Target distribution method and device based on aircraft, electronic equipment and medium

Abstract

The invention provides a target distribution method and device based on an aircraft, electronic equipment and a medium, and the method comprises the steps: generating a total situation value and a target discrete matrix corresponding to each particle based on a continuous matrix corresponding to each particle in a particle swarm matrix; determining a target total situation value and a target allocation scheme corresponding to the optimization target based on the total situation value corresponding to the at least one particle through a situation optimization algorithm; and through an aurora optimization algorithm and a lens reverse learning strategy, on the basis of the updated iteration parameters and the continuous matrix corresponding to at least one particle in the particle swarm matrix, updating the continuous matrix corresponding to each particle, and executing the step of generating the particle swarm matrix for the iteration parameters on the basis of the continuous matrix corresponding to each particle. And obtaining a target total situation value and a target distribution scheme corresponding to the optimization target until the iteration parameter is greater than the iteration threshold value, thereby continuously optimizing the optimization target through iteration, and realizing the maximization of the combat effectiveness.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous control and decision-making technology, and in particular to an aircraft-based target allocation method, device, electronic equipment, and medium. Background Art

[0002] Multi-UAV air combat target allocation can be optimally matched according to the UAV status and target threat level, optimizing resource utilization, avoiding resource waste, ensuring that each UAV can achieve maximum combat effectiveness, and improving combat efficiency.

[0003] In related technologies, the multi-UAV air combat target allocation method generally has the problem of difficulty in balancing computational efficiency and the degree of optimization of the allocation scheme. Some methods simplify the model in pursuit of computational efficiency, which makes it difficult for the allocation scheme to accurately weigh factors such as target threats and UAV status. The final allocation scheme has defects in the rationality of resource utilization and combat coordination, and cannot achieve the maximization of combat effectiveness. Summary of the Invention

[0004] To overcome the problems existing in the related art, the present disclosure provides an aircraft-based target allocation method, device, electronic device and medium.

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided an aircraft-based target allocation method, comprising:

[0006] Obtaining situation assessment data for each first aircraft i of a first group relative to a second aircraft j of a second group, the situation assessment data being used to at least indicate an assessment of the combat capability of the first aircraft i relative to the second aircraft j; the first group corresponds to m first aircraft, where m is an integer greater than or equal to 2, and i is greater than or equal to 1 and less than or equal to m; the second group corresponds to n second aircraft, where n is an integer greater than or equal to 2, and j is greater than or equal to 1 and less than or equal to n, and m ≥ n;

[0007] generating conditional constraints and an optimization objective based on the situation assessment data corresponding to the m first aircraft; wherein the optimization objective is at least used to indicate optimizing the effectiveness of a battle between the m first aircraft and the n second aircraft while satisfying the conditional constraints;

[0008] Based on an iteration parameter, determining, for at least one particle, a continuous matrix corresponding to each particle; wherein the iteration parameter is used to indicate at least the number of iterations, the particle corresponds to the allocation scheme, and the continuous matrix includes a first preset matrix parameter corresponding to each situation assessment data, and the first preset matrix parameter is used to indicate at least the value of the situation assessment data in the continuous matrix;

[0009] generating a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each of the particles;

[0010] Based on the continuous matrix corresponding to each particle in the particle swarm matrix, generating a total situation value and a target discrete matrix corresponding to each particle; wherein the target discrete matrix at least satisfies a constraint condition;

[0011] Determining, by a situation optimization algorithm, a target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one of the particles;

[0012] updating the iteration parameters;

[0013] When the iteration parameter is less than or equal to the iteration threshold, the Aurora optimization algorithm and the lens reverse learning strategy are used to update the continuous matrix corresponding to each particle based on the updated iteration parameter and the continuous matrix corresponding to at least one particle in the particle swarm matrix, and the step of generating a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle is performed until the iteration parameter is greater than the iteration threshold, thereby obtaining the target total situation value corresponding to the optimization target, and determining the target allocation scheme based on the target discrete matrix corresponding to the target total situation value.

[0014] In some embodiments, generating a total situation value and a target discrete matrix corresponding to each particle based on the continuous matrix corresponding to each particle in the particle swarm matrix includes:

[0015] In the continuous matrix corresponding to the particle of the particle swarm matrix, for each row in the continuous matrix, determining a maximum value of the first preset matrix parameters among n first preset matrix parameters in each row; wherein the dimension of the continuous matrix is ​​m*n;

[0016] Determining that the maximum value of the first preset matrix parameter corresponds to a second preset matrix parameter, and determining that the first preset matrix parameters in the continuous matrix other than the maximum value of the first preset matrix parameter correspond to a third preset matrix parameter;

[0017] generating a first discrete matrix based on the second preset matrix parameter and the third preset matrix parameter corresponding to the maximum value of the first preset matrix parameter;

[0018] When the n1th column in the first discrete matrix satisfies m parameters that are all third preset matrix parameters, determining the first target row m1 where the pth largest parameter in the n1th column in the continuous matrix is ​​located, and determining the column where the maximum value of the first preset matrix parameter in the first target row m1 is located as the first target column λ; wherein n1 is greater than or equal to 1 and less than or equal to n, p is greater than or equal to 1 and less than or equal to m, m1 is greater than or equal to 1 and less than or equal to m, and λ is greater than or equal to 1 and less than or equal to n;

[0019] Updating the third preset matrix parameters located in the first target row m1 and the n1-th column in the first discrete matrix to second preset matrix parameters, updating the parameters located in the first target row m1 and the first target column λ in the first discrete matrix to third preset matrix parameters, and generating a second discrete matrix based on the updated first discrete matrix;

[0020] If the m parameters of the second discrete matrix that meet the first target column λ are all third preset matrix parameters, update p, and perform the step of determining the first target row m1 and the first target column λ where the p-th largest parameter in the n1-th column of the continuous matrix is ​​located, until the m parameters of the second discrete matrix that meet the first target column λ include the second preset matrix parameters and any column in the second discrete matrix includes the second preset matrix parameters, generating the target discrete matrix based on the second discrete matrix;

[0021] A total situation value corresponding to the particle is generated based on the target discrete matrix.

[0022] In some embodiments, determining the target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one of the particles using a situation optimization algorithm includes:

[0023] When the number of iterations indicates a first iteration, determining a total state maximum value based on the total state value corresponding to at least one of the particles;

[0024] For the number of iterations, based on the total situation maximum value, a target total situation value corresponding to the optimization target is determined.

[0025] In some embodiments, determining the target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one of the particles using a situation optimization algorithm includes:

[0026] When the number of iterations is used to indicate the q-1th iteration, the maximum total situation value determined in the q-1th iteration is used as the maximum total historical situation value; wherein q is an integer greater than 1 and less than or equal to the iteration threshold;

[0027] When the number of iterations indicates the qth iteration, determining a total state maximum value for the total state value corresponding to at least one particle in the qth iteration;

[0028] When the total situation maximum value corresponding to the qth iteration is greater than or equal to the historical total situation maximum value, determining the target total situation value corresponding to the optimization target based on the total situation maximum value corresponding to the qth iteration;

[0029] When the total situation maximum value corresponding to the qth iteration is less than the historical total situation maximum value, the target total situation value corresponding to the optimization target is determined based on the historical total situation maximum value.

[0030] In some embodiments, updating the continuous matrix corresponding to each particle based on the updated iteration parameter and the continuous matrix corresponding to at least one particle in the particle swarm matrix by using the Aurora optimization algorithm and the lens reverse learning strategy includes:

[0031] Based on the updated iteration parameter, determining a target aurora optimization range in which the iteration parameter is located;

[0032] Determining a target aurora optimization algorithm based on the target aurora optimization range;

[0033] By using the target aurora optimization algorithm, based on the particle swarm matrix, the target continuous matrix corresponding to the target particles in the particle swarm matrix is ​​updated to generate a first target continuous matrix;

[0034] The first target continuous matrix is ​​updated through a lens reverse learning algorithm to generate the updated continuous matrix corresponding to the target particle.

[0035] In some embodiments, the target continuous matrix corresponding to the target particles in the particle swarm matrix is ​​updated based on the particle swarm matrix by the target aurora optimization algorithm to generate a first target continuous matrix, including:

[0036] Based on any of the continuous matrices before updating in the particle swarm matrix except the target continuous matrix corresponding to the target particle, the target continuous matrix corresponding to the target particle is updated to generate a first target continuous matrix.

[0037] In some embodiments, the target continuous matrix corresponding to the target particles in the particle swarm matrix is ​​updated based on the particle swarm matrix by the target aurora optimization algorithm to generate a first target continuous matrix, including:

[0038] Generate an average matrix based on each of the continuous matrices of the particle swarm matrix;

[0039] The target continuity matrix corresponding to the target particle is updated based on the average matrix to generate a first target continuity matrix.

[0040] According to a second aspect of an embodiment of the present disclosure, there is provided an aircraft-based target allocation device, comprising:

[0041] an acquisition module configured to acquire situation assessment data of each first aircraft i of a first group relative to a second aircraft j of a second group, the situation assessment data being used to at least indicate an assessment of the combat capability of the first aircraft i relative to the second aircraft j; the first group corresponding to m first aircraft, where m is an integer greater than or equal to 2, i is greater than or equal to 1 and less than or equal to m; the second group corresponding to n second aircraft, where n is an integer greater than or equal to 2, j is greater than or equal to 1 and less than or equal to n, and m ≥ n;

[0042] a first generating module, configured to generate conditional constraints and an optimization objective based on the situation assessment data corresponding to the m first aircraft; wherein the optimization objective is at least used to indicate optimizing the effectiveness of a combat between the m first aircraft and the n second aircraft while satisfying the conditional constraints;

[0043] A first determining module is configured to determine, for at least one particle, a continuous matrix corresponding to each particle based on an iteration parameter, wherein the iteration parameter is used to indicate at least the number of iterations, the particle corresponds to the allocation scheme, the continuous matrix includes a first preset matrix parameter corresponding to each situation assessment data, and the first preset matrix parameter is used to indicate at least the value of the situation assessment data in the continuous matrix;

[0044] A second generating module is configured to generate a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle;

[0045] A third generating module is configured to generate a total situation value and a target discrete matrix corresponding to each particle based on the continuous matrix corresponding to each particle in the particle swarm matrix; wherein the target discrete matrix at least satisfies a constraint condition;

[0046] A second determining module is configured to determine a target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one particle through a situation optimization algorithm;

[0047] A first updating module, configured to update the iteration parameters;

[0048] The second updating module is used to update the continuous matrix corresponding to each particle based on the updated iteration parameter and the continuous matrix corresponding to at least one particle in the particle swarm matrix through the Aurora optimization algorithm and the lens reverse learning strategy when the iteration parameter is less than or equal to the iteration threshold, and trigger the second generation module to execute the step of generating a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle until the iteration parameter is greater than the iteration threshold, thereby obtaining the target total situation value corresponding to the optimization target, and determining the target allocation scheme based on the target discrete matrix corresponding to the target total situation value.

[0049] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a processor; and a memory for storing computer programs or instructions; wherein the processor executes the computer program or instructions to implement the steps of the method described in the first aspect above.

[0050] According to a fourth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided, which stores a computer program or instructions. When the computer program or instructions in the storage medium are executed by a processor, the steps of the method described in the first aspect above are implemented.

[0051] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects:

[0052] The continuous matrix corresponding to each particle is jointly updated using the Aurora optimization algorithm and the lens reverse learning strategy. When the continuous matrix is ​​updated, the corresponding particle allocation scheme is also updated, thereby introducing a new allocation scheme in the next iteration. During at least two iterations, a target total state value is obtained using the state optimization algorithm. The target total state value indicates the optimal performance of the m first aircraft and n second aircraft in a battle, while satisfying conditional constraints. This allows the optimization target to be continuously optimized during the iterative process to achieve the optimal performance.

[0053] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0055] Figure 1 is a flow chart of an aircraft-based target allocation method provided by an embodiment of the present disclosure;

[0056] Figure 2is a schematic diagram of a total situation value change curve provided by an embodiment of the present disclosure;

[0057] Figure 3 is a flow chart of a generation allocation scheme provided by an embodiment of the present disclosure;

[0058] Figure 4 This is a block diagram of an aircraft-based target allocation device provided by an embodiment of the present disclosure;

[0059] Figure 5 This is a structural block diagram of an electronic device provided by an embodiment of the present disclosure;

[0060] Figure 6 The present invention is a block diagram of an aircraft-based target allocation device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0061] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present disclosure. Rather, they are merely examples of devices consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0062] Figure 1 is a flow chart of a target allocation method based on an aircraft provided by an embodiment of the present disclosure, such as Figure 1 Shown, including:

[0063] Step 101, obtain situation assessment data of each first aircraft i of the first group relative to the second aircraft j of the second group, where the situation assessment data is at least used to indicate the combat capability assessment of the first aircraft i relative to the second aircraft j; the first group corresponds to m first aircraft, m includes an integer greater than or equal to 2, i is greater than or equal to 1 and less than or equal to m; the second group corresponds to n second aircraft, n includes an integer greater than or equal to 2, j is greater than or equal to 1 and less than or equal to n, and m≥n.

[0064] In the disclosed embodiment, the first group and the second group are two opposing groups. For example, the first group represents the friendly side, and the second group represents the enemy side. The friendly side has m first aircraft, and the enemy side has n second aircraft. The m friendly first aircraft and the n enemy second aircraft do not overlap. The aircraft include drones.

[0065] Each first aircraft i may correspond to n situation assessment data, and the electronic device may obtain m*n situation assessment data. For example, m is equal to 3, n is equal to 2, the aircraft includes drones, and the three first drones in the first group are respectively the first drones The first drone and the first drone The two second drones in the second group are the second drones and the second drone Electronics acquires first drone Relative to the second drone Situational assessment data, the first drone Relative to the second drone Situational assessment data, ..., the first UAV Relative to the second drone A total of 6 situation assessment data were obtained.

[0066] Step 102: Generate conditional constraints and optimization targets based on the situation assessment data corresponding to the m first aircraft; wherein the optimization target is at least used to indicate the effectiveness of optimizing the combat between the m first aircraft and the n second aircraft while satisfying the conditional constraints.

[0067] In the disclosed embodiment, a conditional constraint may be used to indicate the number of second aircraft j that a first aircraft i can battle against, and the number of first aircraft i that a second aircraft j can battle against. For example, a conditional constraint may indicate that each first aircraft i can battle against one second aircraft j, and each second aircraft j can battle against at least one first aircraft i.

[0068] When drones engage in combat, higher efficiency indicates better combat results. For example, the optimization objective indicates optimizing the efficiency of a combat involving m first drones and n second drones, while satisfying constraints. The efficiency of a combat involving m first drones and n second drones can be determined based on m*n situation assessment data and constraints. This allows for the maximum efficiency of a combat involving m first drones and n second drones.

[0069] Step 103: Based on an iteration parameter, for at least one particle, determine a continuous matrix corresponding to each particle; wherein the iteration parameter is used to indicate at least the number of iterations, the particle corresponds to the allocation scheme, and the continuous matrix includes first preset matrix parameters corresponding to each situation assessment data, and the first preset matrix parameters are used to indicate at least the value of the situation assessment data in the continuous matrix.

[0070] In the embodiment of the present disclosure, the number of particles is used to indicate the number of allocation schemes, and the dimension of the continuous matrix is ​​m*n. The continuous matrix includes m*n first preset matrix parameters.

[0071] Step 104 : generating a particle swarm matrix for iteration parameters based on the continuous matrix corresponding to each particle.

[0072] In the embodiment of the present disclosure, the electron can form a particle swarm matrix corresponding to the iteration parameter based on a continuous matrix corresponding to N particles, where N is an integer greater than or equal to 1 and less than or equal to m*n, and the dimension of the particle swarm matrix is ​​N×m*n.

[0073] Step 105 : Based on the continuous matrix corresponding to each particle in the particle swarm matrix, generate the total situation value and target discrete matrix corresponding to each particle; wherein the target discrete matrix at least satisfies the constraint condition.

[0074] In the disclosed embodiment, the target discrete matrix corresponding to the particle is used to indicate the allocation scheme, and the allocation scheme satisfies the constraint conditions. The total situation value corresponding to the particle is used to indicate the effectiveness of the battle between the m first aircraft and the n second aircraft under the allocation scheme.

[0075] Step 106 : Determine a target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one particle through a situation optimization algorithm.

[0076] In the embodiment of the present disclosure, the target total situation value represents the maximum total situation value among the total situation values ​​corresponding to at least one particle up to the current number of iterations.

[0077] Step 107: Update the iteration parameters.

[0078] In the embodiment of the present disclosure, the updated iteration parameter is used to indicate an increase in the number of iterations.

[0079] Step 108: When the iteration parameter is less than or equal to the iteration threshold, the continuous matrix corresponding to each particle is updated based on the updated iteration parameter and the continuous matrix corresponding to at least one particle in the particle swarm matrix through the Aurora optimization algorithm and the lens reverse learning strategy, and the step of generating a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle is executed until the iteration parameter is greater than the iteration threshold, and the target total situation value corresponding to the optimization target is obtained, and the target allocation scheme is determined based on the target discrete matrix corresponding to the target total situation value.

[0080] In the disclosed embodiment, the continuous matrix corresponding to each particle is updated jointly by the Aurora optimization algorithm and the lens reverse learning strategy. When the continuous matrix is ​​updated, the allocation scheme corresponding to the particle is also updated accordingly, thereby introducing a new allocation scheme in the next iteration.

[0081] The iteration threshold indicates the maximum number of iterations and is an integer greater than or equal to 2. When the iteration parameter exceeds the iteration threshold, the iteration ends. During at least two iterations, the situation optimization algorithm obtains a target total situation value. The target total situation value indicates the optimal performance of a battle between m first aircraft and n second aircraft, while satisfying conditional constraints. This allows the optimization objective to be continuously optimized during the iteration process to achieve the optimal performance.

[0082] In some embodiments, step 101 includes: step 1011, obtaining battle evaluation data of the first aircraft i relative to the second aircraft j, and generating situation assessment data corresponding to the first aircraft i and the second aircraft j based on the battle evaluation data;

[0083] The combat assessment data includes at least one of the following data: air combat capability situation assessment data, distance situation assessment data, altitude situation assessment data, angle situation assessment data, and speed situation assessment data.

[0084] In the disclosed embodiment, the electronic device initializes first aircraft status information corresponding to each first aircraft i of the first group, and initializes second aircraft status information corresponding to each second aircraft j of the second group.

[0085] The first aircraft state information includes but is not limited to the X coordinate of the first aircraft i Y coordinate Z coordinate Pitch angle Yaw angle Roll angle and speed At least one of them, where U represents the first group; generating the first status information based on the first aircraft status information of the m first aircraft, thereby obtaining the first aircraft status information corresponding to each first aircraft in the first group.

[0086] The first aircraft status information includes an X coordinate Y coordinate Z coordinate Pitch angle Yaw angle Roll angle and speed In the case of m first aircraft X coordinate sets X can be obtained U , Y coordinate set Y U , Z coordinate set Z U , pitch angle set θ U , yaw angle set Roll angle set φ U and velocity set V U; The first state information can be expressed by formula (1).

[0087]

[0088] The first aircraft status information also includes the firepower parameter A of the first aircraft i 1i , Detection capability parameter A 2i 、Maneuverability parameters B i , handling performance coefficient ε 1i , survivability coefficient ε 2i , range coefficient ε 3i , electronic countermeasure coefficient ε 4i , Radar maximum detection range and the weapon's maximum attack range At least one of them.

[0089] The first aircraft includes a first drone. Table 1 is a schematic table of first state information provided by the present disclosure, as shown in Table 1 below.

[0090] Table 1

[0091]

[0092] As shown in Table 1 above, the first state information includes the first aircraft state information of 10 first drones. The first state information of the first drone i includes the X coordinate Y coordinate Z coordinate Pitch angle Yaw angle Roll angle speed Firepower parameter A 1i , Detection capability parameter A 2i 、Maneuverability parameters B i , handling performance coefficient ε 1i , survivability coefficient ε 2i , range coefficient ε 3i , electronic countermeasure coefficient ε 4i , Radar maximum detection range and the weapon's maximum attack range The value of the first aircraft status information of each first unmanned aerial vehicle is different.

[0093] As shown in Table 1 above, column 1 represents the first aircraft status information, and columns 2 to 11 represent the values ​​of various parameters in the first aircraft status information of the first UAV. For example, in column 2, the first UAV is numbered 1, the X coordinate is 14.48 kilometers (km), the Y coordinate is 48.44 km, the Z coordinate is 32.02 km, the pitch angle is -1.38 radians (rad), the yaw angle is 1.00 rad, the roll angle is -2.05 rad, the speed is 150 meters per second (m / s), the firepower parameter is 22, the detection capability parameter is 54, the maneuverability parameter is 35, the handling performance coefficient is 3, the survivability coefficient is 9, the range coefficient is 4, the electronic countermeasure coefficient is 5, the maximum radar detection range is 5.43, and the maximum weapon attack range is 1.34.

[0094] The electronic device initializes the first aircraft state information corresponding to each first aircraft, and can also initialize the distance coefficient a1 and the optimal attack height H corresponding to the first aircraft. opt , height situation assessment coefficient, weight corresponding to situation assessment data, etc. For example, if the distance coefficient a1 is set to 1, the optimal attack height H opt The altitude is 30m, the height situation assessment coefficients b and c are both 1, and the weight corresponding to the situation assessment data is 0.2.

[0095] The second aircraft state information includes but is not limited to the X coordinate of the second aircraft j. Y coordinate Z coordinate Pitch angle Yaw angle Roll angle and speed At least one of them, where T represents the second group; generating second status information based on the second aircraft status information of n second drones, thereby obtaining the second aircraft status information corresponding to each second aircraft in the second group.

[0096] The second aircraft status information includes the X coordinate Y coordinate Z coordinate Pitch angle Yaw angle Roll angle and speed In the case of , we can get the X coordinate set X of n second drones T , Y coordinate set Y T , Z coordinate set Z T , pitch angle set θ T , yaw angle set Roll angle set φ T and velocity set v T; The second state information can be expressed by formula (2).

[0097]

[0098] The X coordinate, Y coordinate, and Z coordinate of the first aircraft and the X coordinate, Y coordinate, and Z coordinate of the second aircraft are in the same coordinate system.

[0099] The second aircraft status information also includes the firepower parameter A of the second aircraft j 1j , Detection capability parameter A 2j 、Maneuverability parameters B j , handling performance coefficient ε 1j , survivability coefficient ε 2j , range coefficient ε 3j and the electronic countermeasure coefficient ε 4j At least one of them.

[0100] The second aircraft includes a second drone. Table 2 is a schematic table of second state information provided by the present disclosure, as shown in Table 2 below:

[0101] Table 2

[0102] serial number 1 2 3 4 5 6 7 8 9 10 X coordinate (km) 45.21 37.49 26.34 31.43 28.84 33.07 39.19 43.03 41.32 49.91 Y coordinate (km) 19.12 41.39 22.23 49.23 8.92 31.96 14.04 26.30 38.78 0.41 Z coordinate (km) 13.65 6.17 34.05 48.56 19.54 42.11 36.58 2.26 27.87 21.77 Pitch angle (rad) -1.01 -0.44 -1.39 0.06 -0.51 -1.01 -0.91 1.27 0.55 -0.09 Yaw angle (rad) 2.58 -2.48 1.54 1.48 0.38 -1.98 0.61 -1.25 -2.29 -1.80 Roll angle (rad) 2.48 -2.69 -1.61 -2.80 -0.36 -3.05 2.49 -1.90 -2.55 -1.21 Speed ​​(m / s) 150 150 150 150 150 150 150 150 150 150 Firepower parameters 28 14 49 23 21 12 21 11 30 40 Detection capability parameters 31 53 40 38 46 40 53 30 45 52 Maneuverability parameters 35 13 13 41 46 31 14 43 23 21 Controllable performance coefficient 7 1 1 7 6 5 7 7 8 3 Survivability coefficient 7 6 4 1 8 4 6 7 1 2 Range coefficient 5 5 9 8 7 1 1 1 8 9 Electronic countermeasures coefficient 7 2 7 1 2 6 3 6 7 6

[0103] As shown in Table 2 above, the second state information includes the second aircraft state information of 10 second UAVs. The second aircraft state information of the second UAV j includes the X coordinate Y coordinate Z coordinate Pitch angle Yaw angle Roll angle speed Firepower parameter A 1j , Detection capability parameter A 2j 、Maneuverability parameters B j , handling performance coefficient ε 1j , survivability coefficient ε 2j , range coefficient ε 3j and the electronic countermeasure coefficient ε 4j The value of the second aircraft status information of each second UAV is different.

[0104] As shown in Table 2 above, column 1 represents the second aircraft status information, and columns 2 to 11 represent the values ​​of the various parameters in the second aircraft status information of the second UAV. For example, in column 2, the second UAV is numbered 1, with an X coordinate of 45.21 km, a Y coordinate of 19.21 km, a Z coordinate of 13.65 km, a pitch angle of -1.0 rad, a yaw angle of 2.58 rad, a roll angle of 2.48 rad, a speed of 150 m / s, a firepower parameter of 28, a detection capability parameter of 31, a maneuverability parameter of 35, a handling performance coefficient of 7, a survivability coefficient of 7, a range coefficient of 5, and an electronic countermeasure coefficient of 7.

[0105] The electronic device initializes the first aircraft status information corresponding to each first aircraft, and can also initialize the distance coefficient a1 and the optimal attack height H corresponding to the first aircraft. opt , altitude situation assessment coefficient and other parameters.

[0106] The electronic device generates at least one of air combat capability situation assessment data, distance situation assessment data, altitude situation assessment data, angle situation assessment data, and speed situation assessment data based on first aircraft status information of the first aircraft i and second aircraft status information of the second aircraft j. Based on at least one of the air combat capability situation assessment data, distance situation assessment data, altitude situation assessment data, angle situation assessment data, and speed situation assessment data, the electronic device generates situation assessment data of the first aircraft i relative to the second aircraft j, thereby evaluating the combat capability of the first aircraft i relative to the second aircraft j based on at least one of the dimensions of air combat capability, distance, altitude, angle, and speed between the two aircraft, and obtaining the situation assessment data of the first aircraft i relative to the second aircraft j.

[0107] In some embodiments, when the combat assessment data includes air combat capability situation assessment data, distance situation assessment data, altitude situation assessment data, angle situation assessment data, and speed situation assessment data, step 1011 includes steps 201 to 205, wherein:

[0108] Step 201 : Generate air combat capability situation assessment data based on the air combat capability assessment parameters of the first aircraft i of the first group and the air combat capability assessment parameters of the second aircraft j of the second group.

[0109] In the embodiment of the present disclosure, for the first aircraft i, the air combat capability of the first aircraft i is evaluated based on the first aircraft state information by using the first air combat capability evaluation function to generate the air combat capability evaluation parameter of the first aircraft i.

[0110] At this time, the first aircraft status information includes the firepower parameter A 1i, Detection capability parameter A 2i 、Maneuverability parameters B i , handling performance coefficient ε 1i , survivability coefficient ε 2i , range coefficient ε 3i and the electronic countermeasure coefficient ε 4i The electronic equipment respectively measures the firepower parameter A 1i , Detection capability parameter A 2i and maneuverability parameters B i Perform logarithmic operation and convert the firepower parameter A 1i Corresponding logarithmic operation results, detection capability parameter A 2i Corresponding logarithmic calculation results and maneuverability parameters B i The corresponding logarithmic operation results are summed to generate a first sum; based on the handling performance coefficient ε 1i , survivability coefficient ε 2i , range coefficient ε 3i and the electronic countermeasure coefficient ε 4i Perform a multiplication operation to generate a first product; obtain the air combat capability evaluation parameter of the first aircraft i based on the first sum and the first product The first air combat capability evaluation function can be expressed as formula (3).

[0111]

[0112] For the second aircraft j, the air combat capability of the second aircraft j is evaluated based on the second aircraft state information through the second air combat capability evaluation function, and the air combat capability evaluation parameter of the second aircraft j is generated.

[0113] At this time, the second aircraft status information includes the firepower parameter A of the second aircraft j 1j , Detection capability parameter A 2j 、Maneuverability parameters B j , handling performance coefficient ε 1j , survivability coefficient ε 2j , range coefficient ε 3j and the electronic countermeasure coefficient ε 4j The electronic equipment respectively measures the firepower parameter A 1j , Detection capability parameter A 2j and maneuverability parameters B j Perform logarithmic operation and convert the firepower parameter A 1j Corresponding logarithmic operation results, detection capability parameter A 2j Corresponding logarithmic calculation results and maneuverability parameters B j The corresponding logarithmic operation results are summed to generate a second sum; based on the control performance coefficient ε 1i , survivability coefficient ε2i , range coefficient ε 3i and the electronic countermeasure coefficient ε 4i Perform a multiplication operation to generate a second product; obtain the air combat capability evaluation parameter of the second aircraft j based on the second sum and the second product The second air combat capability evaluation function can be expressed as formula (4).

[0114]

[0115] The air combat capability situation assessment formula is used to generate air combat capability situation assessment data based on the air combat capability assessment parameters of the first aircraft i of the first group and the air combat capability assessment parameters of the second aircraft j of the second group.

[0116] For example, the air combat capability situation assessment formula can be expressed as formula (5).

[0117]

[0118] Among them, the electronic equipment uses the air combat capability situation assessment formula to take the ratio of the air combat capability assessment parameter of the first aircraft i of the first group and the air combat capability assessment parameter of the second aircraft j of the second group as the air combat capability situation assessment data.

[0119] Step 202 : Generate distance situation assessment data and altitude situation assessment data based on the coordinate parameters of the first aircraft i and the coordinate parameters of the second aircraft j.

[0120] In the embodiment of the present disclosure, the electronic device generates an aircraft distance d based on the coordinate parameters of the first aircraft i and the coordinate parameters of the second aircraft j. ij ; Through the distance situation assessment formula, based on the aircraft distance d ij Generate distance situation assessment data The distance situation assessment formula is used to indicate at least the distance d between the aircraft and the vehicle. ij Less than or equal to the maximum detection range of the radar of the first aircraft i Within and greater than the maximum attack range of the weapon of the first aircraft i When the distance situation between the first aircraft i and the second aircraft j is evaluated, the maximum detection range of the radar is Greater than the weapon's maximum attack range At the aircraft distance d ij Greater than the maximum detection range of the radar of the first aircraft i When determining the distance situation assessment data Including a first preset value; at the aircraft distance d ij Less than or equal to the maximum attack range of the weapon of the first aircraft i When determining the distance situation assessment data A second preset value is included.

[0121] The first aircraft state information includes the X coordinate of the first aircraft i Y coordinate and Z coordinate The second aircraft state information includes the X coordinate of the second aircraft j Y coordinate and Z coordinate The electronic device uses the distance formula based on the X coordinate of the first aircraft i Y coordinate Z coordinate and the X coordinate of the second aircraft Y coordinate Z coordinate Get the aircraft distance d ij The distance formula can be expressed as formula (6).

[0122]

[0123] The first preset value includes 0, indicating that the second aircraft j is not within the radar detection range of the first aircraft i; the second preset value includes 1, indicating that the second aircraft j is within the weapon attack range of the first aircraft i. When the second aircraft j is within the radar detection range of the first aircraft i and is not within the weapon attack range of the first aircraft i, the electronic device calculates the distance situation assessment data of the first aircraft i relative to the second aircraft j; the electronic device calculates the distance situation assessment data of the first aircraft i relative to the second aircraft j based on the aircraft distance d ij and the weapon's maximum attack range Generate a first difference; based on the aircraft distance d ij and the first difference to generate a first ratio; perform an exponential operation on the first ratio, and generate distance situation assessment data based on the exponential operation result corresponding to the first ratio and a second preset value The distance situation assessment formula can be expressed as formula (7).

[0124]

[0125] Where a1 represents the distance coefficient.

[0126] The electronic device is based on the Z coordinate of the first aircraft i and the Z coordinate of the second aircraft j The difference between the height and distance of the aircraft is generated. ij ; Through the altitude situation assessment formula, based on the aircraft altitude distance ΔZ ij and optimal attack height H opt Generate high-level situation assessment data The altitude situation assessment formula is used to indicate at least the altitude distance ΔZ of the aircraft. ij When the aircraft is within the optimal attack range, the altitude situation of the first aircraft i and the second aircraft j is evaluated. For example, the optimal attack range includes the altitude distance ΔZ ij Greater than 0 and less than or equal to 2H opt Range; at the aircraft height distance ΔZ ij Less than or equal to 0, or at the aircraft height distance ΔZ ij Determine high situational assessment data when outside optimal attack range Including the third preset value. The altitude situation assessment formula can be expressed as formula (8).

[0127]

[0128] Among them, the third preset value includes 0, and the optimal attack range includes the height distance ΔZ ij Greater than 0 and less than or equal to H opt Range, or, the optimal attack range includes the height distance ΔZ ij Greater than H opt and less than or equal to 2H opt b and c are both altitude situation assessment coefficients. opt <ΔZ ij ≤2H opt When the electronic equipment calculates the height distance ΔZ of the aircraft ij and optimal attack height H opt Based on the fourth preset value and the aircraft height distance ΔZ ij and optimal attack height H opt ratio, generating high-level situation assessment data The fourth preset value includes 1.

[0129] Step 203 : Generate angle situation assessment data based on the angle parameters of the first aircraft i and the angle parameters of the second aircraft j.

[0130] In the embodiment of the present disclosure, the electronic device generates the angle parameter of the first aircraft i based on the first aircraft state information by using the first angle formula. The angle parameter of the first aircraft i is at least used to indicate the entry angle of the first aircraft i; the angle parameter of the second aircraft j is generated based on the second aircraft state information through the second angle formula The second aircraft j is at least used to indicate the escape angle of the second aircraft j; through the angle situation assessment formula, based on the angle parameter of the first aircraft i and the angle parameter of the second aircraft j Generate angle situation assessment data

[0131] The first aircraft state information includes the X coordinate of the first aircraft i Y coordinate Z coordinate Pitch angle and yaw angle The second aircraft state information includes the X coordinate of the second aircraft j Y coordinate Z coordinate Pitch angle and yaw angle

[0132] The electronic device obtains the distance d of the aircraft through the distance formula ij The pitch angle of the first aircraft i Perform sine and cosine operations respectively to obtain the first sine pitch value and the first cosine pitch value Yaw angle of the first aircraft i Perform sine and cosine operations respectively to obtain the first sine yaw value and the first cosine yaw value Based on the X coordinate of the first aircraft i and the X coordinate of the second aircraft j Get the first lateral offset value; based on the Y coordinate of the first aircraft i and the Y coordinate of the second aircraft j Get the first longitudinal offset value; based on the Z coordinate of the first aircraft i and the Z coordinate of the second aircraft j Get a first height offset value; based on the first lateral offset value, the first cosine yaw value and the first cosine pitch value Get the third product; based on the first longitudinal offset value, the first sinusoidal yaw value and the first cosine pitch value Get the fourth product; based on the first height offset value and the first sinusoidal pitch value Get the fifth product; get the third sum based on the third product, the fourth product and the fifth product; get the third sum based on the third sum and the aircraft distance d ij , get the second ratio; perform arc cosine operation on the second ratio to get the angle parameter of the first aircraft i Thus, the angle between the velocity vector of the first aircraft i and the distance vector of the second aircraft j is calculated. The first angle formula can be expressed as formula (9).

[0133]

[0134] The pitch angle of the second aircraft j Perform sine and cosine operations respectively to obtain the second sine pitch value and the first cosine pitch value Yaw angle of the second aircraft j Perform sine and cosine operations respectively to obtain the second sine yaw value and the second cosine yaw value Based on the X coordinate of the second aircraft j and the X coordinate of the first aircraft i Get the second lateral offset value; based on the Y coordinate of the second aircraft j and the Y coordinate of the first aircraft i Get the second longitudinal offset value; based on the Z coordinate of the second aircraft j and the Z coordinate of the first aircraft i Get the second height offset value; based on the second sinusoidal pitch value First cosine pitch value Second sine yaw value Second cosine yaw value The second lateral offset value, the second longitudinal offset value, the second height offset value and the distance d from the aircraft ij , obtaining a third ratio; performing an arc cosine operation on the third ratio to calculate the angle between the velocity vector of the second aircraft j and the distance vector of the first aircraft i. The second angle formula can be expressed as formula (10).

[0135]

[0136] The electronic equipment calculates the angle parameters of the first aircraft i through the angle situation assessment formula and the angle parameter of the second aircraft j Based on the fourth sum and the fifth preset value, a fourth ratio is generated; the difference between the fourth ratio and the sixth preset value is used as the angle situation assessment data The angle situation assessment formula can be expressed as formula (11).

[0137]

[0138] The fifth preset value includes π, and the sixth preset value includes 1.

[0139] Step 204 : Generate speed situation assessment data based on the speed parameter of the first aircraft i and the speed parameter of the second aircraft j.

[0140] In the embodiment of the present disclosure, the speed parameter of the first aircraft i includes the speed The velocity parameters of the second aircraft j include the velocity

[0141] Electronic device speed and optimal air combat speed V best Determine the speed situation assessment formula; generate speed situation assessment data based on the speed parameters of the first aircraft i and the speed parameters of the second aircraft j through speed situation assessment

[0142] At the best air combat speed V best Greater than In the case of , determining the speed situation evaluation formula includes a first speed situation evaluation formula. The first speed situation evaluation formula can be expressed as formula (12).

[0143]

[0144] At the best air combat speed V best Greater than and less than or equal to In the case of , determining the speed situation evaluation formula includes a second speed situation evaluation formula. The second speed situation evaluation formula can be expressed as formula (13).

[0145]

[0146] Step 205 : generating situation assessment data based on the air combat capability situation assessment data, the distance situation assessment data, the altitude situation assessment data, the angle situation assessment data, and the speed situation assessment data.

[0147] In the embodiment of the present disclosure, the electronic device determines the air combat capability situation assessment data Distance situation assessment data High-level situation assessment data Angle situation assessment data and speed situation assessment data The corresponding weights respectively; through the situation assessment formula, based on the air combat capability situation assessment data Distance situation assessment data High-level situation assessment data Angle situation assessment data and speed situation assessment data The corresponding weights, as well as the air combat capability situation assessment data, distance situation assessment data, height situation assessment data, angle situation assessment data and speed situation assessment data, generate the situation assessment data S ij .

[0148] Electronic equipment uses situation assessment formulas to assess air combat capability situation data Distance situation assessment data High-level situation assessment data Angle situation assessment data and speed situation assessment data Perform weighted sum operation to generate situation assessment data S ij The situation assessment formula can be expressed as formula (14).

[0149]

[0150] Among them, w1, w2, w3, w4 and w5 represent the air combat capability situation assessment data Distance situation assessment data Angle situation assessment data High-level situation assessment data and speed situation assessment data The corresponding weights. For example, the values ​​of w1, w2, w3, w4, and w5 are all 0.2.

[0151] In some embodiments, in step 102, the conditional constraint is used to indicate that a second aircraft j is assigned to each first aircraft i, and at least one first aircraft i is assigned to each second aircraft j; the total situation value is used to indicate that a situation value corresponding to a second aircraft j is assigned to each first aircraft i, and at least one first aircraft i is assigned to each second aircraft j; and the optimization objective is used to indicate determining the maximum value of at least two total situation values.

[0152] In the embodiment of the present disclosure, the decision element x is defined ij , x ij It is used to indicate whether to allocate the second aircraft j to the first aircraft i. ij It can be expressed as formula (15).

[0153]

[0154] Among them, when x ij When the value of is 1, it indicates that the first aircraft i is assigned to the second aircraft j, so that the first aircraft i attacks the second aircraft j; when x ij When the value of is 0, it indicates that the second aircraft j is not allocated to the first aircraft i.

[0155] The conditional constraint can be expressed as formula (16).

[0156]

[0157] Among them, st is the identifier of the condition constraint, It means that when the second aircraft j remains constant, at least one first aircraft i can be assigned to the second aircraft j; Indicates that when the first aircraft i remains constant, one second aircraft j is assigned to the first aircraft i; x ij =0,1, indicating xij The value of is 0 or 1, thus, through the conditional constraint, it is stipulated that each first aircraft i can attack one second aircraft j; since m ≥ n, it indicates that the number of first aircraft is greater than or equal to the number of second aircraft. When the number of first aircraft is greater than the number of second aircraft, At least one first aircraft i is assigned to each second aircraft j, ensuring that each second aircraft j can be attacked by at least one first aircraft i.

[0158] Through the total situation value formula, based on the situation assessment data S corresponding to each first aircraft i ij and decision element x ij Generate the total situation value; the total situation value formula can be expressed as formula (17).

[0159]

[0160] Among them, the total situation value corresponds to the allocation plan, and the total situation value is used to indicate the situation value corresponding to assigning a second aircraft j to each first aircraft i and assigning at least one first aircraft i to each second aircraft j; the total situation value formula satisfies the conditional constraints.

[0161] The optimization objective formula corresponding to the optimization objective can be expressed as formula (18).

[0162]

[0163] Among them, the optimization objective formula also satisfies the conditional constraints.

[0164] For example, m is equal to 3, n is equal to 2, the aircraft includes drones, and the three first drones in the first group are respectively the first drones The first drone and the first drone The two second drones in the second group are the second drones and the second drone Each first UAV is assigned one second UAV, and each second UAV is assigned at least one first UAV. There are six allocation schemes. Table 3 is a schematic diagram of an allocation scheme provided by the present disclosure, as shown in Table 3 below:

[0165] Table 3

[0166]

[0167] As shown in Table 3 above, when the constraints are met, six allocation schemes exist. Each row, from row 2 to row 7, represents a different allocation scheme. Each first drone can attack one second drone, and each second drone can be attacked by at least one first drone. The optimization objective indicates the larger or maximum total situation value among at least two allocation schemes. The allocation scheme corresponding to the larger or maximum total situation value is selected as the target allocation scheme.

[0168] For example, when the allocation scheme number is 1, it is the first drone Assign a second drone The value is 1; for the first drone Assign a second drone The value of is 1; the first drone Assign a second drone The value of is 1; through formula (17), the total situation value

[0169] When the allocation plan number is 2, it is the first drone Assign a second drone The value is 1; for the first drone Assign a second drone The value of is 1; the first drone Assign a second drone The value of is 1; through formula (17), the total situation value

[0170] Assuming that the optimization objective is used to indicate the larger value of the total situation value in the two allocation schemes, the larger total situation value between the total situation value J1 when the allocation scheme number is 1 and the total situation value J2 when the allocation scheme number is 2 is determined by formula (18).

[0171] In some embodiments, the first preset matrix parameter is within a first preset range. When executing step 103, the iteration parameter indicates the first iteration, and for at least one particle, the matrix position corresponding to each particle is determined and the continuous matrix corresponding to each particle is determined, including: based on one particle, determining the matrix position corresponding to the particle; determining the first preset matrix parameter corresponding to each situation assessment data based on the first preset range; and generating a continuous matrix based on the first preset matrix parameter corresponding to each situation assessment data.

[0172] In the embodiment of the present disclosure, the number of iterations may be indicated by a numerical value. For example, in the first iteration, the iteration parameter t may include 1.

[0173] In the first iteration, the electronic device determines the number of particles N, where N is an integer greater than or equal to 1, so that the electronic device can determine the number of particles N for each iteration. Each particle corresponds to an allocation scheme, which is a scheme in which each first aircraft i of the first group is allocated one second aircraft j, and each allocation scheme meets the conditional constraints. The dimension of each particle is m*n. For example, in the first iteration, N is 3, and the three particles are particles particle and particles The positions of particles can be randomly assigned. The corresponding matrix position is 1, the particle The corresponding matrix position is 2, the particle The corresponding matrix position is 3.

[0174] The continuous matrix includes m*n first preset matrix parameters, and the first preset matrix parameters corresponding to each situation assessment data in the particle are initialized, and the parameters randomly taken out within the first preset range are used as the first preset matrix parameters corresponding to the situation assessment data.

[0175] For example, the matrix position corresponding to the particle is k, k is a value greater than or equal to 1 and less than or equal to N, and the particle The corresponding continuous matrix can be expressed as formula (19).

[0176]

[0177] in, Represents particles The corresponding continuous matrix, represents the first preset matrix parameter corresponding to the situation assessment data of the first UAV m and the second UAV j in the kth continuous matrix; k is an integer greater than or equal to 1 and less than or equal to N.

[0178] For another example, the first preset range includes [0, 1], indicating that any first preset matrix parameter among the m*n first preset matrix parameters in the continuous matrix is ​​greater than or equal to 0 and less than or equal to 1. Assuming that m is equal to 3 and n is equal to 2, the particle The corresponding continuous matrix can be expressed as formula (20).

[0179]

[0180] Since the first preset matrix parameter in the continuous matrix is ​​a random value obtained from the range of [0, 1], the continuous matrix usually does not meet the conditional constraints. For example, m is equal to 3, n is equal to 2, the aircraft includes drones, and the three first drones in the first group are the first drones. The first drone and the first drone The two second drones in the second group are the second drones and the second drone The first row represents the first drone The second row of the assigned 2 second aircraft represents the first drone The second aircraft are assigned 2 times, and the third row represents the first UAV. 2 second aircraft assigned.

[0181] In some embodiments, in step 104 , the particle swarm matrix changes as the number of iterations changes.

[0182] In the disclosed embodiment, the dimension of the particle swarm matrix is ​​N×m*n, where N represents the number of particles and m*n represents the dimension of each particle. When the iteration parameter indicates the first iteration, the parameters in the particle swarm matrix X are all randomly obtained first preset matrix parameters.

[0183] For example, in the first iteration, the value of N is 3, and the three particles are particles particle and particles The positions of particles can be randomly assigned. The corresponding matrix position is 1, the particle The corresponding matrix position is 2, the particle The corresponding matrix position is 3. The particle swarm matrix can be expressed as formula (21).

[0184]

[0185] Where X represents the particle swarm matrix, Represents particles The corresponding continuous matrix; Represents particles The corresponding continuous matrix; Represents particles The corresponding continuous matrix.

[0186] In some embodiments, step 105 includes steps 1051 to 1057, wherein:

[0187] Step 1051 : Based on a continuous matrix corresponding to the particle, for each row in the continuous matrix, determine the maximum value of the first preset matrix parameters among the n first preset matrix parameters in each row; wherein the dimension of the continuous matrix is ​​m*n.

[0188] In the disclosed embodiment, the dimension of a continuous matrix is ​​m*n, indicating that the continuous matrix has m rows and n columns and contains m*n first preset matrix parameters. If any row of the continuous matrix contains two identical maximum first preset matrix parameters, the first maximum first preset matrix parameter that appears from left to right is used as the maximum first preset matrix parameter. For example, if any row of the continuous matrix is ​​[0.8, 0.8, 0.3], 0.8 in the first column is used as the maximum first preset matrix parameter.

[0189] Take the above formula (20) as an example to illustrate, in the continuous matrix In the example, the maximum value of the first row is 0.8, which determines that the maximum value of the first preset matrix parameter of the first row is 0.8; the maximum value of the second row is 0.6, which determines that the maximum value of the first preset matrix parameter of the second row is 0.6; the maximum value of the third row is 0.7, which determines that the maximum value of the first preset matrix parameter of the third row is 0.7.

[0190] Step 1052 : Determine that the maximum value of the first preset matrix parameter corresponds to the second preset matrix parameter, and determine that the first preset matrix parameters other than the maximum value of the first preset matrix parameter in the continuous matrix correspond to the third preset matrix parameter.

[0191] In the embodiment of the present disclosure, the second preset matrix parameters are different from the third preset matrix parameters. The second preset matrix parameters are used to indicate that the second aircraft j is allocated to the first aircraft i; the third preset matrix parameters are used to indicate that the second aircraft j is not allocated to the first aircraft i.

[0192] For example, the second preset matrix parameter is 1, and the third preset matrix parameter is 0. For the first row, it is determined that the maximum value of the first preset matrix parameter 0.8 corresponds to 1, and 0.5 corresponds to 0; for the second row, it is determined that the maximum value of the first preset matrix parameter 0.6 corresponds to 1, and 0.3 corresponds to 0; for the third row, it is determined that the maximum value of the first preset matrix parameter 0.7 corresponds to 1, and 0.4 corresponds to 0.

[0193] Step 1053 : Generate a first discrete matrix based on the second preset matrix parameters and the third preset matrix parameters corresponding to the maximum value of the first preset matrix parameters.

[0194] In the embodiment of the present disclosure, the first discrete matrix is ​​used to indicate, for each first aircraft i, whether the second aircraft j is allocated to the first aircraft i.

[0195] For example, the first discrete matrix can be expressed as formula (22).

[0196]

[0197] in, Represents the first discrete matrix, which corresponds to the allocation scheme.

[0198] Step 1054: When the n1-th column in the first discrete matrix satisfies the m parameters that are all third preset matrix parameters, determine the first target row m1 in the continuous matrix where the p-th largest parameter is located, and determine the column in the first target row m1 where the maximum value of the first preset matrix parameter is located as the first target column λ; wherein n1 is greater than or equal to 1 and less than or equal to n, p is greater than or equal to 1 and less than or equal to m, m1 is greater than or equal to 1 and less than or equal to m, and λ is greater than or equal to 1 and less than or equal to n.

[0199] In the embodiment of the present disclosure, the first discrete matrix as shown in the above formula (22) In the first column, all parameters have a value of 0, indicating that there is no second drone. Assigning the first UAV results in the first discrete matrix not meeting the conditional constraints. n1 is 1, and in the continuous matrix shown in the above formula (20) In the figure, the first largest parameter in the first column is 0.5, the row where 0.5 is located is the first row, and m1 is 1; in the first row, the maximum value of the first preset matrix parameter is 0.8, the column where 0.8 is located is the second column, and λ is 2.

[0200] Step 1055: Update the third preset matrix parameters located in the first target row m1 and the n1th column in the first discrete matrix to the second preset matrix parameters, update the parameters located in the first target row m1 and the first target column λ in the first discrete matrix to the third preset matrix parameters, and generate a second discrete matrix based on the updated first discrete matrix.

[0201] In the embodiment of the present disclosure, for example, the first discrete matrix shown in the above formula (22) is m1 is 1, n1 is 1, and the parameter in the first row and first column is 0; the 0 in the first row and first column is updated to 1; m1 is 1, λ is 2, and the parameter in the first row and second column is 1; the 1 in the first row and second column is updated to 0, thereby achieving the position conversion of the second preset matrix parameter in the m1th column, so that the n1th column includes the second preset matrix parameter. For example, the second discrete matrix can be expressed as formula (23).

[0202]

[0203] in, Represents the second discrete matrix.

[0204] Step 1056: When the m parameters of the second discrete matrix that meet the first target column λ are all third preset matrix parameters, update p and perform the step of determining the first target row m1 and the first target column λ where the p-th largest parameter in the n1-th column of the continuous matrix is ​​located, until the m parameters of the second discrete matrix that meet the first target column λ include the second preset matrix parameters and any column in the second discrete matrix includes the second preset matrix parameters, and then generate the target discrete matrix based on the second discrete matrix.

[0205] In the embodiment of the present disclosure, updating p means increasing p by a first fixed step value; for example, when p is 1, when the m parameters of the second discrete matrix that meet the first target column λ are all third preset matrix parameters, the first fixed step value is 1, p+1, and the updated p is 2.

[0206] When the m parameters of the second discrete matrix that meet the first target column λ are all the third preset matrix parameters, it indicates that the first aircraft is not allocated to the second aircraft λ corresponding to the first target column λ. It also indicates that the parameter adjustment has failed and needs to be readjusted. The first fixed step value is increased for p to find the second largest parameter from the n1th column of the continuous matrix.

[0207] The m parameters of the second discrete matrix that meet the first target column λ include the second preset matrix parameters, and any column in the second discrete matrix includes the second preset matrix parameters, which means that each first aircraft i is assigned to the second aircraft j, and each second aircraft j is assigned to at least one first aircraft i.

[0208] The second discrete matrix expressed as formula (23) above In the example, the three parameters of any column include 1, and the second discrete matrix represented by the above formula (23) is As the target discrete matrix, it indicates that a second UAV is assigned to each first UAV, where Second drone assigned The first drone Second drone assigned The first drone Second drone assigned

[0209] Step 1057: Generate the total state value corresponding to the particle based on the target discrete matrix.

[0210] In the disclosed embodiment, the total situation value corresponding to the particle is generated by the total situation value formula shown in the above formula (17).

[0211] For example, based on the target discrete matrix expressed in the above formula (23) The total state value corresponding to the particle

[0212] In some embodiments, step 106 includes steps 1061 to 1062, wherein:

[0213] Step 1061, when the number of iterations indicates the first iteration, determining a total state maximum value based on a total state value corresponding to at least one particle;

[0214] Step 1062: Determine the target total situation value corresponding to the optimization target based on the total situation maximum value for the number of iterations.

[0215] In the disclosed embodiment, in the first iteration, the maximum total situation value is determined from the total situation values ​​corresponding to N particles, and the maximum total situation value is used as the total situation maximum value; the total situation maximum value is used as the target total situation value.

[0216] For example, When , the target total situation value is obtained, and the target discrete matrix is ​​the target discrete matrix expressed by the above formula (23) At this time, the target allocation plan is the first UAV Second drone assigned The first drone Second drone assigned The first drone Second drone assigned

[0217] In some embodiments, step 106 includes steps 1063 to 1066, wherein:

[0218] Step 1063: When the number of iterations indicates the q-1th iteration, the maximum total situation value determined at the q-1th iteration is used as the maximum total situation value in history; wherein q is an integer greater than 1 and less than or equal to the iteration threshold;

[0219] Step 1064: when the number of iterations indicates the qth iteration, determining a total state maximum value for the total state value corresponding to at least one particle of the qth iteration;

[0220] Step 1065: If the total situation maximum value corresponding to the qth iteration is greater than or equal to the historical total situation maximum value, determine the target total situation value corresponding to the optimization target based on the total situation maximum value corresponding to the qth iteration;

[0221] Step 1066: When the total situation maximum value corresponding to the qth iteration is less than the historical total situation maximum value, determine the target total situation value corresponding to the optimization target based on the historical total situation maximum value.

[0222] In the embodiment of the present disclosure, for example, if q is equal to 3 and less than or equal to the iteration threshold, the total state maximum value determined in the q-1th iteration may be the total state maximum value corresponding to a particle among the N particles in the second iteration, or may be the total state maximum value corresponding to a particle among the N particles in the first iteration.

[0223] When the number of iterations is greater than 1, the target total state value corresponding to the optimization target obtained in step 1065 or step 1066 includes the maximum total state value among the total state values ​​corresponding to the q*N particles up to the qth iteration. The target total state value includes the historical maximum total state value or the maximum total state value obtained in the current iteration.

[0224] In some embodiments, step 107 includes: adding a second fixed step value to the iteration parameter, and using the iteration parameter added with the second fixed step value as the updated iteration parameter.

[0225] In the disclosed embodiment, the band parameter is used to indicate the number of iterations, and the second fixed step value is used to indicate an increase in the number of iterations. For example, the second fixed step value includes 1, and after the first iteration is completed, the updated iteration parameter t is 2.

[0226] In some embodiments, step 108 includes steps 1081 to 1084, wherein:

[0227] Step 1081, based on the updated iteration parameters, determining the target aurora optimization range in which the iteration parameters are located;

[0228] Step 1082, determining a target aurora optimization algorithm based on the target aurora optimization range;

[0229] Step 1083, using the target aurora optimization algorithm, based on the particle swarm matrix, updating the target continuous matrix corresponding to the target particles in the particle swarm matrix to generate a first target continuous matrix;

[0230] Step 1084 : Update the first target continuous matrix through the lens reverse learning algorithm to generate an updated continuous matrix corresponding to the target particle.

[0231] In the disclosed embodiment, the target aurora optimization range includes the first target aurora optimization range or the second target aurora optimization range, and the target aurora optimization algorithm includes the first target aurora optimization algorithm or the second target aurora optimization algorithm; the first target aurora optimization range corresponds to the first target aurora optimization algorithm, and the second target aurora optimization range corresponds to the second target aurora optimization algorithm.

[0232] In step 1081, the electronic device determines the target aurora optimization range based on the updated iteration parameter t, the iteration threshold T, the first aurora threshold and the second aurora threshold; or the electronic device determines the target aurora optimization range based on the second aurora threshold for the updated iteration parameter t.

[0233] For example, the first aurora threshold value includes r4 and the second aurora threshold value includes r5, wherein the values ​​of the first aurora threshold value r4 and the second aurora threshold value r5 are both within the range of [0, 1]. The values ​​of the first aurora threshold value r4 and the second aurora threshold value r5 may change with the change of the iteration parameter t, or may be fixed; the first aurora threshold value r4 and the second aurora threshold value r5 may be any value within the range of [0, 1]. When And r5<0.05, it is determined that the iteration parameters are within the first target aurora optimization range; when Or r5≥0.05, it is determined that the iteration parameters are in the second target aurora optimization range.

[0234] The target continuous matrix corresponding to the target particles in the particle swarm matrix is ​​updated twice by the target aurora optimization algorithm and the lens reverse learning algorithm to generate an updated continuous matrix corresponding to the target particles.

[0235] In some embodiments, the target Aurora optimization algorithm includes a first target Aurora optimization algorithm, and step 1083 includes step 301, wherein:

[0236] Step 301 : Based on any continuous matrix before updating in the particle swarm matrix except the target continuous matrix corresponding to the target particle, the target continuous matrix corresponding to the target particle is updated to generate a first target continuous matrix.

[0237] In the embodiment of the present disclosure, the target particle is used to indicate the particle corresponding to the continuous matrix to be updated, and the target continuous matrix is ​​used to indicate the continuous matrix corresponding to the target particle.

[0238] The first objective Aurora optimization algorithm can be expressed by formula (24).

[0239]

[0240] Among them, r3 represents the first target aurora parameter, and the value range of r3 is [0, 1]. When the number of particles N is greater than or equal to 2, X k represents the continuous matrix corresponding to particle k before the update, represents the continuous matrix corresponding to the updated particle k; a2 is greater than or equal to 1 and less than or equal to N, and a2 and k are not equal.

[0241] When the number of particles N is equal to 1, the electronic device updates the first preset matrix parameters to be updated for the target continuous matrix corresponding to the target particle based on any first preset matrix parameters before the update of the target continuous matrix except the first preset matrix parameters to be updated, and generates updated first preset matrix parameters; and generates an updated continuous matrix based on each updated first preset matrix parameter.

[0242] In some embodiments, the target Aurora optimization algorithm includes a second target Aurora optimization algorithm, and step 1083 includes steps 401 to 402, wherein:

[0243] Step 401, generating an average matrix based on each continuous matrix of the particle swarm matrix;

[0244] Step 402 : updating the target continuity matrix corresponding to the target particle based on the average matrix to generate a first target continuity matrix.

[0245] In the embodiment of the present disclosure, the second objective aurora optimization algorithm can be expressed by formula (25).

[0246]

[0247] Where r1 represents the second target auroral parameter, and the value range of r1 is [0, 0.5]; r2 represents the third target auroral parameter, and the value range of r2 is [0, 1]. levy(d) represents the random step size based on the Levy stable distribution, levy(d) ~ |d| 1 -β; β represents the Levy flight index, and the value range of β is (0, 2). T represents the iteration threshold. When the number of particles N is greater than or equal to 2, X k represents the continuous matrix corresponding to particle k before the update, represents the continuous matrix corresponding to the updated particle k; represents the mean matrix.

[0248] When the number of particles N is equal to 1, the electronic device generates an average parameter based on the target continuous matrix for the target particle; updates the first preset matrix parameters to be updated based on the average parameter to generate updated first preset matrix parameters; and generates an updated continuous matrix based on each updated first preset matrix parameter.

[0249] In some embodiments, step 1084 includes steps 501 and 502, wherein:

[0250] Step 501: Based on the mapping rule, update the m*n fourth preset matrix parameters of the first target continuous matrix to generate updated fourth preset matrix parameters, and generate a second target continuous matrix based on the updated fourth preset matrix parameters; wherein the updated m*n fourth preset matrix parameters of the first target continuous matrix are all within a first preset range;

[0251] Step 502: Based on the focal length of the lens, the second target continuous matrix is ​​updated to generate an updated continuous matrix corresponding to the target particles.

[0252] In the embodiment of the present disclosure, the electronic device generates the focal length of the lens based on the iteration parameter and the iteration threshold.

[0253] For example, the electronic device performs an exponential operation on the ratio of the iteration parameter to the iteration threshold to generate the focal length of the lens. The focal length of the lens can be expressed by formula (26).

[0254]

[0255] Where f is the focal length of the lens.

[0256] The lens reverse learning algorithm can be expressed by formula (27).

[0257]

[0258] in, Represents the updated continuous matrix corresponding to the target particle.

[0259] In some examples, the method further comprises:

[0260] Step 109 : When the iteration parameter is greater than the iteration threshold, a total situation value change curve is output based on the total situation maximum value corresponding to each iteration parameter.

[0261] In the disclosed embodiment, when the iteration parameter is greater than the iteration threshold, it indicates that the iteration is terminated. The electronic device can use MATLAB software to draw a total situation value change curve.

[0262] Figure 2 is a schematic diagram of a total situation value change curve provided by an embodiment of the present disclosure, such as Figure 2As shown, the aircraft includes unmanned aerial vehicles. The horizontal axis represents the number of iterations, and the vertical axis represents the total state value. The iteration threshold is 500, and the iteration parameter t is greater than or equal to 1 and less than or equal to 500. Before the iteration begins, the maximum total state value is 0. At the end of the iteration, the maximum total state value is between 17.8 and 18. When the number of iterations is greater than or equal to 1 and less than or equal to 300, the maximum total state value increases as the number of iterations increases. When the number of iterations is greater than 300 and less than or equal to 500, the maximum total state value remains unchanged, indicating that the maximum total state value has been achieved before the number of iterations reaches 300.

[0263] In the embodiment of the present disclosure, when the first group includes our party, the second group includes the enemy, and the aircraft includes a drone, Figure 3 This is a flow chart of a generation allocation scheme provided by an embodiment of the present disclosure, such as Figure 3 Shown, including:

[0264] Step 31, initializing the information of enemy and friendly drones;

[0265] Step 32: constructing conditional constraints and optimization targets based on the information of the enemy and friendly UAVs. The optimization targets are used to indicate how to optimize the combat effectiveness of the enemy and friendly UAVs while meeting the conditional constraints.

[0266] Step 33: Initialize the particle swarm matrix, which includes a continuous matrix corresponding to each particle, and each particle corresponds to one allocation scheme;

[0267] Step 34, for the number of iterations t, based on the continuous matrix corresponding to each particle, obtain the target discrete matrix corresponding to each particle, and the target discrete matrix meets the conditional constraints;

[0268] Step 35, generating a total state value corresponding to the particle based on the target discrete matrix corresponding to the particle;

[0269] Step 36, optimizing the optimization target based on the air combat target allocation scheme to obtain the maximum total situation value in t iterations;

[0270] Step 37, determining whether the number of iterations t is less than or equal to an iteration threshold T, where the iteration threshold T is an integer greater than or equal to 2. If so, proceed to step 38; if not, proceed to step 40;

[0271] Step 38, t=t+1;

[0272] Step 39: Based on the Aurora optimization algorithm and the lens reverse learning strategy, update the continuous matrix corresponding to each particle; and execute step 34;

[0273] Step 40: Generate a final air combat target allocation plan based on the target discrete matrix corresponding to the maximum total situation value.

[0274] In the embodiment of the present disclosure, the number m of our drones is greater than or equal to the number n of Difan drones. For example, m is equal to 3, n is equal to 2, and our three first drones are respectively the first drones. The first drone and the first drone The enemy's two second drones are the second drone and the second drone

[0275] Our drone information includes the first drone state information, initializes the first drone state information i of the first drone i, and the first state information of the first drone i includes the X coordinate Y coordinate Z coordinate Pitch angle Yaw angle Roll angle speed Firepower parameter A 1i , Detection capability parameter A 2i 、Maneuverability parameters B i , handling performance coefficient ε 1i , survivability coefficient ε 2i , range coefficient ε 3i , electronic countermeasure coefficient ε 4i , Radar maximum detection range and the weapon's maximum attack range The value of the first drone status information of each first drone may be different.

[0276] The enemy UAV information includes the second UAV state information, which initializes the second UAV state information j of the second UAV j. The second UAV state information includes the X coordinate Y coordinate Z coordinate Pitch angle Yaw angle Roll angle speed Firepower parameter A 1j , Detection capability parameter A 2j 、Maneuverability parameters B j , handling performance coefficient ε 1j , survivability coefficient ε 2j , range coefficient ε 3j and the electronic countermeasure coefficient ε 4j The value of the second drone status information of each second drone may be different.

[0277] Conditional constraints and optimization objectives are constructed based on the information of enemy and friendly UAVs. The optimization objective is used to indicate how to optimize the combat effectiveness of enemy and friendly UAVs while meeting the conditional constraints. The conditional constraints are to assign one second UAV to each first UAV, and to assign at least one first UAV to each second UAV. As shown in Table 3 above, there are up to six allocation schemes, and each allocation scheme meets the conditional constraints.

[0278] By randomly selecting values ​​in the range of [0, 1], a continuous matrix corresponding to each particle is constructed, and the initialization particle swarm matrix is ​​constructed based on the continuous matrices corresponding to N particles.

[0279] Based on the continuous matrix corresponding to any particle, the electronic device determines that in the discrete matrix corresponding to the continuous matrix, each row includes one second preset threshold parameter "1" and (n-1) third preset threshold parameters "0". The position of the second preset threshold parameter "1" in any row in the first discrete matrix is ​​the same as the position of the largest first preset threshold parameter in that row of the continuous matrix. Therefore, the discrete matrix can be represented as assigning a second drone to each first drone. However, in the first discrete matrix, it is possible that a first drone is not assigned to a second drone. In this case, in the columns of the second matrix corresponding to the first discrete matrix to which the first drone is not assigned, each parameter is the third preset threshold parameter "0".

[0280] At this point, parameter adjustment is required. Referring to steps 1054 to 1056 above, the first discrete matrix is ​​adjusted to obtain the target discrete matrix shown in formula (23). Based on the target discrete matrix and the total situation value formula, the total situation value corresponding to the particle is obtained. Thus, through steps 1054 to 1056 above, the target discrete matrix corresponding to each particle can satisfy the conditional constraints. The target discrete matrix can indicate the allocation scheme, ensuring that the allocation scheme can be quickly generated in a complex air combat environment. The total situation value corresponding to the allocation scheme is then obtained, improving computational efficiency.

[0281] The situation optimization algorithm includes an air combat target allocation scheme. This scheme is used to determine the maximum total situation value in t iterations from the total situation values ​​corresponding to multiple particles. This allows for a better allocation scheme to be gradually obtained through multiple iterations, thereby improving the combat effectiveness of the aircraft.

[0282] Whether the iteration number t is less than or equal to the iteration threshold T is determined to determine whether to terminate the iteration. The iteration threshold T may be a value set by relevant personnel, or the iteration threshold T may be determined by the number of allocation schemes that meet the conditional constraints and the number of particles N. The present disclosure does not limit the origin of the iteration threshold T.

[0283] When t≤T, the target Aurora optimization algorithm to be used is first determined. And r5<0.05, it is determined that the iteration parameter is within the first target aurora optimization range, and the target aurora optimization algorithm includes the first target aurora optimization algorithm. For example, the first target aurora optimization algorithm is the algorithm shown in formula (24); when Or r5≥0.05, it is determined that the iteration parameter is within the second target aurora optimization range, and the target aurora optimization algorithm includes the second target aurora optimization algorithm. For example, the second target aurora optimization algorithm is the algorithm shown in formula (25); thereby, the continuous matrix corresponding to the particle is initially updated by the target aurora optimization algorithm to obtain the continuous matrix corresponding to the particle after the initial update.

[0284] The lens reverse learning strategy corresponds to the lens reverse learning algorithm. Then, the continuous matrix initially updated by the particle is updated again using the lens reverse learning algorithm to obtain the updated continuous matrix corresponding to the particle; then, step 34 is executed.

[0285] When t is greater than T, it indicates that the iteration is ended. The target allocation scheme includes an air combat target allocation scheme. The maximum total situation value in step 40 represents the maximum total situation value determined from the total situation values ​​corresponding to T*N particles during the T iterations. Assuming that the target discrete matrix corresponding to the maximum total situation value is the target discrete matrix shown in the above formula (23), the air combat target allocation scheme includes the first UAV Second drone assigned The first drone Second drone assigned The first drone Second drone assigned Therefore, during the iteration process, the continuous matrix corresponding to the particles can be updated and the distribution scheme corresponding to the particles can be changed through the Aurora optimization algorithm and the lens reverse learning strategy; the N total situation values ​​after each iteration are compared through the situation optimization algorithm to obtain the maximum total situation value in this iteration. When t is greater than or equal to 2, the maximum total situation value in this iteration can be compared again with the maximum total situation value obtained in the previous iteration, thereby achieving the purpose of continuously optimizing the optimization target through iteration, so that the total situation value obtained by the optimization target is continuously close to the true optimal value, so that each UAV can clarify its mission, cooperate with each other, give play to its comprehensive advantages, comprehensively improve the overall effectiveness of the combat system, and maximize combat effectiveness.

[0286] The present disclosure is applicable to scenarios with limited computing time and / or limited computing resources. By controlling the value of the iteration threshold T due to limited computing time and / or limited computing resources, it is ensured that T iterations are performed within the limited computing time and / or limited computing resources, and a target allocation solution is quickly obtained based on the T iterations. For example, referring to Table 3 above, assuming that the best allocation solution is solution numbered 5 and the worst allocation solution is solution numbered 1, the limited computing time and / or limited computing resources cannot support the electronic device to obtain the total situation value corresponding to each allocation solution through enumeration. However, the electronic device can improve the superiority and speed of the multi-UAV air combat target allocation process through iteration within the limited computing time and / or limited computing resources by executing steps 101 to 108 above, thereby obtaining a target allocation solution. The target allocation solution is the best allocation solution obtained within the limited computing time and / or limited computing resources. The target allocation solution can be any solution except solution numbered 1. Therefore, the target allocation solution can be obtained within the limited computing time and / or limited computing resources, and the obtained target allocation solution is guaranteed not to be the worst solution.

[0287] Of course, the method described in the present disclosure can also be used in other scenarios, and the scenarios to which the present disclosure is applied are not limited here.

[0288] Figure 4 This is a block diagram of a target allocation device based on an aircraft provided by an embodiment of the present disclosure, such as Figure 4 As shown, the aircraft-based target allocation device 400 includes an acquisition module 401 , a first generation module 402 , a first determination module 403 , a second generation module 404 , a third generation module 405 , a second determination module 406 , a first update module 407 and a second update module 408 .

[0289] Acquisition module 401 is configured to acquire situation assessment data of each first aircraft i of a first group relative to a second aircraft j of a second group, the situation assessment data being used to at least indicate an assessment of the combat capability of the first aircraft i relative to the second aircraft j; the first group corresponds to m first aircraft, where m is an integer greater than or equal to 2, and i is greater than or equal to 1 and less than or equal to m; the second group corresponds to n second aircraft, where n is an integer greater than or equal to 2, and j is greater than or equal to 1 and less than or equal to n, and m ≥ n;

[0290] A first generating module 402 is configured to generate conditional constraints and an optimization objective based on the situation assessment data corresponding to the m first aircraft; wherein the optimization objective is configured to at least indicate the effectiveness of optimizing a battle between the m first aircraft and the n second aircraft while satisfying the conditional constraints;

[0291] A first determining module 403 is configured to determine, for at least one particle, a continuous matrix corresponding to each particle based on an iteration parameter, wherein the iteration parameter is used to indicate at least the number of iterations, the particle corresponds to the allocation scheme, and the continuous matrix includes first preset matrix parameters corresponding to each situation assessment data, and the first preset matrix parameters are used to indicate at least the value of the situation assessment data in the continuous matrix;

[0292] The second generating module 404 is used to generate a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle;

[0293] The third generating module 405 is used to generate the total situation value and the target discrete matrix corresponding to each particle based on the continuous matrix corresponding to each particle in the particle swarm matrix; wherein the target discrete matrix at least satisfies the constraint condition;

[0294] A second determination module 406 is configured to determine a target total situation value corresponding to an optimization target based on a total situation value corresponding to at least one particle using a situation optimization algorithm;

[0295] A first updating module 407, configured to update iteration parameters;

[0296] The second updating module 408 is used to update the continuous matrix corresponding to each particle based on the updated iteration parameter and the continuous matrix corresponding to at least one particle in the particle swarm matrix through the Aurora optimization algorithm and the lens reverse learning strategy when the iteration parameter is less than or equal to the iteration threshold, and trigger the second generation module to execute the step of generating a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle until the iteration parameter is greater than the iteration threshold, thereby obtaining the target total situation value corresponding to the optimization target, and determining the target allocation scheme based on the target discrete matrix corresponding to the target total situation value.

[0297] In some embodiments, the third generating module 405 is configured to determine, for each row in a continuous matrix corresponding to a particle of the particle swarm matrix, a maximum value of the first preset matrix parameters among the n first preset matrix parameters in each row; wherein the dimension of the continuous matrix is ​​m*n;

[0298] Determining that the maximum value of the first preset matrix parameter corresponds to the second preset matrix parameter, and determining that the first preset matrix parameters other than the maximum value of the first preset matrix parameter in the continuous matrix correspond to the third preset matrix parameter;

[0299] generating a first discrete matrix based on the second preset matrix parameter and the third preset matrix parameter corresponding to the maximum value of the first preset matrix parameter;

[0300] When the n1th column in the first discrete matrix satisfies m parameters that are all third preset matrix parameters, determining the first target row m1 where the pth largest parameter in the n1th column of the continuous matrix is ​​located, and determining the column where the maximum value of the first preset matrix parameter in the first target row m1 is located as the first target column λ; wherein n1 is greater than or equal to 1 and less than or equal to n, p is greater than or equal to 1 and less than or equal to m, m1 is greater than or equal to 1 and less than or equal to m, and λ is greater than or equal to 1 and less than or equal to n;

[0301] Update the third preset matrix parameters located in the first target row m1 and the n1th column in the first discrete matrix to the second preset matrix parameters, update the parameters located in the first target row m1 and the first target column λ in the first discrete matrix to the third preset matrix parameters, and generate a second discrete matrix based on the updated first discrete matrix;

[0302] If the m parameters of the second discrete matrix that meet the first target column λ are all third preset matrix parameters, update p, and perform the step of determining the first target row m1 and the first target column λ where the p-th largest parameter in the n1-th column of the continuous matrix is ​​located, until the m parameters of the second discrete matrix that meet the first target column λ include the second preset matrix parameters and any column in the second discrete matrix includes the second preset matrix parameters, generating a target discrete matrix based on the second discrete matrix;

[0303] Generate the total situation value corresponding to the particle based on the target discrete matrix.

[0304] In some embodiments, the second determining module 406 is configured to determine a total state maximum value based on a total state value corresponding to at least one particle when the iteration number indicates a first iteration;

[0305] According to the number of iterations, based on the maximum value of the total situation, the target total situation value corresponding to the optimization target is determined.

[0306] In some embodiments, the second determining module 406 is configured to, when the number of iterations indicates the q-1th iteration, use the total situation maximum value determined at the q-1th iteration as the historical total situation maximum value; where q is an integer greater than 1 and less than or equal to the iteration threshold;

[0307] When the number of iterations indicates the qth iteration, determining a total state maximum value for the total state value corresponding to at least one particle of the qth iteration;

[0308] When the total situation maximum value corresponding to the qth iteration is greater than or equal to the historical total situation maximum value, the target total situation value corresponding to the optimization target is determined based on the total situation maximum value corresponding to the qth iteration;

[0309] When the total situation maximum value corresponding to the qth iteration is less than the historical total situation maximum value, the target total situation value corresponding to the optimization target is determined based on the historical total situation maximum value.

[0310] In some embodiments, the second updating module 408 is configured to determine, based on the updated iteration parameters, the target aurora optimization range in which the iteration parameters are located;

[0311] Determine the target aurora optimization algorithm based on the target aurora optimization range;

[0312] Through the target aurora optimization algorithm, based on the particle swarm matrix, the target continuous matrix corresponding to the target particles in the particle swarm matrix is ​​updated to generate the first target continuous matrix;

[0313] The first target continuous matrix is ​​updated through the lens reverse learning algorithm to generate an updated continuous matrix corresponding to the target particle.

[0314] In some embodiments, the second updating module 408 is configured to update the target continuous matrix corresponding to the target particle based on any continuous matrix before update in the particle swarm matrix except the target continuous matrix corresponding to the target particle, to generate a first target continuous matrix.

[0315] In some embodiments, the second updating module 408 is configured to generate an average matrix based on each continuous matrix of the particle swarm matrix;

[0316] The target continuity matrix corresponding to the target particle is updated based on the average matrix to generate a first target continuity matrix.

[0317] In some embodiments, the apparatus 400 further includes an output module configured to output a total situation value change curve based on a total situation maximum value corresponding to each iteration parameter when the iteration parameter is greater than an iteration threshold.

[0318] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0319] Figure 5 1 is a block diagram showing a structure of an electronic device 500 according to an exemplary embodiment. For example, the electronic device 500 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0320] Reference Figure 5, electronic device 500 may include one or more of the following components: a processing component 502 , a memory 504 , a power component 506 , a multimedia component 508 , an audio component 510 , an input / output (I / O) interface 512 , a sensor component 514 , and a communication component 516 .

[0321] The processing component 502 generally controls the overall operation of the electronic device 500, such as operations associated with at least one of display, phone calls, data communications, camera operation, and recording operations. The processing component 502 may include one or more processors 520 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 502 may include one or more modules to facilitate interaction between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate interaction between the multimedia component 508 and the processing component 502.

[0322] The memory 504 is configured to store various types of data to support operations on the electronic device 500. Examples of such data include at least one of the following: instructions for any application or method operating on the electronic device 500, contact data, phone book data, messages, pictures, and videos. The memory 504 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0323] The power supply component 506 provides power to various components of the electronic device 500. The power supply component 506 may include at least one of the following: a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 500.

[0324] The multimedia component 508 includes a screen that provides an output interface between the electronic device 500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front camera and / or a rear camera. When the electronic device 500 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0325] The audio component 510 is configured to output and / or input audio signals. For example, the audio component 510 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 500 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 504 or transmitted via the communication component 516. In some embodiments, the audio component 510 also includes a speaker for outputting audio signals.

[0326] I / O interface 512 provides an interface between processing component 502 and peripheral interface modules, such as a keyboard, click wheel, and buttons. These buttons may include, but are not limited to, a home button, volume buttons, a start button, and a lock button.

[0327] The sensor assembly 514 includes one or more sensors for providing various aspects of the status assessment of the electronic device 500. For example, the sensor assembly 514 can detect the open / closed state of the electronic device 500, the relative positioning of components, such as the display and keypad of the electronic device 500. The sensor assembly 514 can also detect changes in the position of the electronic device 500 or a component thereof, the presence or absence of user contact with the electronic device 500, the orientation or acceleration / deceleration of the electronic device 500, and changes in the temperature of the electronic device 500. The sensor assembly 514 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 can also include an optical sensor, such as a complementary metal oxide semiconductor (CMOS) or charge coupled device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 can also include, but is not limited to, at least one of the following: an accelerometer, a gyroscope, a magnetic sensor, a pressure sensor, and a temperature sensor.

[0328] The communication component 516 is configured to facilitate communication between the electronic device 500 and other devices in a wired or wireless manner. The electronic device 500 can access a wireless network based on a communication standard, such as Wi-Fi, 4G, 5G, or a combination thereof. In an exemplary embodiment, the communication component 516 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 516 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0329] In an exemplary embodiment, the electronic device 500 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components.

[0330] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is further provided, such as a memory 504 including executable instructions or a computer program. The instructions or computer program can be executed by the processor 520 of the electronic device 500 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0331] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by the processor of an electronic device, enables the electronic device to execute any one of the above-mentioned aircraft-based target allocation methods of the embodiments of the present disclosure. For example, the method includes: obtaining situation assessment data of each first aircraft i of the first group relative to the second aircraft j of the second group, the situation assessment data at least used to indicate the combat capability assessment of the first aircraft i relative to the second aircraft j; the first group corresponds to m first aircraft, m includes an integer greater than or equal to 2, i is greater than or equal to 1 and less than or equal to m; the second group corresponds to n second aircraft, n includes an integer greater than or equal to 2, j is greater than or equal to 1 and less than or equal to n, m≥n; based on the situation assessment data corresponding to the m first aircraft, generate conditional constraints and optimization targets; wherein the optimization target is at least used to indicate the effectiveness of optimizing the combat between the m first aircraft and the n second aircraft under the condition that the conditional constraints are met; based on the iteration parameter, for at least one particle, determine the continuous matrix corresponding to each particle; wherein the iteration parameter is at least used to indicate the number of iterations, the particle corresponds to the allocation scheme, the continuous matrix includes the first preset matrix parameters corresponding to each situation assessment data, the first preset matrix parameters are the first preset matrix parameters corresponding to each situation assessment data, and the first preset matrix parameters are the first preset matrix parameters corresponding to each situation assessment data. Assume that a matrix parameter is at least used to indicate the value of the situation assessment data in the continuous matrix; based on the continuous matrix corresponding to each particle, generate a particle swarm matrix for the iteration parameter; based on the continuous matrix corresponding to each particle in the particle swarm matrix, generate a total situation value and a target discrete matrix corresponding to each particle; wherein the target discrete matrix at least satisfies the constraint condition; through the situation optimization algorithm, determine the target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one particle; update the iteration parameter; when the iteration parameter is less than or equal to the iteration threshold, through the Aurora optimization algorithm and the lens reverse learning strategy, based on the updated iteration parameter and the continuous matrix corresponding to at least one particle in the particle swarm matrix, update the continuous matrix corresponding to each particle, and perform the step of generating a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle, until the iteration parameter is greater than the iteration threshold, obtain the target total situation value corresponding to the optimization target, and determine the target allocation scheme based on the target discrete matrix corresponding to the target total situation value.

[0332] Figure 6 6 is a block diagram of an aircraft-based target allocation device 600 provided by an embodiment of the present disclosure. For example, the device 600 can be provided as a server. Figure 6Apparatus 600 includes a processing component 622, which further includes one or more processors and memory resources represented by memory 632 for storing instructions, such as applications, that are executable by processing component 622. The applications stored in memory 632 may include one or more modules, each corresponding to a set of instructions. Furthermore, processing component 622 is configured to execute instructions to perform any of the aforementioned aircraft-based target allocation methods. For example, the method includes: obtaining situation assessment data of each first aircraft i of the first group relative to the second aircraft j of the second group, the situation assessment data is at least used to indicate the combat capability assessment of the first aircraft i relative to the second aircraft j; the first group corresponds to m first aircraft, m includes an integer greater than or equal to 2, i is greater than or equal to 1 and less than or equal to m; the second group corresponds to n second aircraft, n includes an integer greater than or equal to 2, j is greater than or equal to 1 and less than or equal to n, m≥n; based on the situation assessment data corresponding to the m first aircraft, generating conditional constraints and optimization objectives; wherein the optimization objective is at least used to indicate the effectiveness of optimizing the combat between the m first aircraft and the n second aircraft when the conditional constraints are met; based on the iteration parameter, for at least one particle, determining the continuous matrix corresponding to each particle; wherein the iteration parameter is at least used to indicate the number of iterations, the particle corresponds to the allocation scheme, the continuous matrix includes the first preset matrix parameters corresponding to each situation assessment data, the first preset matrix parameters are the same as the first preset matrix parameters. Assume that a matrix parameter is at least used to indicate the value of the situation assessment data in the continuous matrix; based on the continuous matrix corresponding to each particle, generate a particle swarm matrix for the iteration parameter; based on the continuous matrix corresponding to each particle in the particle swarm matrix, generate a total situation value and a target discrete matrix corresponding to each particle; wherein the target discrete matrix at least satisfies the constraint condition; through the situation optimization algorithm, determine the target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one particle; update the iteration parameter; when the iteration parameter is less than or equal to the iteration threshold, through the Aurora optimization algorithm and the lens reverse learning strategy, based on the updated iteration parameter and the continuous matrix corresponding to at least one particle in the particle swarm matrix, update the continuous matrix corresponding to each particle, and perform the step of generating a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle, until the iteration parameter is greater than the iteration threshold, obtain the target total situation value corresponding to the optimization target, and determine the target allocation scheme based on the target discrete matrix corresponding to the target total situation value.

[0333] The device 600 may also include a power supply component 626 configured to perform power management of the device 600, a wired or wireless network interface 650 configured to connect the device 600 to a network, and an input / output (I / O) interface 658. The device 600 may operate an operating system stored in the memory 632, such as Windows Server™, Mac OS X™, Unix™ Linux™, Free BSD™, or the like.

[0334] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

[0335] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A target allocation method based on aircraft, characterized in that: include: Obtaining situation assessment data for each first aircraft i of a first group relative to a second aircraft j of a second group, the situation assessment data being used to at least indicate an assessment of the combat capability of the first aircraft i relative to the second aircraft j; the first group corresponds to m first aircraft, where m is an integer greater than or equal to 2, and i is greater than or equal to 1 and less than or equal to m; the second group corresponds to n second aircraft, where n is an integer greater than or equal to 2, and j is greater than or equal to 1 and less than or equal to n, and m ≥ n; generating conditional constraints and an optimization objective based on the situation assessment data corresponding to the m first aircraft; wherein the optimization objective is at least used to indicate optimizing the effectiveness of a battle between the m first aircraft and the n second aircraft while satisfying the conditional constraints; Based on an iteration parameter, determining, for at least one particle, a continuous matrix corresponding to each particle; wherein the iteration parameter is used to indicate at least the number of iterations, the particle corresponds to the allocation scheme, and the continuous matrix includes a first preset matrix parameter corresponding to each situation assessment data, and the first preset matrix parameter is used to indicate at least the value of the situation assessment data in the continuous matrix; generating a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each of the particles; Based on the continuous matrix corresponding to each particle in the particle swarm matrix, generating a total situation value and a target discrete matrix corresponding to each particle; wherein the target discrete matrix at least satisfies a constraint condition; Determining, by a situation optimization algorithm, a target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one of the particles; updating the iteration parameters; When the iteration parameter is less than or equal to the iteration threshold, the Aurora optimization algorithm and the lens reverse learning strategy are used to update the continuous matrix corresponding to each particle based on the updated iteration parameter and the continuous matrix corresponding to at least one particle in the particle swarm matrix, and the step of generating a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle is performed until the iteration parameter is greater than the iteration threshold, thereby obtaining the target total situation value corresponding to the optimization target, and determining the target allocation scheme based on the target discrete matrix corresponding to the target total situation value.

2. The method according to claim 1, characterized in that The step of generating a total situation value and a target discrete matrix corresponding to each particle based on the continuous matrix corresponding to each particle in the particle swarm matrix includes: In the continuous matrix corresponding to the particle of the particle swarm matrix, for each row in the continuous matrix, determining a maximum value of the first preset matrix parameters among n first preset matrix parameters in each row; wherein the dimension of the continuous matrix is ​​m*n; Determining that the maximum value of the first preset matrix parameter corresponds to a second preset matrix parameter, and determining that the first preset matrix parameters in the continuous matrix other than the maximum value of the first preset matrix parameter correspond to a third preset matrix parameter; generating a first discrete matrix based on the second preset matrix parameter and the third preset matrix parameter corresponding to the maximum value of the first preset matrix parameter; When the n1th column in the first discrete matrix satisfies m parameters that are all third preset matrix parameters, determining the first target row m1 where the pth largest parameter in the n1th column in the continuous matrix is ​​located, and determining the column where the maximum value of the first preset matrix parameter in the first target row m1 is located as the first target column λ; wherein n1 is greater than or equal to 1 and less than or equal to n, p is greater than or equal to 1 and less than or equal to m, m1 is greater than or equal to 1 and less than or equal to m, and λ is greater than or equal to 1 and less than or equal to n; Updating the third preset matrix parameters located in the first target row m1 and the n1-th column in the first discrete matrix to second preset matrix parameters, updating the parameters located in the first target row m1 and the first target column λ in the first discrete matrix to third preset matrix parameters, and generating a second discrete matrix based on the updated first discrete matrix; If the m parameters of the second discrete matrix that meet the first target column λ are all third preset matrix parameters, update p, and perform the step of determining the first target row m1 and the first target column λ where the p-th largest parameter in the n1-th column of the continuous matrix is ​​located, until the m parameters of the second discrete matrix that meet the first target column λ include the second preset matrix parameters and any column in the second discrete matrix includes the second preset matrix parameters, generating the target discrete matrix based on the second discrete matrix; A total situation value corresponding to the particle is generated based on the target discrete matrix.

3. The method according to claim 1, characterized in that Determining the target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one particle by using a situation optimization algorithm includes: When the number of iterations indicates a first iteration, determining a total state maximum value based on the total state value corresponding to at least one of the particles; For the number of iterations, based on the total situation maximum value, a target total situation value corresponding to the optimization target is determined.

4. The method according to claim 1, wherein Determining the target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one particle by using a situation optimization algorithm includes: When the number of iterations is used to indicate the q-1th iteration, the maximum total situation value determined in the q-1th iteration is used as the maximum total historical situation value; wherein q is an integer greater than 1 and less than or equal to the iteration threshold; When the number of iterations indicates the qth iteration, determining a total state maximum value for the total state value corresponding to at least one particle in the qth iteration; When the total situation maximum value corresponding to the qth iteration is greater than or equal to the historical total situation maximum value, determining the target total situation value corresponding to the optimization target based on the total situation maximum value corresponding to the qth iteration; When the total situation maximum value corresponding to the qth iteration is less than the historical total situation maximum value, the target total situation value corresponding to the optimization target is determined based on the historical total situation maximum value.

5. The method according to claim 1, wherein The method of updating the continuous matrix corresponding to each particle based on the updated iteration parameter and the continuous matrix corresponding to at least one particle in the particle swarm matrix by using the Aurora optimization algorithm and the lens reverse learning strategy includes: Based on the updated iteration parameter, determining a target aurora optimization range in which the iteration parameter is located; Determining a target aurora optimization algorithm based on the target aurora optimization range; By using the target aurora optimization algorithm, based on the particle swarm matrix, the target continuous matrix corresponding to the target particles in the particle swarm matrix is ​​updated to generate a first target continuous matrix; The first target continuous matrix is ​​updated through a lens reverse learning algorithm to generate the updated continuous matrix corresponding to the target particle.

6. The method according to claim 5, characterized in that The target continuous matrix corresponding to the target particles in the particle swarm matrix is ​​updated based on the particle swarm matrix by the target aurora optimization algorithm to generate a first target continuous matrix, including: Based on any of the continuous matrices before updating in the particle swarm matrix except the target continuous matrix corresponding to the target particle, the target continuous matrix corresponding to the target particle is updated to generate a first target continuous matrix.

7. The method according to claim 5, characterized in that The target continuous matrix corresponding to the target particles in the particle swarm matrix is ​​updated based on the particle swarm matrix by the target aurora optimization algorithm to generate a first target continuous matrix, including: Generate an average matrix based on each of the continuous matrices of the particle swarm matrix; The target continuity matrix corresponding to the target particle is updated based on the average matrix to generate a first target continuity matrix.

8. A target allocation device based on an aircraft, characterized in that: include: an acquisition module configured to acquire situation assessment data of each first aircraft i of a first group relative to a second aircraft j of a second group, the situation assessment data being used to at least indicate an assessment of the combat capability of the first aircraft i relative to the second aircraft j; the first group corresponding to m first aircraft, where m is an integer greater than or equal to 2, i is greater than or equal to 1 and less than or equal to m; the second group corresponding to n second aircraft, where n is an integer greater than or equal to 2, j is greater than or equal to 1 and less than or equal to n, and m ≥ n; a first generating module, configured to generate conditional constraints and an optimization objective based on the situation assessment data corresponding to the m first aircraft; wherein the optimization objective is at least used to indicate optimizing the effectiveness of a combat between the m first aircraft and the n second aircraft while satisfying the conditional constraints; A first determining module is configured to determine, for at least one particle, a continuous matrix corresponding to each particle based on an iteration parameter, wherein the iteration parameter is used to indicate at least the number of iterations, the particle corresponds to the allocation scheme, the continuous matrix includes a first preset matrix parameter corresponding to each situation assessment data, and the first preset matrix parameter is used to indicate at least the value of the situation assessment data in the continuous matrix; A second generating module is configured to generate a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle; A third generating module is configured to generate a total situation value and a target discrete matrix corresponding to each particle based on the continuous matrix corresponding to each particle in the particle swarm matrix; wherein the target discrete matrix at least satisfies a constraint condition; A second determining module is configured to determine a target total situation value corresponding to the optimization target based on the total situation value corresponding to at least one particle through a situation optimization algorithm; A first updating module, configured to update the iteration parameters; The second updating module is used to update the continuous matrix corresponding to each particle based on the updated iteration parameter and the continuous matrix corresponding to at least one particle in the particle swarm matrix through the Aurora optimization algorithm and the lens reverse learning strategy when the iteration parameter is less than or equal to the iteration threshold, and trigger the second generation module to execute the step of generating a particle swarm matrix for the iteration parameter based on the continuous matrix corresponding to each particle until the iteration parameter is greater than the iteration threshold, thereby obtaining the target total situation value corresponding to the optimization target, and determining the target allocation scheme based on the target discrete matrix corresponding to the target total situation value.

9. An electronic device, characterized in that: include: processor; memory for storing computer programs or instructions; The processor executes the computer program or instructions to implement the steps of the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing a computer program or instruction, characterized in that: When the computer program or instructions in the storage medium are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images