n The angle at which a suspicious drone photographs ground-based identification markers. ;in, This is a horizontal shooting angle. The shooting angle is vertical, and the information of the ground target identification marker is confirmed by the risk assessment party. Step S3.22: Measure the brightness of the ground target identification marker information surface. The occlusion ratio of the ground target identification marker information surface Environmental visibility level ;in, ; Step S3.23: Based on the type of ground target identification markers, select a pre-trained ground target identification probability evaluation neural network model to evaluate the first... n Probability of ground target identification obtained from suspicious drones ; Step S3.24: At time point t The formula for determining the probability of a suspicious drone identifying a ground target is as follows: （3） In equation (3), represent t The probability of a suspicious drone identifying a ground target at any given time; Representative at At that moment, the n The probability of identifying ground targets obtained from suspicious drones; This represents the evaluation time point identifier, and its value ranges from time 0 to time 1. t All assessment time points; ; Step S3.25: If the ground target does not carry identification markers, but the risk assessment party infers, based on existing evidence, the probability that the suspicious drone obtained the current ground target's identity through existing flight activities. Then it can be used for Direct assignment, i.e. ; Step S3.3 specifically includes: Step S3.31: Determine the first n The angle at which a suspicious drone photographs information about ground targets. ;in, This represents the horizontal shooting angle. The vertical shooting angle is represented; the ground target information surface refers to the plane that presents the privacy information of the ground target, as determined by the risk assessment party. Step S3.32: Determine the brightness of the ground target information surface by measurement. Ground target information surface occlusion ratio Environmental visibility level ;in, ; Step S3.33: Based on the ground target type, select a pre-trained neural network model for evaluating the clarity of visible privacy information of the ground target to evaluate the first... n Clarity of privacy information visible only when a suspicious drone photographs a ground target. ; Step S3.34: At time point t The formula for obtaining the clarity of private information of ground targets visible to the naked eye captured by a suspicious drone is: （4） Step S3.4 specifically includes: Step S3.41: The risk assessment party estimates the estimated length of the privacy information generation process visible to the ground target party based on the real-time situation. ; Step S3.42: Based on the estimated length Using formula (5), the probability of privacy information being leaked and visible to ground targets is calculated; （5） In equation (5), It is the estimated number of monitoring time points included in the visible privacy information generation process; The time interval representing real-time evaluation; represent t The probability of privacy information being leaked and visible only to ground targets at any given time; mm It is a variable representing an integer, whose value ranges from 0 to... Integers: ; And step S3.5 specifically includes: Step S3.51: Based on the calculation results of step S3.42, at time point... t The probability level of privacy information leakage visible to ground targets is determined. f Secondary real-time assessment; if The probability level of privacy information leakage visible to ground targets is 1. f The next real-time assessment result is "minor"; if The probability level of privacy information leakage visible to ground targets is 1. f The next real-time assessment result was "mild"; if The probability level of privacy information leakage visible to ground targets is 1. f The next real-time assessment result is "moderate"; if The probability level of privacy information leakage visible to ground targets is 1. f The next real-time assessment result is "relatively serious"; if The probability level of privacy information leakage visible to ground targets is 1. f The immediate assessment result was "severe".

3. The method for real-time assessment of the risk of privacy information leakage to ground targets caused by suspicious drones according to claim 2, characterized in that, Step S1.3 specifically includes: Step S1.31: Based on the calculation results of step S1.21, sort the members of the organization to which the relevant person of the ground target belongs in descending order of importance; Step S1.32: Record the ranking number of the relevant person of the ground target as... l The total number of personnel in the organization is recorded as L Calculate the ranking ratio value of the importance of relevant persons of the ground target; the formula corresponding to the ranking ratio value is: （2） And step S1.4 specifically includes: Step S1.41: Based on the calculation results of step S1.32 z Determine the level of harm caused by the leakage of privacy information visible to ground targets; if If the ground target can see the privacy information being leaked, the level of harm is "severe"; if If the ground target can see the level of privacy information leakage as "relatively serious", then the level of harm is "relatively serious". If the privacy information of the ground target is visible, the level of harm is "moderate"; if If the privacy information leak is visible to ground targets, the risk level is "relatively minor"; if If the privacy information leaked is visible to ground targets, the risk level is "minor".

4. The method for real-time assessment of the risk of privacy information leakage to ground targets caused by suspicious drones according to claim 3, characterized in that, Step S4 includes: based on the assessment result of the leakage hazard level of the ground target's visible privacy information obtained in step S1.41 and the leakage probability level of the ground target's visible privacy information obtained in step S3.51, the following steps are taken: f The results of the real-time assessment, and based on the risk matrix shown in Table 1, at time points... t The risk level of leakage of privacy information visible to ground targets is determined. f Secondary real-time assessment; Table 1 Risk Matrix 。

Images