Multi-agent formation method and device based on bee colony algorithm

Abstract

The invention provides a multi-agent formation method and device based on a bee colony algorithm. The method comprises the following steps: acquiring a multi-agent cluster; if the multi-agent cluster does not arrive at the destination, determining reconnaissance peak multi-agent information in the multi-agent cluster; determining the movement speed and the movement direction of worker bee multi-agents in the multi-agent cluster according to the scout peak multi-agent information, the destination and a preset formation rule by adopting an ant colony algorithm; the preset formation rules at least comprise an aggregation rule, an alignment rule, a collision avoidance rule, a random rule and a following rule; the multi-agent cluster is controlled to arrive at a destination according to reconnaissance peak multi-agent information and the movement speed and the movement direction of worker bee multi-agents, a multi-agent-oriented formation method is constructed based on a bee colony algorithm, in the bee colony algorithm, artificial bees serve as searchers, targets are searched randomly in a search space, and information transmission and communication are continuously conducted. Therefore, a globally optimal solution can be jointly found.

Description

Technical Field

[0001] The present invention belongs to the field of multi-agent technology, and in particular relates to a multi-agent formation method and device based on a bee colony algorithm. Background Art

[0002] Currently, when forming a team of multiple agents, the following methods are usually used:

[0003] (1) Multi-agent formation method based on basic traditional planning algorithm.

[0004] Dynamic programming algorithm is a common algorithm for solving multi-level decision optimization problems. This algorithm is applied to UAV trajectory planning. It requires a relatively simple model and does not require the continuity of the threat field. It can obtain the global optimal solution, but the disadvantage is that as the planning area expands, it will be limited by the state space and there will be a combinatorial explosion. It can only be applied to searches within a small range (such as when the UAV is operating at high altitude and the threat is single, it can achieve good results) and is not easy to apply to three-dimensional space. Therefore, it is necessary to reduce the dimension and simplify the calculation to increase the speed, such as decomposing the three-dimensional trajectory into two two-dimensional trajectories in the horizontal and vertical directions and calculating them separately, or converting the three-dimensional optimal trajectory planning into a two-dimensional trajectory planning on a safety surface through digital map preprocessing technology.

[0005] The derivative-related methods mainly include the steepest descent method, Newton method, conjugate gradient method, quasi-Newton method, trust region method and least squares method, among which the steepest descent method is currently used more. The steepest descent method was proposed by J.Asseo in 1982. It uses the steepest descent method to solve the terrain following (TF: Terrain Following) and terrain avoiding (TA: Terrain Avoiding) problems. This method is relatively simple and converges quickly. It requires the first-order terrain to be continuous. Compared with the optimal control method, it does not require high terrain requirements: However, since the algorithm is based on the gradient of the objective function, it requires the derivative function to be continuous, the iterative calculation amount is large, and it is easy to fall into the local optimal solution. Usually, the consideration of threats in this algorithm is too simple, and only the angle between the flight direction and the threat direction is used as the basis for calculating the threat size. Superimposing the threat field on the terrain is equivalent to processing the threat field by increasing the height of the terrain. Therefore, it cannot reflect the shielding effect of the terrain on the threat.

[0006] (2) Multi-agent formation method based on genetic algorithm

[0007] Genetic Algorithm (GA) is a robust search algorithm that can be used for complex system optimization. The algorithm obtains new individuals through chromosome replication, crossover, and mutation, and evaluates the performance of individuals to obtain the optimal individual that meets the requirements. Compared with traditional optimization algorithms, it has the following main characteristics: (1) GA uses the encoding of decision variables as the operation object. Traditional optimization algorithms often directly use the actual value of the decision variable itself, while genetic algorithms use some form of its encoding. (2) GA directly uses fitness as search information without the need for other auxiliary information such as derivatives. (3) GA uses search information from multiple points and has implicit parallelism. (4) GA uses probabilistic search technology rather than deterministic rules. However, due to the time and computer resource constraints of drone trajectory planning, GA will be premature and cannot obtain the global optimal solution.

[0008] Polar coordinates are used to describe threat positions and track points, and the path encoding is reduced from two dimensions to one dimension, which improves the optimization efficiency by reducing the search space. The genetic algorithm is used and the calculation method evaluated by the reconnaissance efficiency index is used to solve the problem of quantifying the reconnaissance efficiency in track planning. The reconnaissance track obtained by this method can effectively improve the reconnaissance efficiency of the UAV. The key to the genetic algorithm lies in the encoding of the group. After a large number of experiments, it is shown that the use of floating-point encoding is more efficient than binary encoding in terms of CPU computing time. The selection of the initial group should be diverse so that each individual in the planning space has the opportunity to participate in the evolution. The track is encoded with real values ​​using the coordinate information of the navigation point and a check bit. The track group is analyzed in combination with the constraints of the track and the evaluation function, and then several self-set genetic operators are used to operate the group. The B-spline curve that is more in line with reality is used to represent the track, and the global and local tracks of the UAV are planned. The advantages of the genetic algorithm, such as good group search performance and inherent parallel computing capabilities, make this algorithm widely used in track planning. However, there is a time-consuming problem in path planning using the genetic algorithm. It is generally applied to the planning process of the reference track, and it is difficult to apply it to real-time planning. The algorithm structure is modified to separate the mutation operation from the crossover operation, making it an independent genetic optimization operation parallel to the crossover; in the crossover operation, individuals are paired, and the crossover point is determined by chaotic sequences, and single-point crossover is implemented to ensure the convergence accuracy of the algorithm; in the mutation operation, chaotic sequences are used to mutate multiple genes in the chromosome to avoid premature algorithm maturation.

[0009] The multi-agent formation method can be summarized into the above two methods. The first method has poor effect in complex scenarios, while the second method is prone to fall into local optimality. Therefore, how to provide a multi-agent formation method and device based on the bee colony algorithm has become a technical problem that needs to be solved urgently in this field. Summary of the invention

[0010] The purpose of the present invention is to provide a multi-agent formation method and device based on a bee colony algorithm.

[0011] According to a first aspect of the present invention, a multi-agent formation method based on a bee colony algorithm is provided, comprising:

[0012] Get a multi-agent cluster;

[0013] Determining whether the multi-agent cluster has reached the destination;

[0014] If the multi-agent cluster has not reached the destination, determining the reconnaissance peak multi-agent information in the multi-agent cluster;

[0015] Using an ant colony algorithm, according to the reconnaissance peak multi-agent information, the destination and pre-set formation rules, the movement speed and movement direction of the worker bee multi-agent in the multi-agent cluster are determined; the pre-set formation rules at least include aggregation rules, alignment rules, collision avoidance rules, random rules and following rules;

[0016] According to the reconnaissance peak multi-agent information and the movement speed and direction of the worker bee multi-agent, the multi-agent cluster is controlled to reach the destination.

[0017] Optionally, the aggregation rule is used to describe the tendency of multi-agents to form a population by assuming that a multi-agent tends to move towards the center of the multi-agents around it; the alignment rule is used to describe that the multi-agents fly at the same speed and use it as a guide for neighboring individuals; the collision avoidance rule is used for the habit of multi-agents to avoid collisions; the random rule is used to change the individual decisions of the moving multi-agents; and the following rule is used for the worker bee multi-agents to continuously follow the movement of the scout bees.

[0018] Optionally, the clustering rule is used to make the worker bee multi-agents move in a clustered manner, calculate the flight angle of a single worker bee multi-agent so that it will not break away from the cluster, and define d max As a warning sign that a single worker bee multi-agent is about to leave the worker bee multi-agent cluster, when the distance between any two worker bees is greater than d max When the aggregation rule is triggered;

[0019] The collision avoidance rule is used to keep a safe distance between multiple agents in the worker bee colony to avoid collisions with each other. min As the alarm distance between worker bee swarm multi-agents, when the distance between any two worker bee multi-agents is less than d min When , the collision avoidance rule is triggered;

[0020] The random rule is used to add a random component to the movement of each worker bee multi-agent in the worker bee swarm multi-agent to prevent deadlock and increase exploration;

[0021] The following rule is used for each individual in the worker bee colony multi-agent to follow the scout bee multi-agent to reach the target point.

[0022] Optionally, the adopting of an ant colony algorithm to determine the movement speed and movement direction of the worker bee multi-agents in the multi-agent cluster according to the reconnaissance peak multi-agent information, the destination and a pre-set formation rule includes:

[0023] According to the pre-set formation rules, the movement factor of the worker bee multi-agent at each moment is determined;

[0024] According to the movement factors and corresponding weights of the worker bee multi-agents, the movement speed and movement direction of each worker bee multi-agent are calculated.

[0025] Optionally, the method further comprises:

[0026] When the scout bee multi-agent is destroyed, the worker bee multi-agent closest to the scout bee multi-agent is selected as a new scout bee multi-agent, and the new scout bee multi-agent carries the destination location.

[0027] Optionally, the bee colony algorithm modeling process includes at least multiple classes, and the multiple classes include at least: Main class, Leader class, Leader class, UAV class, Enemy class and ABC class, wherein the Main class is used to generate objects of the Leader class. The Leader class is a scout peak multi-agent, the object of the UAV class is a follower drone, and the Leader class is used to generate a scout peak multi-agent through the add_Leader method.

[0028] According to a second aspect of the present invention, a multi-agent formation device based on a bee colony algorithm is provided, comprising:

[0029] Acquisition module, used to obtain multi-agent clusters;

[0030] A judgment module, used to judge whether the multi-agent cluster has reached the destination;

[0031] A first determination module, configured to determine the reconnaissance peak multi-agent information in the multi-agent cluster if the multi-agent cluster has not reached the destination;

[0032] A second determination module is used to determine the movement speed and movement direction of the worker bee multi-agent in the multi-agent cluster by using an ant colony algorithm according to the reconnaissance peak multi-agent information, the destination and a pre-set formation rule; the pre-set formation rule at least includes a gathering rule, an alignment rule, a collision avoidance rule, a random rule and a following rule;

[0033] A control module is used to control the multi-agent cluster to reach the destination according to the multi-agent information of the scouting peak and the movement speed and direction of the worker bee multi-agent.

[0034] Optionally, the aggregation rule is used to describe the tendency of multi-agents to form a population by assuming that a multi-agent tends to move towards the center of the multi-agents around it; the alignment rule is used to describe that the multi-agents fly at the same speed and use it as a guide for neighboring individuals; the collision avoidance rule is used for the habit of multi-agents to avoid collisions; the random rule is used to change the individual decisions of the moving multi-agents; and the following rule is used for the worker bee multi-agents to continuously follow the movement of the scout bees.

[0035] Optionally, the clustering rule is used to make the worker bee multi-agents move in a clustered manner, calculate the flight angle of a single worker bee multi-agent so that it will not break away from the cluster, and define d max As a warning sign that a single worker bee multi-agent is about to leave the worker bee multi-agent cluster, when the distance between any two worker bees is greater than d max When the aggregation rule is triggered;

[0036] The collision avoidance rule is used to keep a safe distance between multiple agents in the worker bee colony to avoid collisions with each other. min As the alarm distance between worker bee swarm multi-agents, when the distance between any two worker bee multi-agents is less than d min When , the collision avoidance rule is triggered;

[0037] The random rule is used to add a random component to the movement of each worker bee multi-agent in the worker bee swarm multi-agent to prevent deadlock and increase exploration;

[0038] The following rule is used for each individual in the worker bee colony multi-agent to follow the scout bee multi-agent to reach the target point.

[0039] Optionally, the second determining module is used to:

[0040] According to the pre-set formation rules, the movement factor of the worker bee multi-agent at each moment is determined;

[0041] According to the movement factors and corresponding weights of the worker bee multi-agents, the movement speed and movement direction of each worker bee multi-agent are calculated.

[0042] Optionally, the control module is used to:

[0043] When the scout bee multi-agent is destroyed, the worker bee multi-agent closest to the scout bee multi-agent is selected as a new scout bee multi-agent, and the new scout bee multi-agent carries the destination location.

[0044] Optionally, the bee colony algorithm modeling process includes at least multiple classes, and the multiple classes include at least: Main class, Leader class, Leader class, UAV class, Enemy class and ABC class, wherein the Main class is used to generate objects of the Leader class. The Leader class is a scout peak multi-agent, the object of the UAV class is a follower drone, and the Leader class is used to generate a scout peak multi-agent through the add_Leader method.

[0045] In a third aspect, the present application shows an electronic device, which includes: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the method described in any of the above aspects.

[0046] In a fourth aspect, the present application illustrates a non-temporary computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute a method as described in any of the above aspects.

[0047] In a fifth aspect, the present application illustrates a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the method described in any of the above aspects.

[0048] The beneficial effects brought by the present invention are as follows:

[0049] It can be seen from the above scheme that the embodiment of the present invention provides a multi-agent formation method and device based on the bee colony algorithm, including: obtaining a multi-agent cluster; judging whether the multi-agent cluster has reached the destination; if the multi-agent cluster has not reached the destination, determining the reconnaissance peak multi-agent information in the multi-agent cluster; using the ant colony algorithm, according to the reconnaissance peak multi-agent information, the destination and the pre-set formation rules, determining the movement speed and movement direction of the worker bee multi-agent in the multi-agent cluster; the pre-set formation rules at least include aggregation rules, alignment rules, collision avoidance rules, random rules and following rules; according to The multi-agent information of the reconnaissance peak and the movement speed and direction of the worker bee multi-agent are used to control the multi-agent cluster to reach the destination. Based on the bee swarm algorithm, a multi-agent formation method is constructed. In the bee swarm algorithm, artificial bees act as searchers, randomly search for targets in the search space, and continuously transmit and communicate information to jointly discover the global optimal solution. Compared with previous methods for solving the multi-agent formation problem, the formation scheme based on the bee swarm algorithm determined by the present invention can perform designated tasks with less time and resource costs, and can control multi-agents to reach the target point under the premise of ensuring that there is no collision between each other. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic diagram of a process flow of a multi-agent formation method based on a bee colony algorithm provided according to an embodiment;

[0051] Figure 2 A basic flow chart of a bee colony algorithm provided according to an embodiment;

[0052] Figure 3 A flow chart of following bee movement provided according to an embodiment;

[0053] Figure 4 A logic flow chart of a bee colony algorithm provided according to an embodiment;

[0054] Figure 5 A bee colony algorithm class diagram provided according to an embodiment;

[0055] Figure 6 An initial flight diagram of a drone cluster provided according to an embodiment;

[0056] Figure 7 An orderly flight diagram of a drone cluster provided according to an embodiment;

[0057] Figure 8 A reordered flight graph of a drone cluster provided according to an embodiment;

[0058] Fig. 9 A target point diagram of a drone cluster provided according to an embodiment;

[0059] Fig.10 This is a structural block diagram of a multi-agent formation device based on a bee swarm algorithm in the present application.

[0060] Fig.11 It is a block diagram of an electronic device of the present application.

[0061] Fig.12 It is a block diagram of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] Reference Figure 1, shows a flowchart of a multi-agent formation method based on a bee colony algorithm of the present application, which can be applied to electronic devices, wherein the method specifically may include the following steps:

[0064] S101, obtaining a multi-agent cluster;

[0065] S102, determining whether the multi-agent cluster has reached the destination;

[0066] S103, if the multi-agent cluster has not reached the destination, determining the reconnaissance peak multi-agent information in the multi-agent cluster;

[0067] S104, using an ant colony algorithm, determining the movement speed and direction of the worker bee multi-agent in the multi-agent cluster according to the multi-agent information of the reconnaissance peak, the destination and the pre-set formation rules; the pre-set formation rules at least include aggregation rules, alignment rules, collision avoidance rules, random rules and following rules;

[0068] Among them: the aggregation rule is used to describe the tendency of multi-agents to form a population by assuming that a multi-agent tends to move towards the center of the multi-agents around it; the alignment rule is used to describe that the multi-agents fly at the same speed and use it as a guide for neighboring individuals; the collision avoidance rule is used for the habit of multi-agents to avoid collisions; the random rule is used to change the individual decisions of the moving multi-agents; the following rule is used for the worker bee multi-agent to continuously follow the movement of the scout bee.

[0069] S105. Control the multi-agent cluster to reach the destination based on the multi-agent information of the reconnaissance peak and the movement speed and direction of the worker bee multi-agent.

[0070] Another embodiment of the present application further supplements the multi-agent formation method based on the bee swarm algorithm provided in the above embodiment.

[0071] The organized movement of a swarm towards a target is a complex phenomenon, since only a small number of scout bees know which direction to move, while in most cases, the majority of worker bees do not know the specific location of the target; the worker bee swarm needs to follow the scout bee cluster to fly to the target location. A swarm movement model is proposed, showing that when the scout bees move towards the target point through a known path, the worker bee swarm continues to follow the movement of the scout bees until they reach the destination. Therefore, the algorithm can guide the movement of the worker bee swarm through the purposeful movement of the scout bees.

[0072] Set a leader for the bee colony, that is, a scout bee. The scout bee knows the specific location of the target point in the assumption, and the path for the scout bee has been planned. The scout bee leads the follower bees to the target point.

[0073] Set up a swarm of follower bees. In this problem, the follower bees do not know the location of the target point, so the follower bee swarm needs to be guided by the scout bees to go to the target point at all times.

[0074] Design movement rules for each follower bee to assist the follower bees to move in a cluster without colliding with each other.

[0075] The basic operation steps of the bee colony algorithm can be divided into the following two parts: 1. The scout bee continuously flies to the target point. 2. The worker bee colony follows the scout bee in a certain flying mode. The overall flow chart is as follows: Figure 2 as shown.

[0076] Optionally, the clustering rule is used to make the worker bee multi-agents move in a clustered manner, and the flight angle of a single worker bee multi-agent is calculated so that it does not break away from the cluster, defining d max As a warning sign that a single worker bee multi-agent is about to leave the worker bee multi-agent cluster, when the distance between any two worker bees is greater than d max When the aggregation rule is triggered;

[0077] The collision avoidance rule is used to keep a safe distance between multiple agents in the worker bee swarm to avoid collisions with each other. min As the alarm distance between worker bee swarm multi-agents, when the distance between any two worker bee multi-agents is less than d min When , the collision avoidance rule is triggered;

[0078] The random rule is used to add a random component to the movement of each worker bee multi-agent in the worker bee swarm multi-agent to prevent deadlock and increase exploration;

[0079] The following rule is used for each individual in the worker bee colony multi-agent to follow the scout bee multi-agent to reach the target point.

[0080] Specifically, the scout bee, as the leader of the bee colony algorithm, is represented by leader. Assuming that the flight path and target point of the scout bee are given, the scout bee moves toward the target point along the given trajectory. The worker bee, as the main body of the bee colony algorithm, has the basic task of following the scout bee to the target point, and is affected by the following five movement rules during the process.

[0081] For individual i, use p i To represent the position of an individual, including x, y, and z coordinates. Use v i To express the speed of an individual, the speed includes the magnitude and direction of the speed.

[0082] (1) Aggregation rule: describes the tendency of bees to form a colony by assuming that a bee tends to move toward the center of the individuals around it.

[0083] (2) Alignment rule: describes that bees fly at the same speed and use it as a guide for neighboring individuals.

[0084] (3) Collision avoidance rule: bees’ habit of avoiding collisions.

[0085] (4) Random rules: Individual decisions of bees that change their movements.

[0086] (5) Following rule: Worker bees constantly follow the movements of scout bees.

[0087] like Figure 3 As shown, the behavior of each individual worker bee is influenced by these five movement rules.

[0088] According to Figure 3 As can be seen from the flow chart, each time the follower bee moves, the five rules need to be calculated separately, and finally the movement speed and direction of the follower bee are obtained.

[0089] Clustering rule: Make the worker bees move in a cluster, and calculate the flight angle of a single worker bee so that it will not break away from the cluster. max As a warning sign that a single worker bee is about to leave the worker bee colony, when the distance between any two worker bees is greater than d max The aggregation rule is triggered when . The specific formula is shown in Formula 1.

[0090]

[0091] Alignment rule: describes the tendency of worker bees to fly at the same speed and use it as a guide for neighboring individuals.

[0092] The specific formula is shown in Formula 2.

[0093]

[0094] Collision avoidance rules: The purpose is to keep worker bee clusters at a safe distance to avoid collisions. min As the alarm distance between worker bee colonies, when the distance between any two worker bees is less than d min When , the collision avoidance rule is triggered. The specific formula is shown in Formula 3.

[0095]

[0096] Random rule: refers to adding random components to the movement of each worker bee in the worker bee cluster to prevent deadlock and increase exploration. The specific formula is shown in Formula 4.

[0097] v random = rand(v θ ) (Formula 4)

[0098] Following rule: Each individual in the worker bee colony needs to follow the movement of the scout bee to reach the target point. The following rule is to know the movement of the worker bee colony based on the movement of the scout bee. The specific formula is shown in Formula 5.

[0099] v follow =p target -p (Formula 5)

[0100] According to the above five movement rules, the corresponding movement factors of individual worker bees are calculated at each moment. The weights of different movement factors are different in different situations. After weighting by the weight coefficient, the movement mode of individual worker bees can be obtained. The specific formula is shown in Formula 6.

[0101] v new =w cohere .v cohere +w avoid .v avold +w align .v align +w random .v random +

[0102] w follow .v follow (Formula 6)

[0103] Since the stability of each worker bee's movement needs to be guaranteed, a soft update method is used to update its speed. The specific formula is shown in Formula 7.

[0104] v(t+1)=w·v(t)+v new (Formula 7)

[0105] In actual problems, there may be situations where scout bees are attacked during flight, and it is necessary to consider the situation where worker bees lose their targets during flight. Therefore, it is assumed that when a scout bee is destroyed, the worker bee closest to the scout bee is selected as the new scout bee, and the destination location is known.

[0106] Among them, Formula 1 aggregation factor calculation formula

[0107] Formula 2 Alignment factor calculation formula

[0108] Formula 3 Collision avoidance factor calculation formula

[0109] Formula 4 Random factor calculation formula

[0110] Formula 5: Follow-up factor calculation formula

[0111] Formula 6: Calculation formula for individual movement patterns of worker bees

[0112] Formula 7 Speed ​​update calculation formula;

[0113] The meaning of the letters in the formula:

[0114] Indicates the clustering factor v_cohere

[0115] Indicates the distance d_"max" that is about to leave the cluster

[0116] represents the coordinates p of the worker bee individual

[0117] Indicates the alignment factor v_align

[0118] Represents the collision avoidance factor v_avoid

[0119] Represents the number of worker bees in the colony N

[0120] Indicates the minimum allowable distance between worker bees d_"min"

[0121] represents the set of worker bees whose distance is less than the minimum allowed distance N_"min"

[0122] Indicates the position of the scout bee p_target

[0123] Indicates the follow factor v_follow

[0124] Represents the weights of the five motion factors w_cohere, w_avoid, w_align, w_random, w_follow

[0125] Indicates the speed v_new after the motion factor is updated

[0126] Indicates the speed v_new after the motion factor is updated

[0127] Specifically, Figure 4 The logic flow chart of the bee colony algorithm shown is: using the ant colony algorithm, according to the multi-agent information of the scout peak, the destination and the pre-set formation rules, the movement speed and movement direction of the worker bee multi-agent in the multi-agent cluster are determined, including:

[0128] According to the pre-set formation rules, the movement factors of the worker bee multi-agents at each moment are determined;

[0129] According to the movement factors and corresponding weights of the worker bee multi-agent, the movement speed and direction of each worker bee multi-agent are calculated.

[0130] like Figure 5 As shown, the present invention is further described below in conjunction with the figures and specific implementation methods.

[0131] The present invention is based on the bee colony algorithm to construct a formation method for multiple intelligent agents. In view of the shortcomings of the current control strategy-based solution to the group coordination problem, inspired by the biological cluster behavior, the bee colony algorithm (Bee Algorithm) is proposed. The bee colony algorithm is a type of heuristic optimization algorithm based on simulating the social behavior of bees, which is usually used to solve various optimization problems. In the bee colony algorithm, artificial bees act as searchers, randomly search for targets in the search space, and continuously transmit and communicate information in order to jointly discover the global optimal solution.

[0132] (1) Behavioral Model

[0133] Learning behavior: The bee colony does not know the location of the destination initially. Only the scout bees find the location of the destination through continuous exploration. The follower bees in the bee colony continue to follow the scout bees, learn the movement path of the scout bees, and the exploratory nature of the follower bees in the process of movement gradually decreases.

[0134] Perception behavior: Bees obtain information by perceiving their surroundings. They can sense the distance, direction, and other information of scout bees and other follower bees. Bees will choose the next direction of movement based on this information and try to move toward better coordinate points. The accuracy and sensitivity of perception have an important impact on the effectiveness of the algorithm.

[0135] Decision-making behavior: Bees make decisions based on the current environment information, the information of scout bees, and the information of other follower bees. The decision includes whether to perform alignment, collision avoidance, aggregation, following, etc., and ultimately determines the direction and speed of movement.

[0136] Reasoning behavior: Since the bee colony may collide or leave the cluster, the follower bee needs to judge whether its location is about to collide or leave the cluster based on the existing information, and then perform corresponding actions based on the inferred results.

[0137] (2) Class Construction

[0138] There are several classes in the bee colony algorithm modeling process: The bee colony algorithm modeling process includes at least multiple classes, including at least: Main class, Leader class, Leader class, UAV class, Enemy class and ABC class, among which the Main class is used to generate objects of the Leader class. The Leader class is a reconnaissance peak multi-agent, the object of the UAV class is a follower drone, and the Leader class is used to generate a reconnaissance peak multi-agent through the add_Leader method.

[0139] In other words, the Main class: as the core of the entire swarm algorithm, can generate objects of the Leader class, i.e., reconnaissance drones, objects of the UAV class, i.e., follower drones, and objects of the Enemy class in the Main class. The start method is used to generate a group of follower drones in a specified area, and the target point is not set for the reconnaissance drone. The ABC class is called through the run method to control the cluster flight mode of the follower drones.

[0140] Leader class: represents the reconnaissance drone class. The reconnaissance drone is generated through the add_Leader method. The reconnaissance drone has three-dimensional coordinate attributes and speed attributes. The moveTo method is used to move to the target point. If it is attacked and destroyed during flight, the delete method is used to delete the reconnaissance drone.

[0141] UAV class: represents the follower drone class. Follower drones are generated through the add_UAV method. Follower drones have three-dimensional coordinate attributes and speed attributes. Compared with the Leader class, the UAV class adds a become_leader attribute to handle the situation where the reconnaissance drone is destroyed during flight. If the reconnaissance drone is destroyed, the choose_leader method in the ABC class is used to reselect one from all follower drones as a new reconnaissance drone and guide other follower drones to fly to the target point.

[0142] Enemy class: represents the imaginary enemy, generated by the enemy_node in the Main class. Currently no actual functions are designed.

[0143] ABC (Artificial Bee Colony, ABC) class: It is the core of the bee colony algorithm. The methods in it represent choose_action to follow the drone to choose the flight action, choose_leader to select a new reconnaissance drone from the following drone group when the reconnaissance drone is destroyed, cohere_move_s to follow the drone to gather action, align_move_s to follow the drone to align action, avoid_move_s to follow the drone to avoid collision action, random_move_s to follow the drone to move randomly, follow_move_s to follow the drone to follow the reconnaissance drone movement action, and new_speed to update the speed and movement direction of the following drone after selecting a series of actions. The above class diagram is as follows Figure 5 The bee swarm algorithm class diagram is shown in the figure.

[0144] When the scout bee multi-agent is destroyed, the worker bee multi-agent closest to the scout bee multi-agent is selected as the new scout bee multi-agent, and the new scout bee multi-agent carries the destination location.

[0145] For example, Figure 6 As shown in the initial flight diagram of the drone cluster, the drone cluster was initially generated in the red area. Due to its large number, its flight pattern was in a disordered state.

[0146] like Figure 7 As shown in the figure of orderly flight of drone cluster, after the above process, due to the existence of alignment factor and collision avoidance factor, the drone cluster gradually maintains cluster flight, and each drone maintains a safe distance.

[0147] like Figure 8 As shown in the figure, when the scout bee drone turns a large angle, the worker bee swarm drone will lose its orderly state, but due to the existence of the following factor and the aggregation factor, the worker bee swarm will still follow the scout bee and will not leave the cluster.

[0148] like Fig. 9 As shown, the worker bee colony follows the scout bee to the target point.

[0149] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any manner without conflict, and this application is not limited thereto.

[0150] Another embodiment of the present application provides a multi-agent formation device based on a bee swarm algorithm, which is used to execute the multi-agent formation method based on a bee swarm algorithm provided in the above embodiment.

[0151] like Fig.10 , which is a schematic diagram of the structure of a multi-agent formation device based on a bee colony algorithm provided in an embodiment of the present application. The multi-agent formation device based on a bee colony algorithm includes an acquisition module 1001, a judgment module 1002, a first determination module 1003, a second determination module 1004 and a control module 1005, wherein:

[0152] The acquisition module 1001 is used to acquire a multi-agent cluster;

[0153] The judgment module 1002 is used to judge whether the multi-agent cluster has reached the destination;

[0154] The first determination module 1003 is used to determine the reconnaissance peak multi-agent information in the multi-agent cluster if the multi-agent cluster has not reached the destination;

[0155] The second determination module 1004 is used to use an ant colony algorithm to determine the movement speed and movement direction of the worker bee multi-agent in the multi-agent cluster according to the multi-agent information of the reconnaissance peak, the destination and the pre-set formation rules; the pre-set formation rules at least include aggregation rules, alignment rules, collision avoidance rules, random rules and following rules;

[0156] The control module 1005 is used to control the multi-agent cluster to reach the destination according to the multi-agent information of the scouting peak and the movement speed and direction of the worker bee multi-agent.

[0157] Regarding the device in this 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.

[0158] Another embodiment of the present application further supplements the multi-agent formation device based on the swarm algorithm provided in the above embodiment.

[0159] Optionally, the aggregation rule is used to describe the tendency of multi-agents to form a population by assuming that a multi-agent tends to move towards the center of the multi-agents around it; the alignment rule is used to describe that the multi-agents fly at the same speed and use it as a guide for neighboring individuals; the collision avoidance rule is used for the habit of multi-agents to avoid collisions; the random rule is used to change the individual decisions of the moving multi-agents; and the following rule is used for the worker bee multi-agents to continuously follow the movement of the scout bee.

[0160] Optionally, the clustering rule is used to make the worker bee multi-agents move in a clustered manner, and the flight angle of a single worker bee multi-agent is calculated so that it does not break away from the cluster, defining d max As a warning sign that a single worker bee multi-agent is about to leave the worker bee multi-agent cluster, when the distance between any two worker bees is greater than d max When the aggregation rule is triggered;

[0161] The collision avoidance rule is used to keep a safe distance between multiple agents in the worker bee swarm to avoid collisions with each other. min As the alarm distance between worker bee swarm multi-agents, when the distance between any two worker bee multi-agents is less than d min When , the collision avoidance rule is triggered;

[0162] The random rule is used to add a random component to the movement of each worker bee multi-agent in the worker bee swarm multi-agent to prevent deadlock and increase exploration;

[0163] The following rule is used for each individual in the worker bee colony multi-agent to follow the scout bee multi-agent to reach the target point.

[0164] Optionally, the second determining module is used to:

[0165] According to the pre-set formation rules, the movement factors of the worker bee multi-agents at each moment are determined;

[0166] According to the movement factors and corresponding weights of the worker bee multi-agent, the movement speed and direction of each worker bee multi-agent are calculated.

[0167] Optionally, the control module is used to:

[0168] When the scout bee multi-agent is destroyed, the worker bee multi-agent closest to the scout bee multi-agent is selected as the new scout bee multi-agent, and the new scout bee multi-agent carries the destination location.

[0169] Optionally, the bee colony algorithm modeling process includes at least multiple classes, and the multiple classes include at least: Main class, Leader class, Leader class, UAV class, Enemy class and ABC class, wherein the Main class is used to generate objects of the Leader class. The Leader class is a scout peak multi-agent, the object of the UAV class is a follower drone, and the Leader class is used to generate a scout peak multi-agent through the add_Leader method.

[0170] The embodiment of the present invention provides a multi-agent formation device based on a bee colony algorithm, comprising: obtaining a multi-agent cluster; determining whether the multi-agent cluster has reached a destination; if the multi-agent cluster has not reached the destination, determining the reconnaissance peak multi-agent information in the multi-agent cluster; using an ant colony algorithm to determine the movement speed and direction of worker bee multi-agents in the multi-agent cluster according to the reconnaissance peak multi-agent information, the destination and pre-set formation rules; the pre-set formation rules at least include aggregation rules, alignment rules, collision avoidance rules, random rules and following rules; according to the reconnaissance peak multi-agent information and the movement speed and direction of the worker bee multi-agents, the multi-agent cluster is controlled to reach the destination, and a multi-agent formation method is constructed based on the bee colony algorithm. In the bee colony algorithm, artificial bees act as searchers, randomly search for targets in the search space, and continuously transmit and communicate information to jointly discover the global optimal solution.

[0171] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0172] Optionally, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0173] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0174] Fig.11 800 is a block diagram of an electronic device 800 shown in the present application. For example, the electronic device 800 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.

[0175] Reference Fig.11 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0176] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0177] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, images, videos, etc. The memory 804 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.

[0178] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0179] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 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 touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0180] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0181] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0182] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0183] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast operation information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 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.

[0184] In an exemplary embodiment, the electronic device 800 may 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 to perform the above methods.

[0185] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by a processor 820 of an electronic device 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0186] Fig.1219 is a block diagram of a computer-readable storage medium 1900 shown in the present application. For example, the computer-readable storage medium 1900 may be provided as a server.

[0187] Reference Fig.12 , the computer-readable storage medium 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions, such as an application, that can be executed by the processing component 1922. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0188] The computer readable storage medium 1900 may also include a power supply component 1926 configured to perform power management of the computer readable storage medium 1900, a wired or wireless network interface 1950 configured to connect the computer readable storage medium 1900 to a network, and an input / output (I / O) interface 1958. The computer readable storage medium 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0189] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0190] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0191] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0192] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0193] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0194] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0195] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0196] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0197] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0198] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0199] The above are preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A multi-agent formation method based on bee colony algorithm, characterized in that: include: Get a multi-agent cluster; Determining whether the multi-agent cluster has reached the destination; If the multi-agent cluster has not reached the destination, determining the reconnaissance peak multi-agent information in the multi-agent cluster; Using an ant colony algorithm, according to the reconnaissance peak multi-agent information, the destination and pre-set formation rules, the movement speed and movement direction of the worker bee multi-agent in the multi-agent cluster are determined; the pre-set formation rules at least include aggregation rules, alignment rules, collision avoidance rules, random rules and following rules; According to the reconnaissance peak multi-agent information and the movement speed and direction of the worker bee multi-agent, the multi-agent cluster is controlled to reach the destination.

2. The multi-agent formation method based on bee colony algorithm according to claim 1, characterized in that: The aggregation rule is used to describe the tendency of multi-agents to form a population by assuming that a multi-agent tends to move towards the center of the multi-agents around it; the alignment rule is used to describe that the multi-agents fly at the same speed and use it as a guide for neighboring individuals; the collision avoidance rule is used for the habit of multi-agents to avoid collisions; the random rule is used to change the individual decisions of the moving multi-agents; and the following rule is used for the worker bee multi-agents to continuously follow the movement of the scout bees.

3. The multi-agent formation method based on bee colony algorithm according to claim 2 is characterized in that: The clustering rule is used to make the worker bee multi-agents move in a cluster manner, calculate the flight angle of a single worker bee multi-agent so that it will not break away from the cluster, and define d max As a warning sign that a single worker bee multi-agent is about to leave the worker bee multi-agent cluster, when the distance between any two worker bees is greater than d max When the aggregation rule is triggered; The collision avoidance rule is used to keep a safe distance between multiple agents in the worker bee colony to avoid collisions with each other. min As the alarm distance between worker bee swarm multi-agents, when the distance between any two worker bee multi-agents is less than d min When , the collision avoidance rule is triggered; The random rule is used to add a random component to the movement of each worker bee multi-agent in the worker bee swarm multi-agent to prevent deadlock and increase exploration; The following rule is used for each individual in the worker bee colony multi-agent to follow the scout bee multi-agent to reach the target point.

4. The multi-agent formation method based on bee colony algorithm according to claim 3 is characterized in that: The method of using an ant colony algorithm to determine the movement speed and movement direction of the worker bee multi-agent in the multi-agent cluster according to the reconnaissance peak multi-agent information, the destination and the pre-set formation rules includes: Determine the motion factor of the worker bee multi-agent at each moment according to the pre-set formation rules; According to the movement factors and corresponding weights of the worker bee multi-agents, the movement speed and movement direction of each worker bee multi-agent are calculated.

5. The multi-agent formation method based on bee colony algorithm according to claim 1, characterized in that: The method further comprises: When the scout bee multi-agent is destroyed, the worker bee multi-agent closest to the scout bee multi-agent is selected as a new scout bee multi-agent, and the new scout bee multi-agent carries the destination location.

6. The multi-agent formation method based on bee colony algorithm according to claim 5, characterized in that: The bee colony algorithm modeling process includes at least multiple classes, including at least: Main class, Leader class, Leader class, UAV class, Enemy class and ABC class, wherein the Main class is used to generate objects of the Leader class. The Leader class is a scout peak multi-agent, the object of the UAV class is a follower drone, and the Leader class is used to generate a scout peak multi-agent through the add_Leader method.

7. A multi-agent formation device based on a bee colony algorithm, characterized in that: include: Acquisition module, used to obtain multi-agent clusters; A judgment module, used to judge whether the multi-agent cluster has reached the destination; A first determination module, configured to determine the reconnaissance peak multi-agent information in the multi-agent cluster if the multi-agent cluster has not reached the destination; A second determination module is used to determine the movement speed and movement direction of the worker bee multi-agent in the multi-agent cluster by using an ant colony algorithm according to the reconnaissance peak multi-agent information, the destination and a pre-set formation rule; the pre-set formation rule at least includes a gathering rule, an alignment rule, a collision avoidance rule, a random rule and a following rule; A control module is used to control the multi-agent cluster to reach the destination according to the multi-agent information of the scouting peak and the movement speed and direction of the worker bee multi-agent.

8. The multi-agent formation device based on bee colony algorithm according to claim 7, characterized in that: The aggregation rule is used to describe the tendency of multi-agents to form a population by assuming that a multi-agent tends to move towards the center of the multi-agents around it; the alignment rule is used to describe that the multi-agents fly at the same speed and use it as a guide for neighboring individuals; the collision avoidance rule is used for the habit of multi-agents to avoid collisions; the random rule is used to change the individual decisions of the moving multi-agents; and the following rule is used for the worker bee multi-agents to continuously follow the movement of the scout bees.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method according to any one of claims 1 to 6 when executed by the processor.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images