Method for underwater unmanned swarm intelligence evaluation grading and related device

Abstract

The application belongs to the technical field of underwater unmanned cluster evaluation grading, and discloses a method for underwater unmanned cluster intelligence evaluation grading and related devices; wherein the method for underwater unmanned cluster intelligence evaluation grading comprises the following steps: based on the function type of the underwater unmanned cluster to be evaluated and graded, determining the evaluation task type and obtaining the environmental parameter statistics, task parameter statistics and technical feature statistics; based on the standard scores of the obtained environmental difficulty index and the standard scores of the task effect index, calculating the obtained external weight; multiplying the obtained external weight with the technical feature original score to obtain the improved technical feature score; based on the obtained improved technical feature score, performing evaluation grading to obtain the underwater unmanned cluster intelligence evaluation grading result. The technical scheme disclosed by the application can solve the problems of subjective evaluation, generalization application, fuzzy definition and solidification classification existing in the prior art.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of underwater unmanned cluster evaluation and grading, and particularly relates to a method for evaluating and grading the intelligence of an underwater unmanned cluster and a related device. BACKGROUND

[0002] At present, the existing unmanned system grading methods mostly give grading descriptions based on the autonomy or automation degree of various unmanned systems; among them, expert subjective scoring is the main grading basis, and mostly gives language descriptions of grading standards for unmanned aerial vehicles or unmanned vehicles, and there are few evaluation and grading methods directly applied to underwater unmanned clusters.

[0003] Specifically, the US Department of Defense (DoD) defines autonomy levels based on the relationship between humans and machines (US Department of Defense Autonomy Levels), focusing on the role of humans in command and control during operation; this framework includes four levels: human operation (Human Operated), human delegation (Human Delegated), human supervision (Human Supervised), and full autonomy (Fully Autonomous). This framework focuses on the interaction between humans and systems and is suitable for evaluating command and control relationships in military operations, especially in multi-system collaboration or tasks that require close human-machine collaboration. The PACT (Pilot Authorisation and Control of Tasks) framework was developed by the UK Ministry of Defense and defines an automation level balance between human and machine decision-making, containing ten levels. The advantage of PACT is that it provides a detailed, gradual level from human dominance to full automation, suitable for analyzing the application of decision automation degree in actual tasks. NATO Standardization Agreement (STANAG) 4586 focuses on the interoperability of unmanned aerial vehicle systems and defines five levels of interoperability (LOI), each describing different levels of control and data sharing. The ALFUS (Autonomy Levels for Unmanned Systems) framework developed by the US National Institute of Standards and Technology (NIST) is more comprehensive, providing a quantitative method to evaluate the autonomy level of unmanned systems, considering three dimensions, each graded from 0 to 10, and calculating the average to obtain a comprehensive autonomy level. This three-dimensional quantitative method allows ALFUS to provide detailed autonomy evaluation, which helps to compare and evaluate the performance of unmanned systems in different tasks and environments.

[0004] In summary, the existing unmanned system grading schemes have the following deficiencies:

[0005] 1) Subjective evaluation: all are subjective scoring evaluation, and do not correspond to objective performance indicators;

[0006] 2) General application: the description is too broad, and lacks detailed task description of a certain type of cluster, and the professionalism is insufficient;

[0007] 3) Fuzzy definition: no standardized test method is provided, only a fuzzy language description;

[0008] 4) Solidification classification: except for ALFUS, there is no consideration of environmental change information, and the adaptability to different environments is lacking;

[0009] Therefore, a new scheme for underwater unmanned cluster intelligence evaluation grading is urgently needed. SUMMARY

[0010] The present application aims to provide a method for underwater unmanned cluster intelligence evaluation grading and related devices to solve one or more of the above technical problems. The technical solution disclosed in the present application solves the technical problems of subjective evaluation, general application, fuzzy definition and solidification classification existing in the prior art. The present application technical solution is specifically for underwater unmanned clusters, and covers environmental difficulty indicators and task performance indicators as external weights, so that the evaluation grading method of the present application can adapt to different task test scenarios. Objective performance indicators are introduced to indicate different technical features of environmental difficulty, task performance and intelligence.

[0011] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0012] In a first aspect of the present application, a method for underwater unmanned cluster intelligence evaluation grading is provided, comprising the following steps:

[0013] Based on the functional type of the underwater unmanned cluster to be intelligently evaluated and graded, the evaluation task type is determined;

[0014] Based on the determined evaluation task type, the environmental difficulty indicators, task effectiveness indicators and technical feature indicators of the underwater unmanned cluster are measured respectively to obtain environmental parameter statistics, task parameter statistics and technical feature statistics;

[0015] Based on the obtained environmental parameter statistics and task parameter statistics, the standard scores of the environmental difficulty indicators and the standard scores of the task effectiveness indicators are obtained by using probability score standardization transformation respectively; based on the obtained standard scores of the environmental difficulty indicators and the standard scores of the task effectiveness indicators, the external weights are calculated;

[0016] Based on the obtained technical feature statistics, the technical feature original score is obtained by using probability score standardization transformation;

[0017] The obtained external weight is multiplied by the original score of the technical feature to obtain an improved technical feature score; and evaluation grading is performed based on the obtained improved technical feature score to obtain an underwater unmanned cluster intelligence evaluation grading result.

[0018] The method further improves that,

[0019] In the step of obtaining the standard scores of the environmental difficulty index and the task effect index by using the probability score standardization transformation based on the obtained environmental parameter statistics and task parameter statistics, and in the step of obtaining the original score of the technical feature by using the probability score standardization transformation based on the obtained technical feature statistics,

[0020] The expression for obtaining the standard score by using the probability score standardization transformation is:

[0021] ;

[0022] ;

[0023] In the formula, is the standard score calculation value of the positive index, is the standard score calculation value of the negative index, the positive index is an index whose expected score increases with the increase of data, and the negative index is an index whose expected score decreases with the increase of data; is the mean of the index; is the variance of the index; t is the integral variable of the standard score.

[0024] The method further improves that,

[0025] In the step of obtaining the external weight based on the obtained standard scores of the environmental difficulty index and the task effect index,

[0026] The calculation expression of the external weight is:

[0027] ;

[0028] In the formula, is the external weight calculation value; is the environmental difficulty factor; is the task effect factor;

[0029] ;

[0030] ;

[0031] In the formula, is the number of the environmental difficulty indexes, indicates the i th environmental difficulty index. a standard score of the environmental difficulty index; a number of task effect indexes, a standard score of the first task effect index.

[0032] The method is further improved in that,

[0033] The evaluation task type is a perception type, a cognition type, a decision type, or an action type.

[0034] The environmental difficulty index includes one or more of water flow rate, obstacle density, visibility, acoustic noise level, and water temperature gradient.

[0035] When the evaluation task type is a perception type, the task effect index includes successful detection rate, maximum coverage area, and detection efficiency; when the evaluation task type is a cognition type, the task effect index includes inference accuracy and response speed; when the evaluation task type is a decision type, the task effect index includes qualified plan proportion and planning speed; and when the evaluation task type is an action type, the task effect index includes strike success rate and response speed.

[0036] The technical feature index includes human intervention frequency, information sharing frequency, and effect improvement ratio.

[0037] The method is further improved in that,

[0038] In the step of obtaining technical feature original scores by using a probability score standardization transformation based on the obtained technical feature statistics, the technical feature original scores include autonomy original scores, cooperativity original scores, and learning original scores.

[0039] The method is further improved in that,

[0040] In the step of obtaining improved technical feature scores by multiplying the obtained external weights and the technical feature original scores, and obtaining underwater unmanned swarm intelligence evaluation grading results based on the obtained improved technical feature scores,

[0041] The improved technical feature scores include autonomy improvement scores, cooperativity improvement scores, and learning improvement scores.

[0042] When the autonomy improvement score is less than 0.15, the evaluation is autonomy level one; when the autonomy improvement score is greater than or equal to 0.15 and less than or equal to 0.85, the evaluation is autonomy level two; and when the autonomy improvement score is greater than 0.85, the evaluation is autonomy level three.

[0043] When the collaborative improvement score is less than 0.15, it is evaluated as Level 1 collaborative improvement; when the collaborative improvement score is greater than or equal to 0.15 and less than or equal to 0.85, it is evaluated as Level 2 collaborative improvement; when the collaborative improvement score is greater than 0.85, it is evaluated as Level 3 collaborative improvement.

[0044] When the learning improvement score is less than 0.15, the assessment is Level 1; when the learning improvement score is greater than or equal to 0.15 and less than or equal to 0.85, the assessment is Level 2; when the learning improvement score is greater than 0.85, the assessment is Level 3.

[0045] A further improvement to the method of the present invention is that,

[0046] In the step of multiplying the obtained external weights by the original technical feature score to obtain an improved technical feature score; and performing an evaluation and classification based on the obtained improved technical feature score to obtain the evaluation and classification result of the intelligence of the underwater unmanned swarm,...

[0047] The calculation expression for the intelligence assessment and grading results of underwater unmanned swarms is as follows:

[0048] ;

[0049] In the formula, Indicates the level of intelligence; These represent three levels: autonomy, collaboration, and learning. .

[0050] A second aspect of the present invention provides a system for assessing and classifying the intelligence of underwater unmanned swarms, comprising:

[0051] The assessment task type acquisition module is used to determine the assessment task type based on the functional type of the underwater unmanned swarm to be assessed and graded for intelligence.

[0052] The statistics acquisition module is used to measure the environmental difficulty index, task effect index and technical characteristic index of the underwater unmanned swarm based on the determined evaluation task type, and to obtain environmental parameter statistics, task parameter statistics and technical characteristic statistics.

[0053] The external weight acquisition module is used to obtain the standard scores of the environmental difficulty index and the task effect index respectively by using probability score standardization transformation based on the obtained environmental parameter statistics and task parameter statistics; and to calculate the external weight based on the obtained standard scores of the environmental difficulty index and the task effect index.

[0054] The module for obtaining raw scores of technical features is used to obtain raw scores of technical features based on the obtained technical feature statistics and by using probability score standardization transformation.

[0055] An evaluation grading module is configured to multiply the obtained external weight and the original score of the technical feature to obtain an improved technical feature score, and perform evaluation grading based on the obtained improved technical feature score to obtain an underwater unmanned cluster intelligence evaluation grading result.

[0056] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for underwater unmanned cluster intelligence evaluation grading according to any one of the first aspect of the present application.

[0057] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for underwater unmanned cluster intelligence evaluation grading according to any one of the first aspect of the present application.

[0058] Compared with the prior art, the present application has the following beneficial effects:

[0059] Compared with the prior art, the present application has the following beneficial effects:

[0059] In view of the problem that the existing unmanned system grading scheme mainly relies on subjective scoring evaluation and does not correspond to objective performance indicators, the present application introduces objective performance indicators, which are specific and quantifiable, and can directly reflect different technical features of environmental difficulty, task performance and intelligence (i.e. autonomy, collaboration and learning), so that the evaluation result of the present application is no longer dependent on subjective judgment, but has a more solid and objective basis. In view of the problem that the existing scheme has a description that is too broad and lacks detailed task description of a certain type of cluster (such as underwater unmanned cluster) and lacks professionalism, the present application is specially designed for underwater unmanned cluster and covers environmental difficulty indicators and task performance indicators, which are customized according to the characteristics and task requirements of underwater unmanned cluster, so that the evaluation grading is more targeted and professional. In view of the problem that the existing scheme does not provide a standardized test method and only has a vague language description, the present application not only provides explicit evaluation indicators, but also designs a probability score standardization transformation method, which can unify the different dimensions of the indicators, making it possible to compare and calculate between the indicators, making the evaluation process more scientific and rigorous, and avoiding ambiguity and uncertainty. In view of the problem that the existing technology does not consider environmental change information and lacks adaptability to different environments, the present application introduces an environmental difficulty indicator as an external weight in the evaluation grading method, which can reflect the environmental complexity under different task test scenarios, so that the evaluation result can be automatically adjusted according to the different environments, making the evaluation grading method more flexible and adaptable, and better adapting to changes in different environments and task requirements. BRIEF DESCRIPTION OF DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description; obviously, the drawings described below are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0061] Figure 1 is a flowchart of a method for evaluating and grading the intelligence of an underwater unmanned cluster according to an embodiment of the present application;

[0062] Figure 2 is a schematic diagram of the principle of intelligence score grading according to an embodiment of the present application;

[0063] Figure 3 is a three-dimensional illustration of an environmental task technical indicator according to an embodiment of the present application;

[0064] Figure 4 is a technical feature score flowchart taking a perception task as an example according to an embodiment of the present application;

[0065] Figure 5 is a probability score standardization transformation calculation flowchart according to an embodiment of the present application;

[0066] Figure 6 is a score-grading conversion flowchart according to an embodiment of the present application;

[0067] Figure 7 is a grading threshold diagram according to an embodiment of the present application;

[0068] Figure 8 is a schematic diagram of a system for evaluating and grading the intelligence of an underwater unmanned cluster according to an embodiment of the present application. DETAILED DESCRIPTION

[0069] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application; obviously, the described embodiment technical solutions are some embodiments of the present application, and are not all the embodiments.

[0070] Based on the technical solutions disclosed in the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0071] Referring to Figure 1 and Figure 2 The embodiment of the present application provides a method for underwater unmanned cluster intelligence evaluation and grading, comprising the following steps:

[0072] Step 1, based on the function type of the underwater unmanned cluster to be evaluated and graded, the evaluation task type is determined; wherein the evaluation task type is perception, cognition, decision or action; interpretively, the purpose of this step is to clarify the target and scope of the evaluation, to ensure the pertinence and effectiveness of the evaluation, and the determined evaluation task can fully reflect the intelligence performance of the underwater unmanned cluster in different scenarios;

[0073] Step 2, based on the determined evaluation task type, the environmental difficulty index, the task effect index and the technical feature index of the underwater unmanned cluster to be evaluated and graded are measured respectively, and the environmental parameter statistics, the task parameter statistics and the technical feature statistics are obtained; interpretively, the environmental difficulty index is obtained by measuring the environmental complexity of the evaluation task, such as flow velocity, visibility, obstacle density, etc., these indexes are used to reflect the working difficulty of the underwater unmanned cluster in a specific environment; the task effect index is obtained by measuring the effect of the cluster completing the task, such as task completion rate, task completion time, task execution accuracy, etc., these indexes directly reflect the intelligence level of the underwater unmanned cluster; the technical feature index is obtained by measuring the technical features of the cluster in autonomy, collaboration, learning, etc., these indexes are the key elements of evaluating intelligence;

[0074] Step 3, based on the environmental parameter statistics and the task parameter statistics obtained in step 2, the standard scores of the environmental difficulty index and the task effect index are obtained by using the probability score standardization transformation respectively; based on the standard scores of the environmental difficulty index and the task effect index, the external weight is calculated and obtained;

[0075] Step 4, based on the technical feature statistics obtained in step 2, the technical feature original score is obtained by using the probability score standardization transformation;

[0076] Step 5, based on the external weight obtained in step 3 and the technical feature original score obtained in step 4, the improved technical feature score is calculated; based on the improved technical feature score, the underwater unmanned cluster intelligence evaluation and grading result is obtained.

[0077] In the technical solution provided by this invention, the evaluation task is first determined based on the functional type; then, environmental difficulty indicators, task effectiveness indicators, and technical characteristic indicators are measured respectively, and calculations are performed using their respective statistical measures to obtain improved technical characteristic scores for technical characteristics (i.e., autonomy, collaboration, and learning); finally, the intelligence evaluation grading result is determined based on the improved technical characteristic scores for autonomy, collaboration, and learning. This invention provides a comprehensive and systematic solution for the intelligence evaluation of underwater unmanned swarms by clearly defining the evaluation task, measuring key indicators, calculating scores and grading, and comprehensively considering technical characteristics. Through this process, the intelligence performance of the swarm in different environments can be objectively evaluated, providing strong support for the optimization and improvement of the swarm.

[0078] Please see Figure 3 To accurately characterize the strength of the technical characteristics (i.e., autonomy, collaboration, and learning) of underwater unmanned swarms in completing specific tasks under different environments, the technical solution of this invention adds consideration of environmental complexity and task completion, that is, calculates the external weights of technical characteristic indicators based on environmental difficulty indicators and task effectiveness indicators. For example... Figure 3 As shown, the environmental difficulty index considers the influence of factors such as water flow velocity, obstacle density, acoustic noise level, and water temperature gradient; the task performance index considers different indicators such as detection success rate, inference accuracy rate, planning speed, and strike success rate according to the different types of abilities tested by the task (such as perception, cognition, decision-making, and action); and the technical characteristic index considers the three major characteristics of intelligence: autonomy, collaboration, and learning, which serve as the main basis for intelligence assessment and grading.

[0079] Please see Figure 4 This invention takes the intelligent assessment and grading process of perception capability as an example. The specific assessment and grading process is as follows: In the classic perception task "patrol and reconnaissance", the commonly used environmental difficulty indicators are water flow velocity, obstacle density, acoustic noise level, and temperature gradient. The task performance indicators of the perception task are successful detection rate (the detection accuracy rate within a specified time), coverage area (the maximum area effectively detected by the cluster in the task), and detection efficiency (the area effectively detected and covered by the cluster per unit time). Probability score standardization transformation is applied to the environmental difficulty indicators and task performance indicators respectively to obtain the external weights of the underwater unmanned cluster in the test environment when performing the perception task. Then, probability score standardization transformation is applied again to the technical feature indicators of autonomy, cooperation, and learning: human intervention frequency (the number of interventions per unit time), information sharing frequency (the amount of information shared between unmanned vessels of the same type and between unmanned vessels of different types per unit time), and effect improvement ratio (the ratio of improvement of the main task completion indicators over time) to obtain the original technical feature score. The external weights are multiplied by the original technical feature score to obtain the improved technical feature score.

[0080] Explanatorily, for different types of evaluation tasks, the environmental difficulty index is consistent with the technical feature indexes of autonomy, collaboration and learning, and the task effect index is determined according to the evaluation task; in a specific technical solution, the task effect index is shown in Table 1.

[0081] Table 1. Task effect evaluation index table

[0082]

[0083] Please refer to Figure 5 , the probability score standardization transformation is a kind of mapping that maps the original data to the (0, 1) interval score, the specific steps are shown in Figure 5 , including:

[0084] Most of the indexes in the environmental difficulty index and the task effect index meet the normal distribution, and the standard score obtained after the probability score standardization transformation is expressed as:

[0085] (forward index) or (negative index);

[0086] In the formula, is the mean of the index; is the variance of the index; t is the time;

[0087] The positive index means that the score of the index should increase with the increase of the data (such as the information sharing frequency of collaboration); the negative index means that the score of the index should decrease with the increase of the data (such as the frequency of manual intervention of autonomy).

[0088] In the embodiment of the application, the probability score standardization transformation is denoted as , with this transformation, the standard score of (0, 1) can be obtained, which represents the ratio value of the data exceeding the same type in the normal distribution.

[0089] When calculating the external weight, the environmental difficulty factor and the task effect factor are calculated respectively; wherein the calculation expression of the environmental difficulty factor is:

[0090] ;

[0091] In the formula, is the number of environmental difficulty indexes; exemplarily, there are four environmental difficulty indexes: flow rate, obstacle density, acoustic noise level and temperature gradient, then ; represents the standard score of the th index.

[0092] Similar to the environmental difficulty factor, the calculation expression of the task effect factor is:

[0093] ;

[0094] In the formula, is the number of task effect indicators (n) Figure 4 Exemplarily, ), represents the standard score of the i-th indicator.

[0095] In the embodiment of the present application, the calculation expression of the external weight calculated by the environmental difficulty factor and the task effect factor is:

[0096] ;

[0097] Referring to Figure 6 , in the embodiment of the present application, the probability score standardization transformation is still used when calculating the original scores of autonomy, cooperativeness and learning. The original score of autonomy (OAS), the original score of cooperativeness (OCS) and the original score of learning (OLS) are respectively:

[0098] ;

[0099] ;

[0100] ;

[0101] After being multiplied by the external weight, the corresponding adjusted scores are obtained, and the calculation expression is:

[0102]

[0103]

[0104]

[0105] In this way, the adjusted scores of the three technical features are obtained.

[0106] After the adjusted scores are calculated, the levels of autonomy, cooperativeness and learning can be determined according to the fixed threshold method.

[0107] Referring to Figure 7 , the specific threshold is as follows: Figure 7 ​The underwater unmanned cluster is shown to be mostly in compliance with normal distribution in actual conditions, so the grading result should also show the characteristics of small at both ends and large in the middle; the ratios of the first, second and third levels are set to 15%, 70% and 15% respectively, that is, when the improvement score of the autonomy, collaboration or learning of the evaluated underwater unmanned cluster is less than 0.15, the underwater unmanned cluster is rated as level one of autonomy / collaboration / learning; when the improvement score is between 0.15 and 0.85, the underwater unmanned cluster is rated as level two of autonomy / collaboration / learning; and when the improvement score is greater than 0.85, the underwater unmanned cluster is rated as level three of autonomy / collaboration / learning.

[0108] Finally, according to the sum of the levels of the three technical features of autonomy / collaboration / learning, the final intelligence level is determined. The intelligence level is , which is divided into seven levels, and the specific classification is shown in Table 2.

[0109] Table 2. Grading details

[0110]

[0111] In Table 2, A1 represents level one of autonomy, C1 represents level one of collaboration, and L1 represents level one of learning; A2, A3 and the like are the same.

[0112] In summary, the present application considers the comprehensive influence of environmental difficulty and task completion in the evaluation test, so that the intelligence evaluation process of the underwater unmanned cluster has a certain adaptability to the environment and the task; at the same time, the task-oriented evaluation test method is adopted, and the score is calculated by using the objective index performance of the cluster, so as to eliminate the error caused by subjective scoring; for the four main intelligent types, different task effect indexes are designed, and a certain special purpose is increased. In the specific data processing, the probability score standardization transformation is adopted, which can transform various original data of different dimensions into dimensionless (0, 1) interval data, and has interpretability. In the final grading process, the autonomy, collaboration and learning three intelligent features are considered, each feature is graded by using the fixed threshold method, and the threshold setting conforms to the actual normal data; the intelligence grading is calculated by using the cumulative method, and the grading combination obtained also conforms to the actual demand. In summary, the technical scheme of the present application embodiment improves the existing unmanned system grading scheme comprehensively and effectively, introduces objective performance indexes, designs evaluation schemes for specific clusters, provides standardized test methods, and considers environmental change information, thereby providing a more scientific, rigorous, flexible and practical scheme for the intelligence evaluation and grading of underwater unmanned clusters.

[0113] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the apparatus embodiment, please refer to the method embodiment of the present application.

[0114] Please refer to Figure 8 In the embodiments of the present application, a system for underwater unmanned cluster intelligence evaluation grading is provided, comprising:

[0115] An evaluation task type acquisition module is configured to determine an evaluation task type based on a function type of the underwater unmanned cluster to be evaluated and graded in intelligence;

[0116] A statistical quantity acquisition module is configured to measure an environmental difficulty index, a task effect index and a technical feature index of the underwater unmanned cluster respectively based on the determined evaluation task type, and obtain an environmental parameter statistical quantity, a task parameter statistical quantity and a technical feature statistical quantity;

[0117] An external weight acquisition module is configured to obtain a standard score of the environmental difficulty index and a standard score of the task effect index respectively by using a probability score standardization transformation based on the obtained environmental parameter statistical quantity and the task parameter statistical quantity, and calculate an external weight based on the obtained standard score of the environmental difficulty index and the standard score of the task effect index;

[0118] A technical feature original score acquisition module is configured to obtain a technical feature original score by using a probability score standardization transformation based on the obtained technical feature statistical quantity;

[0119] An evaluation grading module is configured to multiply the obtained external weight and the technical feature original score to obtain an improved technical feature score, and perform evaluation grading based on the obtained improved technical feature score to obtain an underwater unmanned cluster intelligence evaluation grading result.

[0120] In an embodiment of the present application, a computer device is provided, which comprises a processor and a memory for storing a computer program comprising program instructions, the processor being configured to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc., which are the computing core and control core of the terminal, and are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in the computer storage medium to implement a corresponding method flow or corresponding function; the processor in the embodiments of the present application can be used to execute the operations of the method for evaluating and grading the intelligence of underwater unmanned clusters.

[0121] In an embodiment of the present application, a storage medium is provided, specifically a computer readable storage medium (Memory), which is a memory device in a computer device, and is used to store programs and data. It can be understood that the computer readable storage medium herein can include an internal storage medium in the computer device, and of course can also include an extended storage medium supported by the computer device. The computer readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM (Random Access Memory) memory, or a non-volatile memory such as at least one disk memory. One or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the method for evaluating and grading the intelligence of underwater unmanned clusters in the above embodiments.

[0122] Those skilled in the art will appreciate that embodiments of the application can be readily used as software, hardware, or a combination of software and hardware. In one

[0123] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks can represent code, circuits, hardware components, or executable computer program instructions on a machine-readable or computer-readable storage medium which, when executed by a computer or other Figure 1 an apparatus configured to perform the functions specified in the flowchart block or blocks.

[0124] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks can represent code, circuits, hardware components, or executable computer program instructions on a machine-readable or computer-readable storage medium which, when executed by a computer or other Figure 1 an apparatus configured to perform the functions specified in the flowchart block or blocks.

[0125] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks can represent code, circuits, hardware components, or executable computer program instructions on a machine-readable or computer-readable storage medium which, when executed by a computer or other Figure 1 an apparatus configured to perform the functions specified in the flowchart block or blocks.

[0126] Finally, it should be noted that the above-described embodiments are merely given as examples of the application and are not intended to limit the present application in any way. Thus, the scope of the application should be determined by the following claims, and all modifications of the application within the meaning and range of equivalents of the claims are to be embraced.

Claims

1. A method for assessing and classifying the intelligence of underwater unmanned swarms, characterized in that, Includes the following steps: Based on the functional types of underwater unmanned swarms to be assessed and graded for intelligence, the assessment task types are determined. Based on the determined assessment task type, the environmental difficulty index, task effectiveness index, and technical characteristic index of the underwater unmanned swarm are measured respectively to obtain environmental parameter statistics, task parameter statistics, and technical characteristic statistics. Based on the obtained environmental parameter statistics and task parameter statistics, the standard scores of the environmental difficulty index and the standard scores of the task effect index are obtained by using probability score standardization transformation. External weights are calculated based on the standard scores of the obtained environmental difficulty index and the standard scores of the task performance index. Based on the obtained technical feature statistics, the original scores of the technical features are obtained by using probability score standardization transformation; The obtained external weights are multiplied by the original score of the technical feature to obtain the improved technical feature score; Based on the obtained scores of the improved technical features, an evaluation and classification are performed to obtain the evaluation and classification results of the intelligence of underwater unmanned swarms. in, In the step of calculating the external weights based on the standard scores of the obtained environmental difficulty index and the standard scores of the task performance index... The formula for calculating external weights is: ； In the formula, Calculated as external weights; Environmental challenges; For task effectiveness factors; ； ； In the formula, The number of environmental difficulty indicators. Indicates the first Standard scoring for each environmental difficulty indicator; The number of task performance metrics. Indicates the first Standard scoring for each task's performance metrics; The assessment task type can be perception, cognition, decision-making, or action; the environmental difficulty indicators include one or more of water flow velocity, obstacle density, visibility, acoustic noise level, and water temperature gradient; when the assessment task type is perception, the task effectiveness indicators include successful detection rate, maximum coverage area, and detection efficiency; when the assessment task type is cognition, the task effectiveness indicators include inference accuracy and response speed; when the assessment task type is decision-making, the task effectiveness indicators include the percentage of qualified plans and planning speed; when the assessment task type is action, the task effectiveness indicators include strike success rate and response speed; the technical characteristic indicators include human intervention frequency, information sharing frequency, and effect improvement rate.

2. The method for assessing and classifying the intelligence of underwater unmanned swarms according to claim 1, characterized in that, In the steps of obtaining standard scores for the environmental difficulty index and the task performance index based on the obtained environmental parameter statistics and task parameter statistics using probability score standardization transformation, and in the step of obtaining the original score of the technical feature based on the obtained technical feature statistics using probability score standardization transformation,... The expression for obtaining the standard score using probability score standardization is: ； ； In the formula, The standard score for the positive indicator is calculated as follows. This is the standard score calculation value for negative indicators. Positive indicators are those whose deserved score increases as the data increases, while negative indicators are those whose deserved score decreases as the data increases. The mean of the indicator; The variance of the indicator; t The integral variable is the standard score.

3. The method for assessing and classifying the intelligence of underwater unmanned swarms according to claim 1, characterized in that, In the step of obtaining the original score of technical feature based on the obtained technical feature statistics and using probability score standardization transformation, the original score of technical feature includes the original score of autonomy, the original score of collaboration, and the original score of learning.

4. The method for assessing and classifying the intelligence of underwater unmanned swarms according to claim 3, characterized in that, In the step of multiplying the obtained external weights by the original technical feature score to obtain an improved technical feature score; and performing an evaluation and classification based on the obtained improved technical feature score to obtain the evaluation and classification result of the intelligence of the underwater unmanned swarm,... The scoring of improved technical features includes scores for autonomous improvement, collaborative improvement, and learning improvement. When the autonomous improvement score is less than 0.15, it is evaluated as Level 1 autonomous; when the autonomous improvement score is greater than or equal to 0.15 and less than or equal to 0.85, it is evaluated as Level 2 autonomous; when the autonomous improvement score is greater than 0.85, it is evaluated as Level 3 autonomous. When the collaborative improvement score is less than 0.15, it is evaluated as Level 1 collaborative improvement; when the collaborative improvement score is greater than or equal to 0.15 and less than or equal to 0.85, it is evaluated as Level 2 collaborative improvement; when the collaborative improvement score is greater than 0.85, it is evaluated as Level 3 collaborative improvement. When the learning improvement score is less than 0.15, the assessment is Level 1. A learning improvement score of 0.15 or higher and 0.85 or lower is assessed as Level 2; a learning improvement score of 0.85 or higher is assessed as Level 3.

5. The method for assessing and classifying the intelligence of underwater unmanned swarms according to claim 4, characterized in that, In the step of multiplying the obtained external weights by the original technical feature score to obtain an improved technical feature score; and performing an evaluation and classification based on the obtained improved technical feature score to obtain the evaluation and classification result of the intelligence of the underwater unmanned swarm,... The calculation expression for the intelligence assessment and grading results of underwater unmanned swarms is as follows: ； In the formula, Indicates the level of intelligence; These represent three levels: autonomy, collaboration, and learning. .

6. A system for assessing and grading the intelligence of underwater unmanned swarms, characterized in that, include: The assessment task type acquisition module is used to determine the assessment task type based on the functional type of the underwater unmanned swarm to be assessed and graded for intelligence. The statistics acquisition module is used to measure the environmental difficulty index, task effect index and technical characteristic index of the underwater unmanned swarm based on the determined evaluation task type, and to obtain environmental parameter statistics, task parameter statistics and technical characteristic statistics. The external weight acquisition module is used to obtain the standard scores of the environmental difficulty index and the task effect index respectively by using probability score standardization transformation based on the obtained environmental parameter statistics and task parameter statistics; and to calculate the external weight based on the obtained standard scores of the environmental difficulty index and the task effect index. The module for obtaining raw scores of technical features is used to obtain raw scores of technical features based on the obtained technical feature statistics and by using probability score standardization transformation. The evaluation and grading module is used to multiply the obtained external weights by the original score of the technical feature to obtain an improved technical feature score; Based on the obtained scores of the improved technical features, an evaluation and classification are performed to obtain the evaluation and classification results of the intelligence of underwater unmanned swarms. in, In the step of the external weight acquisition module calculating external weights based on the standard scores of the obtained environmental difficulty index and the task performance index, the external weight acquisition module performs the following steps. The formula for calculating external weights is: ； In the formula, Calculated as external weights; Environmental challenges; For task effectiveness factors; ； ； In the formula, The number of environmental difficulty indicators. Indicates the first Standard scoring for each environmental difficulty indicator; The number of task performance metrics. Indicates the first Standard scoring for each task's performance metrics; The assessment task type can be perception, cognition, decision-making, or action; the environmental difficulty indicators include one or more of water flow velocity, obstacle density, visibility, acoustic noise level, and water temperature gradient; when the assessment task type is perception, the task effectiveness indicators include successful detection rate, maximum coverage area, and detection efficiency; when the assessment task type is cognition, the task effectiveness indicators include inference accuracy and response speed; when the assessment task type is decision-making, the task effectiveness indicators include the percentage of qualified plans and planning speed; when the assessment task type is action, the task effectiveness indicators include strike success rate and response speed; the technical characteristic indicators include human intervention frequency, information sharing frequency, and effect improvement rate.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for assessing and classifying the intelligence of underwater unmanned swarms as described in any one of claims 1 to 5.

8. A non-transitory 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 method for assessing and classifying the intelligence of underwater unmanned swarms as described in any one of claims 1 to 5.

Images