A dynamic ontology-based unmanned flight object threat assessment method and system

Abstract

The application discloses a kind of based on dynamic ontology's unmanned flight object threat assessment method and system, based on dynamic ontology analysis unmanned flight object threat factor, and entropy weight method and approximation ideal solution ordering method are used to calculate unmanned flight object threat factor index, and the threat level of unmanned flight object is quantitatively judged.The method includes: unmanned flight object flight characteristic analysis, for the sensitive area characteristics analysis of unmanned flight object, dynamic ontology construction of unmanned flight object threat factor, and based on dynamic ontology's unmanned flight object threat assessment model system construction.The present application can provide a reliable unmanned flight object threat assessment system for public safety, aviation and other fields, improve the identification, evaluation and response capability of unmanned flight target.

Description

Technical Field

[0001] This invention relates to a method for assessing threats to unmanned aerial vehicles (UAVs), and more particularly to a method and system for assessing threats to UAVs based on dynamic ontology. Background Technology

[0002] With the rapid development and widespread application of drone technology, its use in military, commercial, and personal fields is increasing. However, the proliferation of drones has also brought a series of security issues, especially unauthorized malicious activities in sensitive areas. These activities include, but are not limited to, illegal surveillance, illegal transportation, and interference with critical facilities. Therefore, assessing the threat level of unmanned aerial vehicles (UAVs) in sensitive areas, an extension of drone technology, is particularly important. Existing threat assessment systems for UAVs can identify potential threat sources by analyzing information such as the directional threat level, speed, and altitude of UAVs, and determine the threat level of UAVs based on factors such as the nature and scale of the threat. This helps relevant personnel determine preventive and countermeasure measures based on the target threat level, enabling timely and effective threat handling. However, most existing UAV threat assessment systems calculate and judge threats based on quantifiable indicators such as speed and altitude, but lack the ability to calculate indicators that are difficult to quantify, such as the area of ​​origin and directional threat level. Furthermore, existing commonly used threat assessment modeling methods, such as the analytic hierarchy process (AHP), suffer from computational complexity. Summary of the Invention

[0003] Purpose of the invention: To address the above problems, this invention proposes a method and system for assessing unmanned aerial vehicle (UAV) threats based on dynamic ontology, which can provide a reliable UAV threat assessment system for fields such as public safety and aviation, and improve the ability to identify, assess and respond to UAV targets.

[0004] Technical Solution: The technical solution adopted in this invention is a dynamic ontology-based method for assessing the threat of unmanned aerial vehicles, including:

[0005] Based on the flight characteristics of the target, analyze whether the target is an unmanned aerial vehicle (UAV).

[0006] For unmanned aerial vehicles (UAVs), a dynamic ontology original matrix is ​​constructed based on the motion characteristics of the UAVs and the range of sensitive areas. The dynamic ontology original matrix includes the threat factors of the UAVs in the current scene, the quantitative attributes of the threat factors, and the constraint rules in the threat scene.

[0007] Based on the original dynamic ontology matrix, the actual threat level of unmanned aerial vehicles (UAVs) is assessed using an unmanned aerial vehicle (UAV) threat assessment model. This includes: constructing threat indicator matrices for different threat levels and merging them with the original dynamic ontology matrix to obtain an original threat factor matrix; calculating the closeness of the original threat factor matrix using the entropy weight method combined with the approximation ideal solution ranking method; and obtaining the actual threat level of the UAV based on the closeness.

[0008] The analysis of whether a flight target is an unmanned aerial vehicle (UAV) based on its flight characteristics includes: distinguishing the UAV from other flight targets based on its motion state and appearance characteristics; describing the flight target attributes from the dimensions of flight speed, wheelbase, flight altitude, and endurance; and distinguishing the flight target from other common flight targets based on its attributes, including balloons, birds, fixed-wing aircraft, and rotary-wing helicopters.

[0009] The sensitive areas for unmanned aerial vehicles (UAVs) include: different levels of sensitive areas are determined based on relevant laws and regulations, air traffic control requirements, and flight time restrictions.

[0010] Threat factors for unmanned aerial vehicles (UAVs) include: distance between the UAV and important targets, directional threat level, flight speed, number, payload threat level, and flight altitude. Threat factors are adjusted for different scenarios, and a dynamic ontology original matrix is ​​constructed based on each threat factor.

[0011] The construction of threat indicator matrices for different threat levels includes: based on the original dynamic ontology matrix, determining the values ​​of each threat factor indicator for each threat level of the UAV target according to the indicator data corresponding to different threat levels in the current scenario; assigning values ​​to threat factor indicators that cannot be quantified using the Likert assignment method; and obtaining the threat indicator matrix based on the values ​​of each threat factor indicator for the UAV target corresponding to each threat level and the assigned values.

[0012] The calculation of the proximity of the original matrix of threat factors based on the entropy weight method combined with the approximation ideal solution ranking method includes:

[0013] The indicators in the original threat factor matrix are positiveized.

[0014] The original threat factor matrix after positive transformation is standardized to obtain the standardized original threat factor matrix;

[0015] For the standardized original matrix of threat factors, use the formula Calculate the weight of each threat factor indicator, where This represents the proportion of the i-th row and j-th column. This represents the standardized value in the i-th row and j-th column, where n is the total number of rows;

[0016] Use formula Calculate the entropy value for each threat factor indicator, where This represents the entropy value of the j-th index;

[0017] Use formula Calculate the weight of each indicator, where This represents the weight of the j-th column. Represents the coefficient of difference. ;

[0018] Use formula Calculate the weighted values, where The weighted value calculation result in the i-th row and j-th column is used to obtain the weighted normalization matrix;

[0019] Determine the positive and negative ideal solutions of the weighted normalization matrix, where the positive ideal solution is the maximum value of each column and the negative ideal solution is the minimum value of each column;

[0020] Using formula , Calculate the Euclidean distance between the positive and negative ideal solutions; where Let represent the Euclidean distance of the positive ideal solution in the i-th row of the weighted normalization matrix. Let represent the Euclidean distance of the negative ideal solution in the i-th row of the weighted normalized matrix, and m represent the total number of columns. Denotes the positive ideal solution of the j-th column. Represents the negative ideal solution of the j-th column;

[0021] Using formula Calculate the proximity of the original threat factor matrix, where This indicates the degree of closeness to the original matrix of threat factors.

[0022] The actual threat level of an unmanned aerial vehicle (UAV) is obtained based on the proximity rating by comparing the values ​​of the corresponding items for UAVs in the original threat factor matrix with the values ​​of the corresponding items for each threat level.

[0023] This invention proposes a dynamic ontology-based unmanned aerial vehicle (UAV) threat assessment system, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a dynamic ontology-based UAV threat assessment method.

[0024] This invention proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements a dynamic ontology-based method for assessing threats to unmanned aerial vehicles.

[0025] This invention proposes a computer program product, including a computer program and / or instructions, which, when executed by a processor, provides a method for assessing unmanned aerial vehicle threats based on dynamic ontology.

[0026] Beneficial Effects: Compared with existing technologies, this invention has the following advantages: 1. Based on dynamic ontology analysis of UAV threat factors, it is more flexible than existing fixed threat factor analysis, supports the construction of systematic indicators for sensitive factors in sensitive areas, and can quantify threats based on systematic indicators, thus more accurately assessing the threat level of UAVs; 2. It uses the entropy weight method combined with the approximation ideal solution ranking method to calculate the proximity of UAV threat factors, accurately quantifying and judging the threat level of UAVs; 3. It supports a dynamically adjustable quantitative assessment model for threat levels, can quantify the proximity assessment according to different threat levels, and can determine the threat level of UAVs through numerical comparison. Attached Figure Description

[0027] Figure 1 This is a flowchart of the unmanned aerial vehicle threat assessment method based on dynamic ontology described in this invention;

[0028] Figure 2 This is a diagram illustrating the target threat level proximity calculation process described in this invention. Detailed Implementation

[0029] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0030] The flowchart of the dynamic ontology-based threat assessment method for unmanned aerial vehicles described in this invention is as follows: Figure 1 As shown, the process includes: analyzing whether a flight target is an unmanned aerial vehicle (UAV) based on its flight characteristic attributes; for UAVs, determining and constructing a dynamic ontology original matrix based on the UAV's motion characteristics and the sensitive area range; the dynamic ontology original matrix includes the threat factors of the UAV in the current scenario, the quantitative attributes of the threat factors, and the constraint rules in the threat scenario; assessing the actual threat level of the UAV using an UAV threat assessment model based on the dynamic ontology original matrix, including: constructing threat indicator matrices for different threat levels and merging them with the dynamic ontology original matrix to obtain a threat factor original matrix; calculating the closeness of the threat factor original matrix using the entropy weight method combined with the approximation ideal solution ranking method; and obtaining the actual threat level of the UAV based on the closeness.

[0031] For example, there is a moving target with a relatively high speed, not carrying any other equipment, a wheelbase of approximately 250mm, a flight altitude of 20m, which has been flying for 5 minutes, is not within the no-fly zone, is located in the restricted flight zone around the airport, and is flying in the direction of the airport.

[0032] The first step is to analyze the flight characteristics of the moving target. In terms of flight speed, it is much faster than the speed of a balloon. In terms of shape, it is much smaller than a fixed-wing aircraft and a rotary-wing helicopter, but larger than most birds. At the same time, its flight altitude is lower than that of a fixed-wing aircraft. Therefore, it is determined that this moving target is an unmanned aerial vehicle.

[0033] The second step is to analyze the sensitivity of the area where this unmanned aerial vehicle (UAV) is located. From a time perspective, it is not currently within a no-fly zone, but its position is within a restricted flight zone and it is flying towards a prohibited flight zone. Therefore, it is determined that this UAV is in a medium-sensitive zone and is flying towards a high-sensitive zone.

[0034] The third step is to analyze the threat factors of the unmanned aerial vehicle (UAV). This analysis considers six dimensions: distance from the important target, directional threat level, flight speed, number, payload threat level, and flight altitude. Regarding the distance from the important target, this target is located in a medium-sensitive zone; regarding the flight direction, this target is flying towards a highly sensitive zone; regarding the flight speed, this target is currently moving at a relatively high speed; regarding the number, this target is a single entity; regarding the payload threat level, this target is not carrying any equipment and its payload is empty; regarding the flight altitude, this target is flying at a relatively low altitude of 20 meters.

[0035] The fourth step involves constructing a threat assessment model based on the threat factors analyzed in the third step. This model uses indicators such as distance to key targets, directional threat level, flight speed, quantity, payload threat level, and flight altitude as inputs for calculation and assessment. Normally, flight speed, quantity, flight altitude, and distance to key targets can be quantified, while directional threat level and payload threat level need to be determined using the Likert method for evaluation. Because the implementation method only demonstrates the specific implementation process, to simplify calculations, only three threat factors will be selected for assessment in subsequent calculations.

[0036] In this embodiment, the threat level is set to five levels, from level one to level five. Three indicators—distance from important targets, flight speed, and flight altitude—are selected to construct a threat assessment model. The values ​​of the indicators for threat levels that cannot be quantified are assigned using the Likert method. For example, the threat level values ​​for distance from important targets for levels one to five are 100 meters, 300 meters, 500 meters, 700 meters, and 900 meters, respectively; the threat levels for flight speed for levels one to five are 20 meters / second, 14 meters / second, 10 meters / second, 6 meters / second, and 2 meters / second, respectively; and the threat levels for flight altitude for levels one to five are 10 meters, 20 meters, 50 meters, 70 meters, and 100 meters, respectively. A threat indicator matrix for different threat levels is constructed, and further calculations are performed based on this matrix.

[0037] Assuming the drone target is 400 meters away from the important target, flies at a speed of 10 meters per second, and flies at an altitude of 20 meters, the original dynamic ontology matrix is ​​obtained. By merging the threat indicator matrices of different threat levels with the original dynamic ontology matrix, the original threat factor matrix is ​​obtained. The original threat factor matrix is ​​shown below (for ease of explanation, the matrix contents are presented in a table):

[0038] Table 1 Original matrix of threat factors

[0039]

[0040] In threat assessment of drones, the closer they are to important targets, the greater the threat level; that is, the lower the value of this indicator, the higher the threat level. Similarly, the higher the flight speed, the greater the threat level; and the lower the flight altitude, the greater the threat level; that is, the lower the value of this indicator, the higher the threat level. Based on this, each indicator is positively weighted, with maximum indicators remaining unchanged, and minimum indicators using a formula... Processing is carried out, among which This indicates a comparison of the j-th element in the i-th row of the matrix. This represents the maximum value in column j. In this example, we need to perform positive transformation on the distance to the important target and the flight altitude. The result after processing is shown below (for ease of explanation, the matrix content is represented in a table, and the numerical units are no longer shown after positive transformation):

[0041] Table 2 Original matrix of threat factors after positive transformation

[0042]

[0043] For the processed original threat factor matrix, use the formula Standardize all elements in the matrix, where Let represent the standardized result in the i-th row and j-th column of the matrix, where n represents the total number of rows. The original standardized threat factor matrix is ​​shown below (for ease of explanation, the matrix content is presented in tabular form, and the results are rounded to four decimal places):

[0044] Table 3. Standardized Original Matrix of Threat Factors

[0045]

[0046] Use formula The weight of each standardized value was calculated, and the results are shown in the table below (for ease of explanation, the matrix content is presented in tabular form, and the results are rounded to four decimal places):

[0047] Table 4 Standard Value Proportion Matrix

[0048]

[0049] Use formula Calculate the entropy value, where This represents the weight value of the i-th row and j-th column. A value of 0 can be set to 0.0001 to ensure logarithmic operations are possible. n is the total number of rows. In this example, the entropy value calculated for the distance (P) to the important target is... The entropy of the flight speed (V) is The entropy value of flight altitude (H) is Then use the formula The coefficient of difference can be obtained as follows: Using the formula The weight of the distance (P) to the important target can be obtained as follows: The weight of flight speed (V) is The weight of flight altitude (H) is All the above calculation results are rounded to four decimal places.

[0050] After obtaining the weights, use the formula Calculate the weighted values, where This represents the weighted value calculation result in the i-th row and j-th column. This represents the weight of the j-th column. Let represent the standardized result in row i and column j. The weighted standardized matrix obtained after calculation is shown in the table below (for ease of explanation, the matrix content is presented in tabular form, and the results are rounded to four decimal places):

[0051] Table 5 Weighted Standardization Matrix

[0052]

[0053] Then, the positive and negative ideal solutions of the weighted normalization matrix are determined, where the positive ideal solution... The maximum value in each column is the negative ideal solution. To find the minimum value in each column, we can obtain... , .

[0054] Using formula , ,in Let represent the Euclidean distance of the positive ideal solution in the i-th row of the weighted normalization matrix. Let represent the Euclidean distance of the negative ideal solution in the i-th row of the weighted normalized matrix, and m represent the total number of columns. Let be the element value of the weighted normalized matrix in the i-th row and j-th column. Denotes the positive ideal solution of the j-th column. Let represent the negative ideal solution in column j. In this example, the Euclidean distance of the positive ideal solution can be obtained. Euclidean distance of negative ideal solution (All results are rounded to four decimal places).

[0055] Using formula The closeness of the original threat factor matrix was calculated. .

[0056] The specific calculation process for closeness is as follows: Figure 2 As shown in the figure, a higher proximity score indicates a better data sample in that row. In this example, it indicates a higher threat level. The results clearly show that the proximity score of the drone target is 0.6620, which falls between Level 2 threat (0.7712) and Level 3 threat (0.5085). Therefore, when considering distance from important targets, flight speed, and flight altitude as threat factors, this target should be classified as a Level 3 threat target.

[0057] In one embodiment, a dynamic ontology-based unmanned aerial vehicle (UAV) threat assessment system is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the aforementioned dynamic ontology-based UAV threat assessment method.

[0058] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described dynamic ontology-based unmanned aerial vehicle threat assessment method.

[0059] In one embodiment, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the aforementioned dynamic ontology-based unmanned aerial vehicle threat assessment method.

[0060] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0061] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0062] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0063] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

Claims

1. A method for threat assessment of unmanned aerial vehicles based on dynamic ontology, characterized in that, include: Based on the flight characteristics of the target, analyze whether the target is an unmanned aerial vehicle (UAV). For unmanned aerial vehicles (UAVs), a dynamic ontology original matrix is ​​constructed based on the motion characteristics of the UAVs and the range of sensitive areas. The dynamic ontology original matrix includes the threat factors of the UAVs in the current scene, the quantitative attributes of the threat factors, and the constraint rules in the threat scene. Based on the original dynamic ontology matrix, the actual threat level of unmanned aerial vehicles (UAVs) is assessed using an unmanned aerial vehicle (UAV) threat assessment model. This includes: constructing threat indicator matrices for different threat levels and merging them with the original dynamic ontology matrix to obtain an original threat factor matrix; calculating the closeness of the original threat factor matrix using the entropy weight method combined with the approximation ideal solution ranking method; and obtaining the actual threat level of the UAV based on the closeness. The calculation of the proximity of the original matrix of threat factors based on the entropy weight method combined with the approximation ideal solution ranking method includes: The indicators in the original threat factor matrix are positiveized. The original threat factor matrix after positive transformation is standardized to obtain the standardized original threat factor matrix; For the standardized original matrix of threat factors, use the formula Calculate the weight of each threat factor indicator, where This represents the proportion of the i-th row and j-th column. This represents the standardized value in the i-th row and j-th column, where n is the total number of rows; Use formula Calculate the entropy value for each threat factor indicator, where This represents the entropy value of the j-th index; Use formula Calculate the weight of each indicator, where This represents the weight of the j-th column. Represents the coefficient of difference. ; Use formula Calculate the weighted values, where The weighted value calculation result in the i-th row and j-th column is used to obtain the weighted normalization matrix; Determine the positive and negative ideal solutions of the weighted normalization matrix, where the positive ideal solution is the maximum value of each column and the negative ideal solution is the minimum value of each column; Using formula , Calculate the Euclidean distance between the positive and negative ideal solutions; where Let represent the Euclidean distance of the positive ideal solution in the i-th row of the weighted normalization matrix. Let represent the Euclidean distance of the negative ideal solution in the i-th row of the weighted normalized matrix, and m represent the total number of columns. Denotes the positive ideal solution of the j-th column. Represents the negative ideal solution of the j-th column; Using formula Calculate the proximity of the original threat factor matrix, where This indicates the degree of closeness to the original matrix of threat factors.

2. The method for threat assessment of unmanned aerial vehicles based on dynamic ontology according to claim 1, characterized in that: The analysis of whether a flight target is an unmanned aerial vehicle (UAV) based on its flight characteristics includes: distinguishing the UAV from other flight targets based on its motion state and appearance characteristics; describing the flight target attributes from the dimensions of flight speed, wheelbase, flight altitude, and endurance; and distinguishing the flight target from other common flight targets based on its attributes, including balloons, birds, fixed-wing aircraft, and rotary-wing helicopters.

3. The method for threat assessment of unmanned aerial vehicles based on dynamic ontology according to claim 1, characterized in that: The sensitive areas for unmanned aerial vehicles (UAVs) include: different levels of sensitive areas are determined based on relevant laws and regulations, air traffic control requirements, and flight time restrictions.

4. The method for threat assessment of unmanned aerial vehicles based on dynamic ontology according to claim 1, characterized in that: Threat factors for unmanned aerial vehicles (UAVs) include: distance between the UAV and important targets, directional threat level, flight speed, number, payload threat level, and flight altitude. Threat factors are adjusted for different scenarios, and a dynamic ontology original matrix is ​​constructed based on each threat factor.

5. The method for threat assessment of unmanned aerial vehicles based on dynamic ontology according to claim 1, characterized in that: The construction of threat indicator matrices for different threat levels includes: based on the original dynamic ontology matrix, determining the values ​​of each threat factor indicator for each threat level of the UAV target according to the indicator data corresponding to different threat levels in the current scenario; assigning values ​​to threat factor indicators that cannot be quantified using the Likert assignment method; and obtaining the threat indicator matrix based on the values ​​of each threat factor indicator for the UAV target corresponding to each threat level and the assigned values.

6. The method for threat assessment of unmanned aerial vehicles based on dynamic ontology according to claim 1, characterized in that: The actual threat level of an unmanned aerial vehicle (UAV) is determined based on the proximity factor by comparing the values ​​of the corresponding items for UAVs in the original threat factor matrix with the values ​​of the corresponding items for each threat level.

7. A dynamic ontology-based unmanned aerial vehicle threat assessment system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the dynamic ontology-based unmanned aerial vehicle threat assessment method according to any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the dynamic ontology-based unmanned aerial vehicle threat assessment method according to any one of claims 1 to 6.

9. A computer program product, comprising a computer program and / or instructions, characterized in that, When the computer program and / or instructions are executed by the processor, they implement the dynamic ontology-based unmanned aerial vehicle threat assessment method according to any one of claims 1 to 6.

Images