Unmanned cluster system intelligence level comprehensive evaluation method and system based on group entropy, and medium

Abstract

The invention discloses an unmanned cluster system intelligence level comprehensive evaluation method and system based on group entropy and a medium, and relates to the field of system evaluation, and the method comprises the steps: obtaining communication data and behavior data of a target unmanned cluster system in different task scenes; the target unmanned cluster system is composed of a plurality of intelligent agents; constructing a group entropy evaluation model based on the communication data and the behavior data, and calculating to obtain the group entropy of the target unmanned cluster system; the group entropy is a weighted combination of the normalized structure entropy and the normalized behavior entropy; delimiting an intelligent level grade of the target unmanned cluster system based on an interval range corresponding to the group entropy; and the intelligent level grade is used as an evaluation feedback index and is used for guiding topological structure optimization and cooperative behavior strategy adjustment of the target unmanned cluster system. According to the invention, comprehensive evaluation of the intelligent level of the unmanned cluster system is realized from a multi-dimensional angle, and the accuracy of intelligent level evaluation is improved.

Description

Technical Field

[0001] The present application relates to the technical field of system evaluation, and particularly to a comprehensive evaluation method, system and medium for the intelligence level of an unmanned cluster system based on group entropy. Background Art

[0002] With the wide application of unmanned cluster systems in the national defense and civilian fields, the need to evaluate their intelligence level has become increasingly important. However, existing intelligence level evaluation methods are mostly limited to a specific dimension, such as communication connectivity or task execution efficiency, and it is difficult to comprehensively reflect the overall intelligence performance of unmanned cluster systems in complex task environments.

[0003] Unmanned cluster systems not only depend on the capabilities of individual nodes, but also on the effectiveness of collaborative work and communication structures within the cluster. Therefore, the evaluation of their intelligence performance requires a more comprehensive and systematic approach. Traditional evaluation methods are difficult to handle the multi-dimensional intelligence performance of unmanned cluster systems in dynamic environments, especially in the face of complex situations such as node failures, communication interruptions, interference or task changes, and often cannot accurately evaluate the overall intelligence level of unmanned cluster systems. It is precisely for the above reasons that the current evaluation of the intelligence level of unmanned cluster systems is not accurate. Summary of the Invention

[0004] The purpose of the present application is to provide a comprehensive evaluation method, system and medium for the intelligence level of an unmanned cluster system based on group entropy, which realizes the comprehensive evaluation of the intelligence level of an unmanned cluster system from multiple dimensions and improves the accuracy of its intelligence level evaluation.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In a first aspect, the present application provides a comprehensive evaluation method for the intelligence level of an unmanned cluster system based on group entropy. The comprehensive evaluation method for the intelligence level of an unmanned cluster system based on group entropy includes:

[0007] Obtain the communication data and behavior data of a target unmanned cluster system in different task scenarios; the target unmanned cluster system is composed of multiple agents; the communication data at least includes: the shortest directed path length between any two agents and the total length of all directed paths in the target unmanned cluster system; the behavior data at least includes: the number of agents taking specific behaviors within the neighborhood of each agent and the number of agents included in the neighborhood of each agent;

[0008] Construct a group entropy evaluation model based on the communication data and the behavior data, and calculate the group entropy of the target unmanned cluster system; the communication data is used to determine the structural entropy of the target unmanned cluster system; the behavior data is used to determine the behavior entropy of the target unmanned cluster system; the group entropy is a weighted combination of the normalized structural entropy and the normalized behavior entropy;

[0009] Define the intelligent level grade of the target unmanned cluster system based on the interval range corresponding to the group entropy; the intelligent level grade is used as an evaluation feedback index to guide the optimization of the topological structure and the adjustment of the collaborative behavior strategy of the target unmanned cluster system.

[0010] In a second aspect, the present application also provides a computer system, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for comprehensively evaluating the intelligent level of an unmanned cluster system based on group entropy in the first aspect.

[0011] In a third aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, and characterized in that when the computer program is executed by a processor, it implements the method for comprehensively evaluating the intelligent level of an unmanned cluster system based on group entropy in the first aspect.

[0012] According to the specific embodiments provided by the present application, the following technical effects are disclosed by the present application:

[0013] The present application collects the communication data and behavior data of the target unmanned cluster system in different task scenarios, constructs a group entropy evaluation model, and quantifies these data into two parts, namely structural entropy and behavior entropy, which respectively reflect the communication efficiency and individual collaboration ability of the unmanned cluster system. Then, the normalized structural entropy and behavior entropy are weighted and combined to obtain the group entropy of the unmanned cluster system, which is used as the core evaluation index of the intelligent level. Finally, according to the interval range corresponding to the group entropy, the intelligent level grade of the unmanned cluster system is defined, and different intelligent level grades correspond to different intelligent performance capabilities. Therefore, the present application provides a more comprehensive and accurate intelligent evaluation method for unmanned cluster systems in complex task environments. Description of the Drawings

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0015] Figure 1The evaluation framework diagram of the group entropy provided by the embodiments of the present application;

[0016] Figure 2 The flowchart of the comprehensive evaluation method for the intelligence level of the unmanned cluster system based on group entropy provided by the embodiments of the present application;

[0017] Figure 3 The specific calculation interface diagram of the group entropy provided by the embodiments of the present application;

[0018] Figure 4 The evaluation result interface diagram of the group entropy provided by the embodiments of the present application;

[0019] Figure 5 The internal structure diagram of the computer system provided by the embodiments of the present application. Detailed implementation manners

[0020] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0021] The purpose of the present application is to provide a comprehensive evaluation method, system and medium for the intelligence level of an unmanned cluster system based on group entropy, which realizes the comprehensive evaluation of the intelligence level of the unmanned cluster system from multiple dimensions and improves the accuracy of its intelligence level evaluation.

[0022] The present application quantifies and analyzes the intelligence of the unmanned cluster system from two dimensions of structural entropy and behavioral entropy by constructing a group entropy evaluation model. The intelligent performance of the unmanned cluster system not only depends on individual behaviors, but also is restricted by the overall communication structure, task collaboration and its adaptability to the external environment. As Figure 1 shown, the present application comprehensively considers the performance of the unmanned cluster system in different task environments by analyzing the comprehensive effects of individual behaviors and collective collaborations within the unmanned cluster system. By quantitatively evaluating the communication topology, organizational structure and behavior patterns, and combining the actual collected data during task execution, the scores of structural entropy and behavioral entropy are calculated, and then the overall intelligence evaluation of the unmanned cluster system is generated.

[0023] The concept of group entropy is introduced to further deeply analyze and quantify the intelligent behavior evolution pattern of the unmanned cluster system. As an entropy-like metric for measuring the emergence of cluster intelligence, group entropy can macroscopically reflect the orderliness and complexity of cluster behavior and provide a basis for statistical analysis of the overall intelligence of the unmanned cluster system. By evaluating the collaborative behavior, information transfer efficiency, and behavior complexity among individuals within the unmanned cluster system, group entropy helps to reveal the intelligence level of the unmanned cluster system in task execution. The evaluation system of group entropy includes two levels: structural entropy and behavioral entropy:

[0024] Structural entropy is used to measure the communication architecture and information transfer efficiency of the unmanned cluster system and is closely related to the cluster communication ability. A higher structural entropy indicates more efficient communication among nodes in the system and smooth information transfer; while a lower structural entropy indicates that the communication within the system may be blocked or less efficient. By analyzing the communication timeliness, path length, and information transfer efficiency among nodes, structural entropy can quantify the overall communication network performance of the unmanned cluster system.

[0025] Behavioral entropy is used to measure the interaction behavior and intelligent emergence pattern among individuals in the unmanned cluster system, especially in aspects such as joint perception, anti-interference, anti-damage, and action control capabilities. The level of behavioral entropy reflects the adaptive ability, behavior diversity, and coordination among individuals in the unmanned cluster system during task execution. For example, in a joint perception task, behavioral entropy can quantify the fusion degree of the detection behavior of each node and the perceived data, and further evaluate the response ability of the entire unmanned cluster system to the environmental situation. In the evaluation of anti-interference and anti-damage capabilities, behavioral entropy demonstrates the intelligent performance of the unmanned cluster system in dealing with external interference and node failures by measuring the robustness and self-healing ability of individual behaviors. Behavioral entropy also reflects the autonomy in decision-making control and the collaborative efficiency in task execution of the unmanned cluster system, and evaluates its overall action control ability.

[0026] To make the above objects, features, and advantages of the present application more obvious and understandable, the following further details the present application in conjunction with the accompanying drawings and specific embodiments.

[0027] As Figure 2 shown, this embodiment provides a comprehensive evaluation method for the intelligent level of an unmanned cluster system based on group entropy. The comprehensive evaluation method for the intelligent level of the unmanned cluster system based on group entropy includes:

[0028] Step S1: Obtain the communication data and behavior data of the target unmanned cluster system in different task scenarios.

[0029] In this embodiment, the target unmanned cluster system consists of multiple agents; the communication data at least includes: the shortest directed path length between any two agents and the total sum of all directed path lengths in the target unmanned cluster system; the behavior data at least includes: the number of agents taking specific behaviors within the neighborhood of each agent and the number of agents included in the neighborhood of each agent. In addition, the above communication data and behavior data also include the total number of agents in the target unmanned cluster system.

[0030] Step S2: Based on the communication data and behavior data, construct a group entropy evaluation model, and calculate the group entropy of the target unmanned cluster system.

[0031] In this embodiment, the communication data is used to determine the structural entropy of the target unmanned cluster system; the behavior data is used to determine the behavior entropy of the target unmanned cluster system; the group entropy is a weighted combination of the normalized structural entropy and the normalized behavior entropy. The formula for calculating the group entropy in the above group entropy evaluation model is:

[0032] GE = α1STE * +α2GBE * ;

[0033] In the formula, GE is the group entropy, STE * is the normalized structural entropy, GBE * is the normalized behavior entropy, and α1 and α2 are the proportion weights of the structural entropy and the behavior entropy in different task scenarios, ensuring that α1 + α2 = 1.

[0034] Among them, the determination of the normalized structural entropy includes:

[0035] The first step is to determine the initial structural entropy based on the total number of agents in the target unmanned cluster system, the total sum of all directed path lengths in the target unmanned cluster system, and the shortest directed path length between any two agents, that is:

[0036]

[0037] In the formula, STE is the initial structural entropy, N is the total number of agents (also known as nodes) in the target unmanned cluster system, P ij is the information transfer time efficiency probability between agent (node) i and agent (node) j, d ij is the shortest directed path length between agent (node) i and agent (node) j, and D is the total sum of all directed path lengths in the target unmanned cluster system.

[0038] The second step is to determine the maximum structural entropy based on the total sum of all directed path lengths in the target unmanned cluster system, that is:

[0039] m_STE = log2(D);

[0040] In the formula, m_STE is the maximum structural entropy.

[0041] In the third step, based on the initial structural entropy and the maximum structural entropy, the normalized structural entropy is obtained, that is:

[0042]

[0043] The determination process of the normalized behavior entropy includes:

[0044] In the first step, based on the number of agents taking specific behaviors within the neighborhood of each agent in the target unmanned cluster system, and the number of agents included in the neighborhood of each agent, the behavior entropy of each agent is determined, that is:

[0045]

[0046] In the formula, GBE i is the behavior entropy of agent i, n b is the number of behaviors, p i,k is the probability that agent i takes behavior b k , m k is the number of agents taking behavior b k in the neighborhood of agent i, m i is the number of agents included in the neighborhood of agent i. Among them, the behavior set of the target unmanned cluster system b k is the k-th behavior b in the behavior set b k , and the neighborhood of agent i is defined as the set composed of all other agents that can directly perform data interaction with agent i within the preset communication range. This communication range is determined by the communication radius threshold of agent i and is used to characterize the local interaction environment of agent i.

[0047] In the second step, based on the total number of agents in the target unmanned cluster system and the behavior entropy of all agents, the behavior entropy of the target unmanned cluster system is determined, that is:

[0048]

[0049] In the formula, GBE is the behavior entropy of the target unmanned cluster system, w i is the weight of agent i.

[0050] In the third step, based on the behavior entropy of the target unmanned cluster system and the maximum behavior entropy of the agent, the normalized behavior entropy is obtained, that is:

[0051]

[0052] In the formula, is the set of agents in the target unmanned cluster system.

[0053] Step S3: Based on the interval range corresponding to the group entropy, delimit the intelligence level grades of the target unmanned cluster system.

[0054] In this embodiment, according to the result of normalizing the group entropy, a group entropy score interval of [0, 1] is obtained. Based on the group entropy score, the intelligence level of the unmanned cluster system is divided into 9 grades, and the corresponding grade names and grade descriptions are given for each grade. See Table 1 for details:

[0055] Table 1 Division system of intelligence level evaluation grades for unmanned cluster systems

[0056]

[0057]

[0058] To verify the effectiveness of the above comprehensive evaluation method for the intelligence level of the unmanned cluster system based on group entropy, the following numerical simulation experiments were carried out. The numerical simulation experiments quantified and evaluated the performance of the unmanned cluster system in two dimensions of structural entropy and behavioral entropy by simulating complex task scenarios. Through detailed analysis of the communication topology and inter-individual collaborative behavior of the unmanned cluster system, the quantification results of structural entropy and behavioral entropy were obtained and normalized. The experimental results show that this evaluation method can effectively reflect the intelligent performance of the unmanned cluster system in different task environments, verify its rationality and accuracy in the division of intelligence level grades, and provide effective support for the intelligent optimization design of the unmanned cluster system.

[0059] As Figure 3 shown, this figure shows the various calculation indicators and frequencies related to structural entropy and behavioral entropy, which evaluate the detailed performance of the unmanned cluster system in two dimensions of structural entropy and behavioral entropy. In terms of structural entropy, the communication topology and organizational structure inside the unmanned cluster system are evaluated in detail, and the communication efficiency and orderliness inside the unmanned cluster system are quantified through parameters such as path length and path number; in the part of behavioral entropy, multiple indicators such as the diversity of individual behaviors and the coordination of group behaviors in the unmanned cluster system are evaluated. The specific evaluation data include: the number of situation awareness times, the number of target recognition times, the number of cluster coordination times, etc., fully demonstrating the intelligent performance of the unmanned cluster system during the task execution process.

[0060] As Figure 4As shown, the figure shows the normalized values of structural entropy and behavioral entropy and their proportions in the total entropy, and reflects the results of the intelligent level division of the system through a pie chart. The normalized scores of structural entropy and behavioral entropy in the figure are 0.25997 and 0.55201 respectively, indicating that the unmanned cluster system performs outstandingly in individual behavior cooperation and group task execution. The total group entropy score is 0.43519, and the intelligent level is classified as L3, which means that the unmanned cluster system has basic intelligent cooperation capabilities and basic task execution efficiency. Figure 4 The pie chart in

[0061] shows the proportion of structural entropy and behavioral entropy, further proving that the proportion of behavioral entropy is larger in this evaluation, reflecting the adaptability and cooperation of the unmanned cluster system in task execution.

[0062] In another exemplary embodiment, a computer system is provided. The computer system can be a server or a terminal, and its internal structure diagram can be as Figure 5 shown. The computer system includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer system is used to provide computing and control capabilities. The memory of the computer system includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer system is used to store the communication data and behavioral data of the target unmanned cluster system in different task scenarios. The input / output interface of the computer system is used to exchange information between the processor and external devices. The communication interface of the computer system is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements the above-mentioned comprehensive evaluation method for the intelligent level of the unmanned cluster system based on group entropy.

[0063] Those skilled in the art can understand that Figure 5 the structure shown in

[0064] In another exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which when executed by a processor implements the steps in the above method embodiments.

[0065] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0066] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random-access memory (ReRAM), magnetoresistive random-access memory (MRAM), ferroelectric random-access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0067] The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0068] All actions of obtaining signals, information or data in this application are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where it is located and with the authorization given by the owner of the corresponding device.

[0069] Based on the above analysis, this application mainly has the following effects:

[0070] (1) By introducing structural entropy and behavioral entropy, the overall intelligence level of the unmanned cluster system is systematically evaluated from a dual dimension. Especially in a complex task environment, a comprehensive analysis of the communication architecture and individual behavior coordination ability of the unmanned cluster system is carried out to ensure that the evaluation results are more accurate and comprehensive.

[0071] (2) System performance data is generated through simulation data and actual operation data, and quantitative analysis is carried out in combination with the group entropy theory, which significantly improves the accuracy and scientific nature of the evaluation, and ensures the objectivity and reliability of the results. The evaluation data is based on the actual operation situation and task performance of the unmanned cluster system, and can truly reflect its intelligence level.

[0072] (3) Based on the classification of the intelligence level by group entropy, the intelligence level of the unmanned cluster system can be divided into multiple levels according to the performance of the unmanned cluster system in terms of structural entropy and behavioral entropy. This classification of the intelligence level provides a clear reference basis for the system optimization design and intelligent improvement, helping designers identify the deficiencies of the system, thereby improving the task execution efficiency and cooperative combat ability.

[0073] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other.

[0074] Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. An intelligent level comprehensive evaluation method for an unmanned cluster system based on group entropy, characterized in that The comprehensive evaluation method for the intelligence level of an unmanned cluster system based on group entropy includes: Obtain the communication data and behavior data of the target unmanned cluster system in different task scenarios; the target unmanned cluster system consists of multiple agents; the communication data at least includes: the shortest directed path length between any two agents and the sum of all directed path lengths in the target unmanned cluster system; the behavior data at least includes: the number of agents taking specific behaviors within the neighborhood of each agent and the number of agents included in the neighborhood of each agent; Construct a group entropy evaluation model based on the communication data and the behavior data, and calculate the group entropy of the target unmanned cluster system; the communication data is used to determine the structural entropy of the target unmanned cluster system; the behavior data is used to determine the behavior entropy of the target unmanned cluster system; the group entropy is a weighted combination of the normalized structural entropy and the normalized behavior entropy; Based on the interval range corresponding to the group entropy, delimit the intelligence level grade of the target unmanned cluster system; the intelligence level grade is used as an evaluation feedback index to guide the optimization of the topological structure and the adjustment of the cooperative behavior strategy of the target unmanned cluster system.

2. The intelligent level comprehensive evaluation method for the unmanned cluster system based on group entropy according to claim 1, wherein The formula for calculating the group entropy in the group entropy evaluation model is: GE = α1STE * + α2GBE * ; where GE is the group entropy, and STE * is the normalized structural entropy, and GBE * is the normalized behavior entropy. α1 and α2 are the proportion weights of the structural entropy and the behavior entropy in different task scenarios respectively, and α1 + α2 = 1.

3. The comprehensive evaluation method for the intelligence level of an unmanned cluster system based on group entropy according to claim 2, characterized in that, The determination of the normalized structural entropy includes: Based on the total number of agents in the target unmanned cluster system, the sum of all directed path lengths in the target unmanned cluster system, and the shortest directed path length between any two agents, determine the initial structural entropy; Based on the sum of all directed path lengths in the target unmanned cluster system, determine the maximum structural entropy; Based on the initial structural entropy and the maximum structural entropy, obtain the normalized structural entropy.

4. The intelligent level comprehensive evaluation method for the unmanned cluster system based on group entropy according to claim 2, wherein The determination process of the normalized behavior entropy includes: Based on the number of agents taking specific behaviors within the neighborhood of each agent in the target unmanned cluster system and the number of agents included in the neighborhood of each agent, determine the behavior entropy of each agent; Based on the total number of agents in the target unmanned cluster system and the behavior entropy of all agents, determine the behavior entropy of the target unmanned cluster system; Based on the behavior entropy of the target unmanned cluster system and the maximum behavior entropy of the agents, obtain the normalized behavior entropy.

5. The intelligent level comprehensive evaluation method for the unmanned cluster system based on group entropy according to claim 3, characterized in that The calculation formula for the initial structural entropy is: P ij = d ij / D; The calculation formula for the maximum structural entropy is: m_STE = log2(D); The calculation formula for the normalized structural entropy is: Among them, STE is the initial structural entropy, N is the total number of agents in the target unmanned cluster system, and P ij is the information transfer time efficiency probability between agent i and agent j, and d ij is the shortest directed path length between agent i and agent j, D is the sum of all directed path lengths in the target unmanned cluster system, and m_STE is the maximum structural entropy.

6. The intelligent level comprehensive evaluation method for an unmanned cluster system based on group entropy according to claim 4, characterized in that The calculation formula for the behavior entropy of each agent is: The calculation formula for the behavior entropy of the target unmanned cluster system is: The calculation formula for the normalized behavior entropy is: Among them, GBE i is the behavior entropy of agent i, n b is the number of behaviors, p i,k is the probability of taking behavior b k in the neighborhood of agent i, m k is the number of agents taking behavior b k in the neighborhood of agent i, m i is the number of agents included in the neighborhood of agent i, GBE is the behavior entropy of the target unmanned cluster system, N is the total number of agents in the target unmanned cluster system, w i is the weight of agent i, GBE * is the normalized behavior entropy, is the set of agents in the target unmanned cluster system.

7. The intelligent level comprehensive evaluation method for the unmanned cluster system based on group entropy according to claim 6, wherein The neighborhood of the agent i is defined as the set composed of all other agents that can directly perform data interaction with the agent i within the preset communication range.

8. The comprehensive evaluation method for the intelligence level of an unmanned cluster system based on group entropy according to claim 1, characterized in that, The intelligence level grades are divided into 9 types, namely manual control, simple autonomy, cooperative cooperation, autonomous networking, perception and decision-making, intelligent planning, cooperative decision-making, self-learning, and comprehensive autonomy.

9. A computer system, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the comprehensive evaluation method for the intelligence level of an unmanned cluster system based on population entropy according to any one of claims 1-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the comprehensive evaluation method for the intelligence level of an unmanned cluster system based on population entropy according to any one of claims 1-8.

Images