A simulation scenario modeling method and system for unmanned aerial vehicle intelligence level testing

Abstract

The application belongs to the technical field of simulation test, and provides a simulation scene modeling method and system for unmanned aerial vehicle (UAV) intelligent level test. The method comprises the following steps: analyzing UAV intelligence capability according to UAV general confrontation process and OODA link, combining UAV intelligence capability to form a UAV test task; establishing a meta-model and a data hierarchical structure of a test scene according to the UAV test task, and obtaining a simulation test scene model; quantifying relevant data parameters based on a scene environment, a scene environment task, a scene obstacle threat and a scene task target, establishing a complexity model of the test scene, solving the complexity model by using an analytic hierarchy process, and determining each weight factor of the complexity model; and performing intelligent level test on a to-be-tested UAV according to UAV test scenes with different complexities. The application can more effectively and accurately realize intelligent level test on the to-be-tested UAV.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of simulation testing, and is a simulation scene modeling method and system for unmanned aerial vehicle (UAV) intelligent level testing. BACKGROUND

[0002] With the rapid development of modern science and technology, intelligent warfare is the development trend of future warfare, and unmanned aerial vehicles (UAVs) are the key role in intelligent warfare. The depth and breadth of the application of UAVs in various fields are increasing. As an important platform for future unmanned confrontation, it is crucial to determine the intelligent capability level of UAVs to improve the completion rate of the confrontation task of UAVs. At present, the test and test base of UAVs is still in the foundation construction period, and most of the test fields have single capability, which cannot meet the comprehensive test and test demand of the intelligent capability of UAV systems. At the same time, with the continuous improvement of the performance and system complexity of UAV equipment, the traditional test in the physical environment has been unable to meet the test of the performance and capability.

[0003] Simulation technology plays an important role in UAV training with its economy and repeatability, greatly reducing the risk of UAV test flight. At the same time, for the intelligent algorithm of UAV, including target recognition, task planning, and multi-UAV cooperative formation, more and more are verified in the simulation scene. Modeling the simulation scene for UAV intelligent level testing and determining the composition of the simulation test scene are key steps in building the simulation test scene. In addition, due to the complexity of the data involved in the UAV confrontation task and the difficulty in obtaining the data, the existing method cannot effectively test the UAV confrontation task.

[0004] Therefore, it is necessary to provide a simulation scene modeling method and system for UAV intelligent level testing to solve the above problems. SUMMARY

[0005] The present application aims to provide a simulation scene modeling method and system for UAV intelligent level testing to solve the technical problem that the data involved in the UAV confrontation task is complex and difficult to obtain in the prior art, and the existing method cannot effectively test the UAV confrontation task. The technical problem to be solved by the present application is solved by the following technical scheme.

[0006] The first aspect of the application provides a simulation scene modeling method for unmanned aerial vehicle intelligence level testing, comprising: establishing a meta-model and a data hierarchical structure of a test scene according to an unmanned aerial vehicle test task, to obtain a simulation test scene model; quantifying relevant data parameters based on a scene environment, a scene environment task, a scene obstacle threat and a scene task target, to establish a complexity model of the test scene; the scene task target comprises hidden target data, adversarial target data and dynamic target data; the complexity model is solved by using an analytic hierarchy process, to determine each weight factor of the complexity model of each test scene, and to further adjust each weight factor of the complexity model of each test scene; and the unmanned aerial vehicle to be tested is tested for intelligence level according to unmanned aerial vehicle test scenes of different complexities.

[0007] According to an optional embodiment, the following expression is used to establish the complexity model of the test scene:

[0008]

[0009] wherein C S represents the complexity model of the test scene; S m represents quantized state vectors corresponding to the scene environment, the scene environment task, the scene obstacle threat and the scene task target respectively, m is an index and is a positive integer, wherein the quantized state vector of the scene environment is S1=[S 11 , S 12 , S 13 ]=[A1, A2, A3, A4, A5, A6, A7], the quantized state vector of the scene environment task is S2=[B1, B2, B3, B4], and the quantized state vector of the scene obstacle threat is h is the number of obstacle threats in the scene, and k is the number of obstacle threats on the flight path of the unmanned aerial vehicle to the target; the quantized state vector of the scene task target is S4=[D1, D2, D3], wherein the meanings of A1 to D3 are shown in the data column of Table 1, and A1 to D3 take the complexity value column in Table 1 as values; represents a weight factor vector corresponding to the quantized state vectors of the scene environment, the scene environment task, the scene obstacle threat and the scene task target respectively, m is an index and is a positive integer; T is an inverted symbol; C SA represents the complexity of the scene environment, C SB represents the complexity of the scene environment task, C SC represents the complexity of the scene obstacle threat, C SD represents the complexity of the scene task target,

[0010] According to an optional embodiment, further comprising: establishing an importance weight factor vector according to the importance of the quantized state vector corresponding to the scene environment, the scene environment task, the scene obstacle threat and the scene task target, and adjusting each weight factor of the complexity model of each test scene by using the following expression:

[0011]

[0012] wherein, w r represents the weight factor of the element quantized state of the rth test scene; z s represents the importance corresponding to the geographic environment data, the electromagnetic environment data, the weather environment data, the scene environment task data, the scene obstacle threat data and the scene task target data in the test scene, and s is the element value index of the vector Z, which is determined by r; z t represents the comprehensive value of the importance corresponding to the geographic environment data, the electromagnetic environment data, the weather environment data, the scene environment task data, the scene obstacle threat data and the scene task target data in the test scene, and t is 1, 2, 3, 4, 5 or 6.

[0013] According to an optional embodiment, comprising: constructing a judgment matrix according to the data hierarchical structure of the simulation test scene model established by the analytic hierarchy process, and using the scale method to calculate each weight factor of the complexity model of the test scene.

[0014] According to an optional embodiment, further comprising: calculating the consistency index of each constructed judgment matrix respectively by using the following expression, so as to judge the consistency of all constructed judgment matrices:

[0015]

[0016] wherein, CR i represents the consistency index of the ith judgment matrix, i={S6, A7, B4, C6, D3}; λ max，i represents the maximum eigenvalue of the ith judgment matrix, RI i represents the random consistency index corresponding to the order of the ith judgment matrix; n i represents the order of the ith judgment matrix.

[0017] When the consistency index of all constructed judgment matrices is less than a specified value, it is indicated that all constructed judgment matrices meet the consistency.

[0018] According to an optional implementation, the quantifying the relevant data parameters comprises: quantifying the following relevant data parameters according to the capabilities required for the unmanned aerial vehicle test task: scene size, scene type, electromagnetic signal type and style, electromagnetic signal density, visibility, wind speed, weather type, environment quantity, electromagnetic environment quantity, task quantity, obstacle size, obstacle height, threat range, threat type, dynamics, concealment, and countermeasures; and determining the complexity of each relevant data parameter according to the quantification results of the relevant data parameters.

[0019] According to an optional implementation, the method comprises: providing scene environment task data and scene obstacle threat quantity, repeatedly determining whether the specified quantity of each data is met, updating the quantity count each time the determination is performed, and determining that the specified quantity of each data is met until the simulation test scene model is completed.

[0020] According to an optional implementation, the simulation test scene model is established based on the MOF element, and specifically comprises: concretizing the following data abstracted from the model layer to form a data structure required for establishing the simulation test scene model: geographic environment, weather environment, electromagnetic environment, obstacle threat, scene task, and task target.

[0021] The second aspect of the present application provides a simulation scene modeling system for unmanned aerial vehicle intelligence level testing, which uses the simulation scene modeling method for unmanned aerial vehicle intelligence level testing according to the first aspect of the present application. The simulation scene modeling system comprises: a first establishing module configured to establish a meta-model and a data hierarchical structure of a test scene according to an unmanned aerial vehicle test task, and obtain a simulation test scene model; a second establishing module configured to quantize relevant data parameters based on a scene environment, a scene environment task, a scene obstacle threat, and a scene task target, and establish a complexity model of the test scene; the scene task target comprises concealment target data, countermeasure target data, and dynamic target data; a determining processing module configured to solve the complexity model by using an analytic hierarchy process, determine each weight factor of the complexity model of each test scene, and further adjust each weight factor of the complexity model of each test scene; and a test processing module configured to perform intelligence level testing on a test unmanned aerial vehicle according to different complexity of the test unmanned aerial vehicle test scene.

[0022] The third aspect of the present application provides an electronic device, comprising: one or more processors; a storage device configured to store one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors implement the simulation scene modeling method for unmanned aerial vehicle intelligence level testing according to the first aspect of the present application.

[0023] The fourth aspect of the present application provides a computer readable medium, which stores a computer program, and the computer program is executed by a processor to realize the simulation scene modeling method for unmanned aerial vehicle intelligence level test.

[0024] The present application has the following advantages:

[0025] Compared with the prior art, the simulation scene modeling method for unmanned aerial vehicle intelligence level test is provided, the meta-model and data hierarchical structure of the test scene are established according to the unmanned aerial vehicle test task, the simulation test scene model is obtained, the related data parameters are quantified based on the scene environment, the scene environment task, the scene obstacle threat and the scene task target, and the complexity model of the test scene is established more accurately, the complexity model is solved by using the analytic hierarchy process, each weight factor of the complexity model of each test scene is determined, each weight factor of the complexity model of each test scene is further adjusted, the unmanned aerial vehicle intelligence level test is performed on the unmanned aerial vehicle to be tested according to unmanned aerial vehicle test scenes with different complexities, and the unmanned aerial vehicle intelligence level test can be more effectively and accurately realized. BRIEF DESCRIPTION OF DRAWINGS

[0026] Figure 1 is a step flow chart of an example of the simulation scene modeling method for unmanned aerial vehicle intelligence level test of the present application;

[0027] Figure 2 is a schematic diagram of the unmanned aerial vehicle intelligence capability for the unmanned aerial vehicle intelligence level test of the present application;

[0028] Figure 3 is a schematic diagram of the unmanned aerial vehicle intelligence capability for the unmanned aerial vehicle intelligence level test of the present application;

[0029] Figure 4 is a schematic diagram of the simulation test scene model in the simulation scene modeling method for unmanned aerial vehicle intelligence level test of the present application;

[0030] Figure 5 is a schematic diagram of the data structure hierarchy of the simulation test scene model in the simulation scene modeling method for unmanned aerial vehicle intelligence level test of the present application;

[0031] Figure 6 is a flowchart of another angle of constructing the simulation test scene model in the simulation scene modeling method for unmanned aerial vehicle intelligence level test of the present application;

[0032] Figure 7 is a schematic diagram of an example of the simulation scene modeling system for unmanned aerial vehicle intelligence level test of the present application;

[0033] Figure 8is a structural schematic diagram of an electronic device embodiment according to the present application;

[0034] Figure 9 is a structural schematic diagram of a computer readable medium embodiment according to the present application. DETAILED DESCRIPTION

[0035] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0036] In view of the above problems, the present application provides a simulation scene modeling method for unmanned aerial vehicle intelligent level testing, which establishes a meta-model and a data hierarchical structure of a test scene according to an unmanned aerial vehicle testing task, obtains a simulation test scene model, quantifies relevant data parameters based on a scene environment, a scene environment task, a scene obstacle threat and a scene task target, establishes a more accurate complexity model of the test scene by adjusting each weight factor of the complexity model of each test scene, solves the complexity model by using an analytic hierarchy process, determines each weight factor of the complexity model of each test scene, further adjusts each weight factor of the complexity model of each test scene, and tests the intelligent level of a to-be-tested unmanned aerial vehicle according to unmanned aerial vehicle testing scenes of different complexities, which can more effectively and accurately realize intelligent level testing of the to-be-tested unmanned aerial vehicle.

[0037] Embodiment 1

[0038] The simulation scene modeling method for unmanned aerial vehicle intelligent level testing of the present application will be described in detail below with reference to Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 and Figure 6 .

[0039] Figure 1 is a step flowchart of an example of the evaluation index weight determination method based on the correlation between evaluation indexes of the present application.

[0040] First, in step S101, a meta-model and a data hierarchical structure of a test scene are established according to an unmanned aerial vehicle testing task, and a simulation test scene model is obtained.

[0041] Specifically, the unmanned aerial vehicle testing task includes a reconnaissance testing task, a strike testing task or a confrontation testing task, and a maneuver testing task corresponding to a reconnaissance task, a strike task or a confrontation task, and a maneuver task.

[0042] For example, a plurality of intelligent capabilities of the unmanned aerial vehicle are combined to form the unmanned aerial vehicle testing task.

[0043] It should be noted that according to the unmanned aerial vehicle confrontation task, the OODA link (Observe-Orient-Decide-Act link) containing observation, judgment, decision and action is considered, which can be specifically referred to Figure 2 . The confrontation test task flow of the unmanned aerial vehicle is constructed as five parts of environment detection, target identification, situation generation, task planning, attack / investigation / maneuver. Among them, environment detection and target identification belong to "observation", environment detection collects real-time confrontation environment information through various sensors to provide raw input data for all subsequent decisions, and target identification parses specific entities from the collected information to provide target characteristic data for judgment and decision. Situation generation belongs to "judgment", based on the detected information, real-time battlefield situation map is formed through data analysis, fusion and modeling, so that the commander and the unmanned aerial vehicle system can correctly understand and evaluate the current combat situation to provide basis for next action decision. Task planning belongs to the "decision" part, on the basis of fully understanding the confrontation situation, a specific and current task plan is made. Investigation / confrontation / maneuver belongs to "action", in the investigation action, the unmanned aerial vehicle executes the reconnaissance task according to the task planning, collects detailed battlefield information, in the maneuver action, the unmanned aerial vehicle executes the confrontation task, implements precise attack on the specified target, and in the maneuver action, the unmanned aerial vehicle performs maneuver flight, avoids the air defense firepower of the other party, adapts to the change of the battlefield environment or adjusts the action direction and position according to the instruction.

[0044] According to the general operation process of the unmanned aerial vehicle, the intelligent capabilities of the unmanned aerial vehicle are divided into observation capability, judgment capability, decision capability and action capability, as shown in Figure 3 . The observation capability is mainly reflected in the detection and identification capability of the unmanned aerial vehicle to the environment and the target, including the detection of the environment information of the unmanned aerial vehicle and the cognitive identification of the target. The judgment capability reflects the situation analysis capability of the unmanned aerial vehicle to the battlefield, the evaluation of the target threat by the unmanned aerial vehicle, and the construction of the battlefield situation. The decision capability mainly reflects the planning capability of the unmanned aerial vehicle to the action, including task planning, flight path planning and maneuver decision. The action capability reflects the execution capability of the unmanned aerial vehicle to the planned behavior, including the investigation action to the target, the attack action to the target and the maneuver action of the unmanned aerial vehicle.

[0045] Further, according to the above intelligent capability of the unmanned aerial vehicle, the meta-model and data hierarchical structure of the test scene are established.

[0046] Specifically, the simulation test scene model is established based on the MOF meta. As shown in Figure 4 , it specifically includes the following contents:

[0047] Step S201: Constructing the meta-meta model layer (i.e., M3 layer), according to the intelligent capabilities of the UAV, forming a UAV test task by combining multiple intelligent capabilities. According to the UAV confrontation task and the intelligent capabilities of the UAV, the test task is configured, for example, four test tasks are configured: target reconnaissance, UAV maneuvering, target jamming attack, and target fire attack. For the target reconnaissance task, the target reconnaissance task is defined as the UAV executing a reconnaissance task, detecting obstacles and threats to the target during the flight process, detecting threats after detecting obstacles, evaluating threats, constructing a confrontation situation, planning a route to avoid threats, obtaining specific information of the reconnaissance task target, and returning to a designated location. The intelligent capabilities required by the UAV for the target reconnaissance task include environmental information detection, target sensing identification, target threat evaluation, battlefield situation construction, route planning, task planning, maneuvering decision, reconnaissance action, and maneuvering action.

[0048] Step S202: Constructing the meta model layer (i.e., M2 layer), according to the related concepts and requirements of the UAV test task, abstracting the scene meta model required for testing the intelligent capabilities of the UAV. According to the test task, the scene meta model includes: scene environment data, scene obstacle threat data, scene task target data, and scene environment task data. The scene environment data refers to the environmental state data of the UAV executing a combat task. The scene obstacle threat data refers to the state data of the obstacles encountered by the UAV during the task execution process. The scene task target data refers to the state data of the task target in the test task. The scene environment task data refers to the number of different scene environments passed through by the UAV during the flight process and the number of tasks executed.

[0049] Step S203: constructing a model layer (i.e., M1 layer), and concretizing the four types of data abstracted in the M2 meta-model layer to form data structures required for modeling, specifically including data structures of the six-tuple of geographic environment, weather environment, electromagnetic environment, obstacle threat, scene task, and task target. The geographic environment refers to the geographic spatial scale and geographic spatial related features where the UAV performs the flight task, including two-dimensional data of scene size and scene type. The weather environment refers to the meteorological conditions faced by the UAV when performing the confrontation task, described by three-dimensional data of visibility, wind speed, and weather type. The electromagnetic environment refers to the overall condition of electromagnetic phenomena faced by the UAV when performing the confrontation task, specifically including two-dimensional data of electromagnetic signal type and pattern, and electromagnetic signal density. The obstacle threat is modeled by six-dimensional data of obstacle size, obstacle height, threat range, threat type, dynamicity, and concealment. The task target is modeled by three-dimensional data of concealment, dynamicity, and confrontation. The environment task includes four-dimensional data of geographic environment quantity, weather environment quantity, electromagnetic environment quantity, and task quantity. The M3 model layer is expressed as an XML document model. Based on the XML coding format, the six-tuple data structures are provided with XML model documents, and the test scene model is represented by the XML document model.

[0050] Step S204: constructing an object layer (i.e., M0 layer), which quantifies the parameters in the six-tuple data structure of the UAV intelligent capability test scene model, and provides parameter data for the scene model, as shown in Table 1. The data of the object layer is stored in the XML document model of the M1 layer, and an XML format simulation test scene model object is generated.

[0051] The following data abstracted from the model layer is concretized to form the data required for establishing the simulation test scene model: geographic environment, weather environment, electromagnetic environment, obstacle threat, scene task, and task target (specifically corresponding to Figure 5 “geographic environment data S1, electromagnetic environment data S2, weather environment data S3, scene environment task data S4, scene obstacle threat data S5, and scene task target data S6”). Further, a data structure hierarchical composition diagram of the simulation test scene model is formed as shown in Figure 5

[0052] In an embodiment, the construction of the simulation test scene model includes the following steps:

[0053] Step S301: providing scene environment task data and scene obstacle threat quantity.

[0054] As shown in Figure 6 , the provision of the scene environment task data includes the provision of electromagnetic environment data, task target data, geographic environment data, and the provision of obstacle threat data. ​

[0055] Further, a specified number corresponding to each data is also provided for performing the repeating judgment step.

[0056] Step S302: Repeating the judgment of whether the specified number of each data is met, the number count is updated once for each judgment until the specified number of each data is determined (also referred to as "repeating judgment step").

[0057] For each type of data provided, the judgment of whether the specified number of each data is met is repeated, and the number of the current data judged is incremented by one (corresponding to "number plus one" shown in the middle) to update the count value (i.e., the number count is updated) until the specified number of the current data is determined. Figure 6

[0058] In a specific embodiment, the above-mentioned repeating judgment step can also be performed simultaneously for all data until the specified number of each data is determined, and the repeating judgment step is stopped.

[0059] Step S303: When the specified number of each data is determined, the simulation test scenario model is completed.

[0060] It should be noted that the above is only described as an optional example and cannot be understood as a limitation of the present application.

[0061] Next, in step S102, based on the scene environment, scene environment task, scene obstacle threat and scene task target, the relevant data parameters are quantified, and the complexity model of the test scenario is established; the scene task target includes concealment target data, adversarial target data and dynamic target data.

[0062] Specifically, based on the scene environment, scene environment task, scene obstacle threat and scene task target, the relevant data parameters are quantified.

[0063] According to the ability required for the unmanned aerial vehicle test task, the following relevant data parameters are quantified: scene size, scene type, electromagnetic signal type and style, electromagnetic signal density, visibility, wind speed, weather type, environment quantity, electromagnetic environment quantity, task quantity, obstacle size, obstacle height, threat range, threat type, dynamic, concealment and adversarial. According to the quantification results of the relevant data parameters, the complexity (i.e., complexity value) of each relevant data parameter is determined. For details, see Table 1 below.

[0064] Table 1

[0065]

[0066]

[0067] ​Table 1 is a data structure parameter quantization table of the simulation test scene model. Note: K1 in the electromagnetic signal type and pattern A3 means the number of patterns and types of electromagnetic signals that can be detected and identified by the unmanned aerial vehicle under normal working conditions, and K2 means the number of types and patterns of signals that the unmanned aerial vehicle can tolerate at most.

[0068] The following specifically explains how to model the complexity of the simulation test scene. According to the data structure layering of the simulation test scene model (see Figure 5 for details), the test scene complexity is modeled based on the four-tuple metadata of the scene environment, the scene environment task, the scene obstacle threat, and the scene task target.

[0069] The following expression is used to establish the complexity model of the test scene (i.e., the simulation test scene):

[0070]

[0071] wherein C S represents the complexity model of the test scene; S m represents the quantized state vectors corresponding to the scene environment, the scene environment task, the scene obstacle threat, and the scene task target, respectively, m is a subscript and a positive integer, and S m = [S1, S2, S3, S4], wherein the quantized state vector of the scene environment is S1 = [S 11 , S 12 , S 13 ] = [A1, A2, A3, A4, A5, A6, A7], the quantized state vector of the scene environment task is S2 = [B1, B2, B3, B4], and the quantized state vector of the scene obstacle threat is h is the number of obstacle threats in the scene, and k is the number of obstacle threats on the flight path of the unmanned aerial vehicle to the target. The quantized state vector of the scene task target is S4 = [D1, D2, D3], wherein the meanings of A1 to D3 are described in the data column of Table 1, and the values of A1 to D3 are the complexity values in Table 1; represents the weight factor vectors corresponding to the quantized state vectors of the scene environment, the scene environment task, the scene obstacle threat, and the scene task target, respectively, m is a subscript and a positive integer; T is an inverted symbol, and W m = [W1, W2, W3, W4]. C SA represents the complexity of the scene environment, C SB represents the complexity of the scene environment task, C SC represents the complexity of the scene obstacle threat, C SD represents the complexity of the scene task target,

[0072] The state vector corresponds to the weight factor vector using the following expression:

[0073] W1=[W 11 W 12 W 13 ]=[w1w2w3w4w5w6w7] (2)

[0074] W2=[w8w9w 10 w 11 ] (3)

[0075] W3=[w 12 w 13 w 14 w 15 w 16 w 17 ] (4)

[0076] W4=[w 18 w 19 w 20 ] (5)

[0077] Specifically, the scene environment complexity is as follows:

[0078]

[0079]

[0080] Wherein, the value of a is from 0 to the number of geographic environments in the test scene, and the term means that the state of the most complex geographic environment is taken as part of the scene complexity value; the value of b is from 0 to the number of electromagnetic environments in the test scene, and the term means that the state of the most complex electromagnetic environment is taken as part of the scene complexity value; the value of c is from 0 to the number of weather environments in the test scene, and the term means that the state of the most complex weather environment is taken as part of the scene complexity value; the value of d is from 0 to the number of tasks in the test scene, and the term means that the state of the most complex task is taken as part of the scene complexity value.

[0081] Meanwhile, considering the importance of the 4-tuple 6-dimensional data structure S1=[S 11 , S 12 , S 13 ], S2, S3, S4, S5, S6, the weight factor vector Z representing the importance of the geographic environment data S1, the electromagnetic environment data S2, the weather environment data S3, the scene environment task data S4, the scene obstacle threat data S5, and the scene task target data S6 in the test scene is established,

[0082] Z=[z1 z2 z3 z4 z5 z6] (8)

[0083] wherein, z s represents the importance of the above-mentioned 6-dimensional state data, specifically the weight factor of the importance degree of the geographic environment data S1, the electromagnetic environment data S2, the weather environment data S3, the scene environment task data S4, the scene obstacle threat data S5, and the scene task target data S6 in the test scene; according to the obtained vector Z, the weight factor w r

[0084]

[0085] wherein, w r represents the weight factor of the element quantized state (specifically the quantized state of the data to be evaluated) of the rth test scene; z s represents the importance degree corresponding to the geographic environment data, the electromagnetic environment data, the weather environment data, the scene environment task data, the scene obstacle threat data, and the scene task target data in the test scene, s is the element value index of the vector Z, and the value of s is determined by r; z t represents the comprehensive value of the importance degree corresponding to the geographic environment data, the electromagnetic environment data, the weather environment data, the scene environment task data, the scene obstacle threat data, and the scene task target data in the test scene, and t takes the value of 1-6, i.e. t is 1, 2, 3, 4, 5, or 6. Specifically, the value of s is determined by r, as shown in formula (9), when r ∈ [1, 2] and r is a positive integer, s = 1. The test scene specifically refers to the task test scene corresponding to the reconnaissance test task, the strike test task or the countermeasure test task, and the maneuver test task.

[0086] The weight factor is normalized to satisfy the following conditional expression.

[0087]

[0088] Further, the unmanned aerial vehicle intelligence level evaluation model is established according to the simulation test scene complexity. Since C S ∈ [0, 1], the simulation test scene complexity can be divided into four levels and mapped to a four-level unmanned aerial vehicle intelligence level evaluation model, and the correspondence between the test scene model complexity and the unmanned aerial vehicle intelligence level is shown in Table 2.

[0089] Table 2

[0090]

[0091] Table 2 is a mapping table of the simulation test scene complexity and the unmanned aerial vehicle intelligence level.

[0092] ​Next, in step S103, the analytic hierarchy process is used to solve the complexity model to determine the weight factors of the complexity model of each test scenario, and further adjust the weight factors of the complexity model of each test scenario.

[0093] The analytic hierarchy process is used to solve the scene complexity model, specifically to solve the weight factor vectors of the scene complexity model, and specifically to solve the weight factor vectors W1, W2, W3, W4 corresponding to the quantized state vectors of the scene environment, scene environment task, scene obstacle threat, and scene task target, respectively.

[0094] Using the scale method (see Table 3 for details), according to the data hierarchical structure of the simulation test scene model established by the analytic hierarchy process, a judgment matrix is constructed to calculate the weight factors of the complexity model of the test scene.

[0095] If the W1-W4, Z vector length is n, the constructed symmetric judgment matrix A={a ij}∈R n×n , where a ij >0, describes the relative importance of the ith element and the jth element. At the same time, the diagonal elements are 1, and

[0096] a ij a ji =1, i=1K n, j=1K n

[0097] Table 3

[0098]

[0099] Table 3 is a 1-9 scale table for two elements that affect the unmanned aerial vehicle intelligence level evaluation model.

[0100] It should be noted that the elements in Table 3 specifically refer to Figure 5 S1-S6, A1-A7, B1-B4, C1-C6, D1-D3 in Table 3, i.e., any two data at the same level in the data to be evaluated, such as geographic environment data S1 and electromagnetic environment data S2, geographic environment data S1 and weather environment data S3, scene environment task data S4 and scene obstacle threat data S5. For example, environmental data B1 and weather environment quantity B2, dynamic C5 and concealment C6, wind speed A6 and weather type A7, etc.

[0101] According to the comprehensive judgment of the importance of each index by multiple experts, and in combination with the 1-9 scale method shown in Table 3, five judgment matrices are constructed for the importance scores of the data.

[0102]

[0103]

[0104]

[0105]

[0106]

[0107] Specifically, the above A S6 is a judgment matrix constructed based on geographic environment data S1, electromagnetic environment data S2, weather environment data S3, scene environment task data S4, scene obstacle threat data S5, and scene task target data S6 in a test scenario. A7 is a judgment matrix constructed based on scene size A1, scene type A2, and electromagnetic signal type and style A3. B4 is a judgment matrix constructed based on environment quantity B1, weather environment quantity B2, electromagnetic environment quantity B3, and task quantity B4. C6 is a judgment matrix constructed based on obstacle size C1, obstacle height C2, threat type C3, threat range C4, dynamicity C5, and concealment C6. D3 is a judgment matrix constructed based on concealment D1, dynamicity D2, and countermeasurability D3.

[0108] The consistency of the judgment matrix is determined according to the following formula, where RI i is a random consistency index, and the values are shown in Table 4.

[0109] The consistency index of each constructed judgment matrix is calculated using the following expression, so as to determine the consistency of all constructed judgment matrices:

[0110]

[0111] where CR i represents the consistency index of the ith judgment matrix, i = {S6, A7, B4, C6, D3}; λ max，i represents the maximum eigenvalue of the ith judgment matrix, RI i represents the random consistency index corresponding to the order of the ith judgment matrix; and n i represents the order of the ith judgment matrix.

[0112] When the consistency index of all constructed judgment matrices is less than a specified value, it is indicated that all constructed judgment matrices meet the consistency. The specified value is, for example, 0.1.

[0113] Table 4

[0114]

[0115] Table 4 is a random consistency index RI value table.

[0116] For example, in an example, the following consistency index is calculated.

[0117] The maximum eigenvalue of matrix A S6 A A7 A B4 A C6 A D3 is calculated respectively, and substituted into the consistency index calculation formula to obtain the following results:

[0118] CR s6 = 0.0539, CR A7 = 0.0510, CR B4 = 0.0224, CR C6 = 0.0185, CR D3 = 0.0079.

[0119] The consistency index value of each judgment matrix is less than 0.1, so the judgment matrix satisfies the consistency condition. The above calculation results show that the judgment matrix constructed by the data hierarchical structure of S1, S2, S3, S4, S5 and S6 is reasonable. Figure 5

[0120] By selecting the corresponding eigenvector of the maximum eigenvalue in the judgment matrix A S6 and normalizing it, the weight factor vector Z is obtained:

[0121] Z = [0.4470 0.3040 0.2520 0.7850 0.1312 0.1044]

[0122] Then, the corresponding eigenvector of the maximum eigenvalue of the judgment matrix A A7 A B4 A C6 A D3 is calculated respectively and normalized to obtain the corresponding weight factor.

[0123] Further, according to the importance Z of the six-dimensional data of the geographic environment data S1, the electromagnetic environment data S2, the weather environment data S3, the scene environment task data S4, the scene obstacle threat data S5 and the scene task target data S6 in the test scene, the weight factors are adjusted by using the above expression (9), and the values of the weight factors are finally obtained:

[0124] W1 = [W 11 W 12 W 13 ] = [0.1108 0.0592 0.0123 0.0117 0.0181 0.0305 0.0181]

[0125] ​W2 = [0.1968 0.1968 0.1190 0.0558]

[0126] W3 = [0.0056 0.0056 0.0369 0.0145 0.0103 0.0220]

[0127] W4 = [0.0408 0.0225 0.0124].

[0128] Next, in step S104, intelligent level testing is performed on the unmanned aerial vehicle to be tested according to unmanned aerial vehicle test scenes of different complexities.

[0129] In one embodiment, intelligent level testing is performed on a target unmanned aerial vehicle in a simulation test scene of a target reconnaissance test task.

[0130] In an unmanned aerial vehicle reconnaissance test task, the unmanned aerial vehicle to be tested is to conduct reconnaissance on a stationary, non-threatening, camouflaged target at a known location in a forest of, for example, 8x8 kilometers, the weather environment is sunny, the visibility is greater than 5 kilometers, the wind speed is 5 m / s, only conventional type electromagnetic signals exist, and the ratio of the electromagnetic environment signal density to the signal density that the unmanned aerial vehicle to be tested can withstand is 0.1, 10 threat obstacles are set in the scene, which are non-threatening, stationary, and have no concealment, the detection range of the unmanned aerial vehicle to be tested is greater than the threat range of the obstacles, and the height is less than 25 meters, and the size is between 1 meter and 10 meters, of which 5 obstacles are on the straight line path of the unmanned aerial vehicle to be tested and the target. The environment, weather environment, and electromagnetic environment tasks in the test scene do not change. For example, searching for a stationary, non-threatening, camouflaged target in the test scene, the target of the unmanned aerial vehicle reconnaissance test task is, for example, an enemy command vehicle sprayed with green camouflage in the jungle.

[0131] According to the description of the simulation test scene, the characterization vectors of the scene environment, scene changes, scene obstacle threats, and scene task targets are represented as:

[0132] S1 = [S 11 S 12 S 13 ] = [0.34 0.5 0 0.1 0 0.34 0]

[0133] S2 = [0 0 0 0]

[0134] S3 = [0.335 0.17 0 0 0 0]

[0135] S4 = [1 0]

[0136] According to the simulation test scene complexity model, the following is obtained:

[0137] Cs = 0.07819 + 0 + 0.1108 + 0 = 0.1224

[0138] According to Table 2, the unmanned aerial vehicle to be tested is tested in the simulation test scene with a complexity of 0.1224, and if the unmanned aerial vehicle to be tested completes the test task in the simulation test scene, the intelligent level of the unmanned aerial vehicle to be tested is Level 1.

[0139] It should be noted that the above is only described as an optional example and cannot be understood as a limitation of the present application.

[0140] Compared with the prior art, the present application is a simulation scene modeling method for unmanned aerial vehicle intelligent level testing, which establishes a meta-model and a data hierarchical structure of the test scene according to the unmanned aerial vehicle test task, obtains a simulation test scene model, quantifies relevant data parameters based on the scene environment, scene environment task, scene obstacle threat and scene task target, and establishes a more accurate complexity model of the test scene. The complexity model is solved by using the analytic hierarchy process to determine the weight factors of each test scene complexity model, and the weight factors of each test scene complexity model are further adjusted. According to the unmanned aerial vehicle test scene with different complexity, the intelligent level of the unmanned aerial vehicle to be tested is tested, which can more effectively and accurately realize the intelligent level testing of the unmanned aerial vehicle to be tested.

[0141] Embodiment 2

[0142] The following is an embodiment of the system of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the system embodiments of the present application, please refer to the method embodiments of the present application.

[0143] Figure 7 is a structural schematic diagram of an example of a simulation scene modeling system for unmanned aerial vehicle intelligent level testing according to the present application.

[0144] The following will be described with reference to Figure 7 The simulation scene modeling system for unmanned aerial vehicle intelligent level testing will be described, which uses the simulation scene modeling method of the first aspect of the present application.

[0145] The simulation scene modeling system 600 includes a first establishing module 610, a second establishing module 620, a determining processing module 630 and a testing processing module 640.

[0146] Specifically, the first establishing module 610 establishes a meta model and a data hierarchical structure of the test scene according to the unmanned aerial vehicle test task, and obtains a simulation test scene model. The second establishing module 620 quantifies relevant data parameters based on a scene environment, a scene environment task, a scene obstacle threat and a scene task target, and establishes a complexity model of the test scene. The scene task target includes concealment target data, adversarial target data and dynamic target data. The determining processing module 630 solves the complexity model by using an analytic hierarchy process, determines each weight factor of the complexity model of each test scene, and further adjusts each weight factor of the complexity model of each test scene. The test processing module performs intelligent level testing on the unmanned aerial vehicle to be tested according to unmanned aerial vehicle test scenes of different complexities.

[0147] According to an optional embodiment, the following expression is used to establish the complexity model of the test scene:

[0148]

[0149] wherein C S represents the complexity model of the test scene; S m represents a quantized state vector corresponding to the scene environment, the scene environment task, the scene obstacle threat and the scene task target respectively, m is a subscript and is a positive integer, wherein the quantized state vector of the scene environment is S1=[S 11 , S 12 , S 13 ]=[A1, A2, A3, A4, A5, A6, A7], the quantized state vector of the scene environment task is S2=[B1, B2, B3, B4], and the quantized state vector of the scene obstacle threat is h is the number of obstacle threats in the scene, and k is the number of obstacle threats on the flight path of the unmanned aerial vehicle to the target. The quantized state vector of the scene task target is S4=[D1, D2, D3], wherein the meanings of A1 to D3 are shown in the data column of Table 1, and A1 to D3 take the complexity value column in Table 1 as values; represents a weight factor vector corresponding to the quantized state vector of the scene environment, the scene environment task, the scene obstacle threat and the scene task target respectively, m is a subscript and is a positive integer; T is an inverted symbol. C SA represents the complexity of the scene environment, C SB represents the complexity of the scene environment task, C SC represents the complexity of the scene obstacle threat, C SD represents the complexity of the scene task target,

[0150] According to an optional embodiment, further comprising: establishing an importance weight factor vector according to the importance of the quantized state vector corresponding to the scene environment, the scene environment task, the scene obstacle threat and the scene task target, and adjusting each weight factor of the complexity model of each test scene by using the following expression:

[0151]

[0152] wherein, w r represents the weight factor of the element quantized state of the rth test scene; z s represents the importance corresponding to the geographic environment data, the electromagnetic environment data, the weather environment data, the scene environment task data, the scene obstacle threat data and the scene task target data in the test scene, and s is the element value index of the vector Z, which is determined by r; z t represents the comprehensive value of the importance corresponding to the geographic environment data, the electromagnetic environment data, the weather environment data, the scene environment task data, the scene obstacle threat data and the scene task target data in the test scene, and t is 1, 2, 3, 4, 5 or 6. The test scene specifically refers to the task test scene corresponding to the reconnaissance test task, the strike test task or the countermeasure test task, and the maneuver test task.

[0153] According to an optional embodiment, the scale method is used to construct a judgment matrix according to the data hierarchical structure of the simulation test scene model established by the analytic hierarchy process, so as to calculate each weight factor of the complexity model of the test scene.

[0154] According to an optional embodiment, further comprising: calculating the consistency indexes of each constructed judgment matrix respectively by using the following expression, so as to judge the consistency of all constructed judgment matrices:

[0155]

[0156] wherein, CR i represents the consistency index of the ith judgment matrix, and i={S6, A7, B4, C6, D3}; λ max，i represents the maximum eigenvalue of the ith judgment matrix, RI i represents the random consistency index corresponding to the order of the ith judgment matrix; n i represents the order of the ith judgment matrix.

[0157] When the consistency indexes of all constructed judgment matrices are less than a specified value, it is indicated that all constructed judgment matrices meet the consistency.

[0158] According to an optional implementation, the quantifying the relevant data parameters comprises: quantifying the following relevant data parameters according to the capabilities required to be evaluated by the unmanned aerial vehicle test task: scene size, scene type, electromagnetic signal type and style, electromagnetic signal density, visibility, wind speed, weather type, environment quantity, electromagnetic environment quantity, task quantity, obstacle size, obstacle height, threat range, threat type, dynamics, concealment, and countermeasures; and determining the complexity of each relevant data parameter according to the quantification results of the relevant data parameters.

[0159] According to an optional implementation, the scene environment task data and the scene obstacle threat quantity are configured, and it is repeatedly determined whether the specified quantity of each data is met, the quantity count is updated once each time the determination is performed, and the simulation test scene model is completed when it is determined that the specified quantity of each data is met.

[0160] According to an optional implementation, the simulation test scene model is established based on the MOF element, and specifically comprises: the following data abstracted from the model layer is specified to form a data structure required to establish the simulation test scene model: geographic environment, weather environment, electromagnetic environment, obstacle threat, scene task, and task target.

[0161] It should be noted that, since Figure 7 The simulation scene modeling method performed by the simulation scene modeling system is substantially the same as the simulation scene modeling method in the example of Figure 1 The same part is omitted.

[0162] Compared with the prior art, the simulation scene modeling method for unmanned aerial vehicle intelligent level testing is provided, the meta-model and the data hierarchical structure of the test scene are established according to the unmanned aerial vehicle test task, the simulation test scene model is obtained, the relevant data parameters are quantified based on the scene environment, the scene environment task, the scene obstacle threat, and the scene task target, the complexity model of the test scene is established by adjusting the weight factors of the complexity model of each test scene, the analytic hierarchy process is used to solve the complexity model, the correspondence between the test scene model complexity and the unmanned aerial vehicle intelligent level is determined, the intelligent level testing of the unmanned aerial vehicle to be tested is performed according to the unmanned aerial vehicle test scene with different complexity, and the intelligent level testing of the unmanned aerial vehicle to be tested can be more effectively and accurately realized.

[0163] Embodiment 3

[0164] Figure 8 is a structural schematic diagram of an electronic device embodiment according to the present application.

[0165] As Figure 8As shown, the electronic device is in the form of a general computing device. The processor can be one or multiple and work cooperatively. The present application does not exclude distributed processing, i.e. the processor can be dispersed in different physical devices. The electronic device of the present application is not limited to a single physical device, but can also be the sum of multiple physical devices.

[0166] The memory stores computer executable programs, usually machine readable codes. The computer readable programs can be executed by the processor to enable the electronic device to perform the method of the present application, or at least some steps of the method.

[0167] The memory includes volatile memory, such as random access memory (RAM) and / or cache memory, and / or non-volatile memory, such as read only memory (ROM).

[0168] Optionally, the electronic device further comprises an I / O interface for data exchange between the electronic device and external devices. The I / O interface can be one or more of several types of bus structures, including memory bus or memory controller, peripheral bus, graphics acceleration port, processing unit, or local bus using any of the bus structures.

[0169] It should be understood that Figure 8 The electronic device shown is only an example of the present application, and the electronic device of the present application can also include elements or components not shown in the above examples. For example, some electronic devices also include display units such as display screens, and some electronic devices also include human-computer interaction elements such as buttons and keyboards. As long as the electronic device can execute the computer readable programs in the memory to implement the method of the present application or at least some steps of the method, it can be considered as an electronic device covered by the present application.

[0170] From the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by software combined with necessary hardware. Therefore, as long as the functions of the embodiments are not affected, the specific operating order of the software and the hardware can be changed. Figure 9 As shown, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or on a network, and includes a number of commands to make a computing device (which can be a personal computer, a server, or a network device, etc.) execute the above method according to the embodiments of the present application.

[0171] The software product can employ any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium. The readable storage medium, for example, can be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0172] The computer readable storage medium can include a data signal transported over a carrier wave and can be baseband or propagated along with carriers. The propagated carrier can take any suitable form, including but not limited to electro-magnetic, optical, or any suitable combination thereof. A computer readable storage medium can be any medium (tangible or non-tangible) that can store data for use by or in connection with the computer system or device. The program code embodied on the computer readable storage medium can be transmitted using any carrier wave appropriate to the communication context, including but not limited to wireless, wire line, optical, radio frequency (RF), or any suitable combination thereof.

[0173] The program code can be executed by one or more programmable processors, which can be implemented as one or more microprocessors, microcontrollers, digital signal processors, application specific integrated circuits, field programmable gate arrays, processors of embedded systems, or the like. The program code can be downloaded from an external source, such as a website, via a network, such as the Internet, or via any other external source. The program code can be downloaded via a wired medium or a wireless medium. The program code can be downloaded from a removable storage medium, such as a CD-ROM, a DVD, a memory stick, or the like.

[0174] The computer readable medium described above can bear one or more programs, which, when executed by the device, cause the computer readable medium to implement the data interaction method of the present disclosure.

[0175] Those skilled in the art can understand that the above-mentioned modules can be distributed in the device according to the description of the embodiments, and can also be changed in one or more devices different from the embodiments. The modules of the above-mentioned embodiments can be combined into one module, or can be further split into a plurality of sub-modules.

[0176] Through the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a plurality of commands to make a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) execute the method according to the embodiments of the present application.

[0177] It should be noted that the above detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0178] In the above detailed description, reference is made to the accompanying drawings, which form a part hereof. In the drawings, similar symbols typically identify similar components, unless context dictates otherwise. The illustrative embodiments described in the detailed description, drawings, and claims are not meant to be limiting. Other embodiments can be used, and other changes can be made, without departing from the spirit or scope of the subject matter presented herein.

[0179] The above only describes the preferred embodiments of the present application and is not intended 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 principles of the present application shall be included in the protection scope of the present application.

Claims

1. A simulation scenario modeling method for unmanned aerial vehicle intelligence level test, characterized in that, Comprise: According to the unmanned aerial vehicle test task, the meta model and the data hierarchical structure of the test scene are established, and the simulation test scene model is obtained; Based on the scene environment, scene environment task, scene obstacle threat and scene task target, the relevant data parameters are quantified, and the complexity model of the test scene is established; the scene task target includes concealment target data, antagonistic target data and dynamic target data; The following expression is used to establish the complexity model of the test scene: wherein, represents a complexity model of a test scenario; represents a quantized state vector corresponding to a scenario environment, a scenario environment task, a scenario obstacle threat, and a scenario task target, respectively, m is a positive integer, wherein the quantized state vector of the scenario environment is , wherein A1 is a scenario size, A2 is a scenario type, A3 is an electromagnetic signal type and style, A4 is an electromagnetic signal density, A5 is a visibility, A6 is a wind speed, and A7 is a weather type; the quantized state vector of the scenario environment task is , wherein B1 is a geographical environment quantity, B2 is a weather environment quantity, B3 is an electromagnetic environment quantity, and B4 is a task quantity; the quantized state vector of the scenario obstacle threat is , wherein C1 to C6 are size C1, height C2, threat type C3, threat range C4, dynamic C5, and concealment C6, respectively; h is a quantity of obstacle threat objects in the scenario, and k is a quantity of obstacle threat objects on a flight path of the unmanned aerial vehicle to the target; the quantized state vector of the scenario task target is , wherein D1 is concealment, D2 is dynamic, and D3 is resistance; represents a weight factor vector corresponding to the quantized state vectors of the scenario environment, the scenario environment task, the scenario obstacle threat, and the scenario task target, respectively; T is an inverted symbol; represents a scenario environment complexity, = ; represents a scenario environment task complexity, = ; represents a scenario obstacle threat complexity, = ; represents a scenario task target complexity, = The analytic hierarchy process is used to solve the complexity model, to determine the weight factors of the complexity model of each test scenario, and to further adjust the weight factors of the complexity model of each test scenario. According to the unmanned aerial vehicle test scene with different complexity, the intelligent level test of the unmanned aerial vehicle to be tested is carried out.

2. The simulation scenario modeling method for unmanned aerial vehicle intelligence level test according to claim 1, characterized in that, Further comprise: According to the importance degree of the quantized state vector corresponding to the scene environment, scene environment task, scene obstacle threat and scene task target, the importance degree weight factor vector is established, and the following expression is used to adjust each weight factor of the complexity model of each test scene: wherein, a weight factor representing the element quantization state of the rth test scenario; representing the importance degree corresponding to the geographic environment data, electromagnetic environment data, weather environment data, scene environment task data, scene obstacle threat data and scene task target data in the test scenario, s is the element value subscript of the vector z, the value of s is determined by r; representing the comprehensive value of the importance degree corresponding to the geographic environment data, electromagnetic environment data, weather environment data, scene environment task data, scene obstacle threat data and scene task target data in the test scenario, t is 1, 2, 3, 4, 5, 6. 3.The simulation scenario modeling method for UAV intelligence level test, according to claim 1, characterized in that, Comprise: According to the data hierarchical structure of the simulation test scene model established by the analytic hierarchy process, the judgment matrix is constructed by using the scaling method, so as to calculate the weight factor of the complexity model of the test scene.

4. The simulation scenario modeling method for unmanned aerial vehicle intelligence level test according to claim 3, characterized in that, Further comprise: The following expression is used to calculate the consistency index of each constructed judgment matrix respectively, so as to judge the consistency of all constructed judgment matrices: wherein, represents the consistency index of the first judgment matrix, ; represents the maximum eigenvalue of the first judgment matrix, represents the random consistency index corresponding to the order of the first judgment matrix; represents the order of the first judgment matrix; S6 is scene task target data; When the consistency index of all constructed judgment matrices is less than the specified value, it is indicated that all constructed judgment matrices meet the consistency.

5. The simulation scenario modeling method for UAV intelligence level test according to claim 1, characterized in that, The quantification of the relevant data parameters comprises: According to the ability required to be evaluated by the unmanned aerial vehicle test task, the following relevant data parameters are quantified: scene size, scene type, electromagnetic signal type and style, electromagnetic signal density, visibility, wind speed, weather type, environment quantity, electromagnetic environment quantity, task quantity, obstacle size, obstacle height, threat range, threat type, dynamic, concealment and antagonism; According to the quantification result of the relevant data parameters, the complexity of each relevant data parameter is determined.

6. The simulation scenario modeling method for unmanned aerial vehicle intelligence level test according to claim 1, characterized in that, Comprise: The scene environment task data and the scene obstacle threat quantity are arranged, and it is repeatedly judged whether the specified quantity of each data is met. The quantity count is updated once for each execution of the judgment, until it is determined that the specified quantity of each data is met. When it is determined that the specified quantity of each data is met, the simulation test scene model is completed.

7. The simulation scene modeling method for unmanned aerial vehicle intelligent level test according to claim 1, wherein The simulation test scene model is established based on MOF meta, specifically comprising: the following data abstracted from the model layer are materialized to form the data structure required to establish the simulation test scene model: geographic environment, weather environment, electromagnetic environment, obstacle threat, scene task and task target.

8. A simulation scenario modeling system for unmanned aerial vehicle intelligence level test, characterized in that, The simulation scene modeling system comprises the simulation scene modeling method for unmanned aerial vehicle intelligent level test according to any one of claims 1 to 7. The first establishment module establishes the meta model and the data hierarchical structure of the test scene according to the unmanned aerial vehicle test task, and obtains the simulation test scene model. The second establishing module quantifies relevant data parameters based on the scene environment, the scene environment task, the scene obstacle threat and the scene task target, and establishes a complexity model of the test scene; the scene task target comprises hidden target data, confrontation target data and dynamic target data; The determining processing module solves the complexity model by using an analytic hierarchy process, determines each weight factor of the complexity model of each test scene, and further adjusts each weight factor of the complexity model of each test scene; The test processing module performs intelligent level testing on the unmanned aerial vehicle to be tested according to unmanned aerial vehicle test scenes of different complexities.

9. An electronic device, comprising: Comprise: One or more processors; Storage devices for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the simulation scene modeling method for unmanned aerial vehicle intelligent level testing according to claim 1.

Images