CN114490284A - A test method for autonomous unmanned systems - Google Patents
A test method for autonomous unmanned systemsDownload PDFInfo
- Publication number
- CN114490284A CN114490284ACN202111611666.7ACN202111611666ACN114490284ACN 114490284 ACN114490284 ACN 114490284ACN 202111611666 ACN202111611666 ACN 202111611666ACN 114490284 ACN114490284 ACN 114490284A
- Authority
- CN
- China
- Prior art keywords
- index
- evaluation
- autonomous unmanned
- matrix
- factor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明属于无人系统测试技术领域，尤其涉及一种用于自主无人系统的测试方法。The invention belongs to the technical field of unmanned system testing, and in particular relates to a testing method for an autonomous unmanned system.
背景技术Background technique
自主无人系统是拥有认知、分析、决策和行动等能力的高度智能化的闭环反馈控制系统。随着人工智能技术的快速发展，自主、集群、有人/无人协同为典型特征的规模化无人系统，将成为未来科技的重要发展方向。目前自主无人系统由两大部分组成，一是具备智能处理和决策能力的无人平台，二是具有感知、交互、通信等能力的辅助部分组成。自主无人系统具备感知、交互和学习的能力，基于知识进行自主推理、自主决策，从而达成设定的目标。Autonomous unmanned systems are highly intelligent closed-loop feedback control systems with the capabilities of cognition, analysis, decision-making and action. With the rapid development of artificial intelligence technology, large-scale unmanned systems with typical characteristics of autonomy, clustering, and manned/unmanned collaboration will become an important development direction of future technology. At present, the autonomous unmanned system consists of two parts, one is an unmanned platform with intelligent processing and decision-making capabilities, and the other is an auxiliary part with capabilities such as perception, interaction, and communication. Autonomous unmanned systems have the ability to perceive, interact and learn, and conduct autonomous reasoning and decision-making based on knowledge, so as to achieve the set goals.
人工智能无论从理论研究还是从应用实践都存在众多分支和发展方向。在理论上人工智能分为王大学派，如符号主义(Symbolicism)或计算机学派(Computerism)；连结主义或生理学派(Physiologism)；行为主义(Actionism)或控制论学派(Cybemeticsism)等。在应用实践上，人工智能可应用的方向包括符号计算、模式识别、机器翻译、机器学习、问题求解、逻辑推理与定理证明、自然语言处理、分布式人工智能、计算机视觉、智能信息检索、专家系统等。Artificial intelligence has many branches and development directions both from theoretical research and from application practice. In theory, artificial intelligence is divided into Wang University schools, such as Symbolism or Computerism; Connectionism or Physiologism; Actionism or Cybernetics. In application practice, the applicable directions of artificial intelligence include symbolic computing, pattern recognition, machine translation, machine learning, problem solving, logical reasoning and theorem proving, natural language processing, distributed artificial intelligence, computer vision, intelligent information retrieval, experts system, etc.
由于每种具体的人工智能系统往往只具备一个或若干上述提到的功能，没有统一的分析和测试方法对不同的人工智能系统进行测试。因此，针对自主无人系统的人工智能水平的定量评测还面临多项困难，需要研究建立针对无人系统人工智能水平的表征方法，建立认知和决策行为评级量表，研究量化的测试方法，对无人系统的人工智能水平进行评估。Since each specific artificial intelligence system often only has one or several of the above-mentioned functions, there is no unified analysis and testing method to test different artificial intelligence systems. Therefore, the quantitative evaluation of the artificial intelligence level of autonomous unmanned systems still faces many difficulties. It is necessary to study and establish a characterization method for the artificial intelligence level of unmanned systems, establish a rating scale for cognition and decision-making behavior, and study quantitative testing methods. Evaluate the level of artificial intelligence of unmanned systems.
发明内容SUMMARY OF THE INVENTION
基于此，本发明提供一种用于自主无人系统的测试方法，通过借鉴人类智商测试的分析策略，构建智能评价指标量表和计算方法。Based on this, the present invention provides a test method for an autonomous unmanned system, which constructs an intelligent evaluation index scale and a calculation method by referring to the analysis strategy of human IQ test.
本发明通过以下技术方案实现。The present invention is realized by the following technical solutions.
一种用于自主无人系统的测试方法，包括：A test method for autonomous unmanned systems, comprising:
根据自主无人系统的智能化特征，构建分层分级的评估模型量表，建立分层分级的指标因素集U；对所述指标因素集U中的各项属性进行评分，确定决策能力评价集V；将所述指标因素集U的各项属性与对应的决策能力评价集V进行组合，构建评判隶属矩阵R；对指标因素集U中的各项属性进行相对权重评估，通过构建比较评判矩阵A，最终得出分级指标的权重向量W；将指标权重向量W和分级指标评判隶属矩阵R相乘，最终得出模糊决策集B，所述模糊决策集B的各个元素即为对自主无人的系统的各个指标因素的评分。According to the intelligent characteristics of the autonomous unmanned system, a hierarchical evaluation model scale is constructed, and a hierarchical and hierarchical index factor set U is established; the attributes in the index factor set U are scored to determine the decision-making ability evaluation set V; combine the attributes of the index factor set U with the corresponding decision-making ability evaluation set V to construct a judgment membership matrix R; carry out a relative weight evaluation on the attributes in the index factor set U, and construct a comparative judgment matrix A, and finally obtain the weight vector W of the grading index; multiply the index weight vector W and the grading index judgment membership matrix R, and finally obtain the fuzzy decision set B, and each element of the fuzzy decision set B is the The score of each index factor of the system.
本发明的有益效果：Beneficial effects of the present invention:
相对于传统评估模型量表中是针对特定智能设备或算法进行评估，本发明没有限制评估模型量表的内容，通过多级评分及加权的量表设计方法，使评分方法具备高度扩展性；本发明的评估计算过程引入模糊决策的计算方法，通过指标权重向量，实现对不同评分项目的权重调整。Compared with the traditional evaluation model scale, which is evaluated for a specific intelligent device or algorithm, the present invention does not limit the content of the evaluation model scale, and through the multi-level scoring and weighted scale design method, the scoring method is highly scalable; The evaluation calculation process of the invention introduces the calculation method of fuzzy decision, and realizes the weight adjustment of different scoring items through the index weight vector.
附图说明Description of drawings
图1为本发明一种用于自主无人系统的测试方法流程图。FIG. 1 is a flow chart of a testing method for an autonomous unmanned system according to the present invention.
具体实施方式Detailed ways
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述。In order to make those skilled in the art better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application.
如图1所示，本实施方式中的一种用于自主无人系统的测试方法，具体包括如下步骤：As shown in FIG. 1 , a test method for an autonomous unmanned system in this embodiment specifically includes the following steps:
步骤一、根据自主无人系统的智能化特征，构建分层分级的评估模型量表，建立分层分级的指标因素集U；Step 1. According to the intelligent characteristics of the autonomous unmanned system, build a hierarchical evaluation model scale, and establish a hierarchical and hierarchical index factor set U;
具体实施时，可以针对评估对象的实际情况，提出一些切实能够反映评估对象效能的评估内容，所述评估内容的好坏与系统性能的好坏密切相关，评估内容构成模型的最高一层(以下简称顶层)，然后，将每一项评估内容层层分解，直至产生可精确定义的和可精确测试的属性为止，将这些属性按照层级组合起来，本层级的属性组合成该层级的指标因素子集合，该集合同时是上一层级的指标因素集的元素之一。以此类推，构建完整分层分级的指标因素集U；During the specific implementation, some evaluation contents that can truly reflect the performance of the evaluation object can be proposed according to the actual situation of the evaluation object. The quality of the evaluation content is closely related to the quality of the system performance. (referred to as the top level), and then decompose each evaluation content layer by layer until accurately definable and accurately testable attributes are generated. These attributes are combined according to the level, and the attributes of this level are combined into the index factors of this level. A set that is also one of the elements of the index factor set at the previous level. And so on, construct a complete hierarchical index factor set U;
步骤二、对所述指标因素集U中的各项属性进行评分，确定决策能力评价集V；Step 2: Scoring each attribute in the index factor set U to determine a decision-making ability evaluation set V;
本实施例中所述的评判集是对决策能力进行评估的基本标准，采用量化或非量化评分方法，对指标因素集U中的某项具体指标进行评估，并统计评分的结果。The evaluation set described in this embodiment is a basic standard for evaluating decision-making ability. A quantitative or non-quantitative scoring method is used to evaluate a specific index in the index factor set U, and the scoring result is counted.
所述量化评分方法是通过搭建试验环境，对自主无人系统的某项指标进行测试，并根据指标给出评分的数值的分布；例如，得分在[0,10)、[10,20)、……、[90,100]分数区间的分数的占比，各分值占比的集合即为评价集V。The quantitative scoring method is to test a certain index of the autonomous unmanned system by building a test environment, and give the distribution of the numerical value of the score according to the index; ..., the proportion of the scores in the [90, 100] score interval, and the collection of the proportions of each score is the evaluation set V.
所述非量化评分方法是通过多名专家评分，对自主无人系统的某项指标进行打分，并统计评分的分布；例如，打分在[0,10)、[10,20)、……、[90,100]分数区间的专家的占比，各分值占比的集合即为评价集V。The non-quantitative scoring method is to score a certain indicator of the autonomous unmanned system through scoring by multiple experts, and count the distribution of scores; The proportion of experts in the [90, 100] score interval, and the collection of the proportions of each score is the evaluation set V.
步骤三、将所述指标因素集U的各项属性与对应的决策能力评价集V进行组合，构建评判隶属矩阵R。具体为：对所述指标因素集U中的每个指标因素，都完成评分，形成该指标因素对应的评判集，然后将所有评判集依照指标因素集U的结构组合起来，得到指标评判隶属矩阵R，其中各个元素表示为rij，即第j个指标关于第i项评价因素的指标值；Step 3: Combine the attributes of the index factor set U with the corresponding decision-making ability evaluation set V to construct an evaluation membership matrix R. Specifically: complete the scoring for each index factor in the index factor set U, form a judgement set corresponding to the index factor, and then combine all the judgement sets according to the structure of the index factor set U to obtain the index judgement membership matrix R, where each element is represented as rij , that is, the index value of the jth index about the i-th evaluation factor;
步骤四、对指标因素集U中的各项属性进行相对权重评估，通过构建比较评判矩阵A，最终得出分级指标的权重向量W；Step 4: Perform relative weight evaluation on each attribute in the index factor set U, and finally obtain the weight vector W of the grading index by constructing a comparison and judgment matrix A;
具体实施时，由于各级指标对自主无人系统的各个属性对自主无人系统智能水平的影响程度不同，因此在进行综合评判时，进一步按照重要程度对不同属性进行加权，给出每级指标的权重向量W。During the specific implementation, since the various attributes of the autonomous unmanned system have different influences on the intelligence level of the autonomous unmanned system, the different attributes are further weighted according to their importance in the comprehensive evaluation, and the indexes of each level are given. The weight vector W of .
采用层次分析法对指标因素集U中的各项属性进行相对权重评估，具体为：The analytic hierarchy process is used to evaluate the relative weights of each attribute in the index factor set U, specifically:
首先，构造比较评判矩阵A，根据各指标之间的内在联系，通过两两比较法，确定自主无人系统的各个属性之间的相对重要程度，构造比较评判矩阵A＝(aij)，ij表示第i个指标与第j个指标的相对重要性，然后，将评判矩阵A按行、列进行归一化后，得到权重向量W。First, construct a comparative evaluation matrix A, and determine the relative importance of each attribute of the autonomous unmanned system through the pairwise comparison method according to the internal relationship between the indicators, and construct a comparative evaluation matrix A=(aij ), ij Indicates the relative importance of the ith index and the jth index, and then, after normalizing the judgment matrix A by row and column, the weight vector W is obtained.
步骤五、将指标权重向量W和分级指标评判隶属矩阵R相乘，最终得出模糊决策集B，所述模糊决策集B的各个元素即为对自主无人的系统的各个指标因素的评分。Step 5: Multiply the index weight vector W and the grading index judgment membership matrix R to finally obtain a fuzzy decision set B, and each element of the fuzzy decision set B is the score for each index factor of the autonomous and unmanned system.
自此，实现对自主无人的系统的智能特征的量化评估。Since then, a quantitative assessment of the intelligence characteristics of autonomous unmanned systems has been achieved.
实施例1:Embodiment 1:
(1)针对某个自主无人系统，建立评估模型量表，并构建三级指标因素集。一级评判指标共有n类，其构成的因素集U如下：(1) For an autonomous unmanned system, establish an evaluation model scale, and construct a three-level index factor set. There are n types of first-level evaluation indicators, and the factor set U composed of them is as follows:
U＝{指标1，指标2，指标3，……，指标n}＝{u1,u2,u3,…,un}U={index 1, index 2, index 3,..., index n}={u1,u2,u3,...,un}
同理，上述指标中第k类一级指标，可以划分为m类二级评判指标，其构成的因素集如下：Similarly, the k-th first-level indicators in the above indicators can be divided into m-type second-level evaluation indicators, and the set of factors is as follows:
Uk＝{指标1，指标2，指标3，……，指标m}＝{uk1,uk2,uk3,…,ukm}Uk={indicator1,indicator2,indicator3,...,indicatorm}={uk1,uk2,uk3,...,ukm}
依次类推，上述指标中，第q类二级指标，可以划分为l类三级评判指标，其构成因素集如下：By analogy, among the above indicators, the second-level indicators of type q can be divided into the third-level evaluation indicators of type l, and the set of factors is as follows:
Ukq＝{指标1，指标2，指标3，……，指标l}＝{ukq1,ukq2,ukq3,…,ukql}Ukq={index 1, index 2, index 3,..., index l}={ukq1,ukq2,ukq3,...,ukql}
如上所述，逐级对指标进行分解，直至分解到最底层可精确定义的和可精确测试的属性。As described above, the indicators are decomposed level by level, down to the lowest level of precisely definable and precisely testable properties.
(2)制定评判集，采用100分制打分方法，最高分数是100，代表在该项指标上，自主无人系统达到最高智能程度；最低分数为0，代表在该项指标上，自主无人系统无智能。划定各个评分区间，可以得到评判集V：(2) Formulate a judgment set, and use a 100-point scoring method. The highest score is 100, which means that the autonomous unmanned system has reached the highest level of intelligence on this indicator; the lowest score is 0, which represents that this indicator is autonomous and unmanned. The system has no intelligence. By delineating each scoring interval, the judgment set V can be obtained:
V＝(v1,v2,v3,v4,v5,v6,v7,v8,v9,v10)＝([0,10)，[10,20)，[20,30)，[30,40)，V=(v1,v2,v3,v4,v5,v6,v7,v8,v9,v10)=([0,10),[10,20),[20,30),[30,40),
[40,50)，[50,60)，[60,70)，[70,80)，[80,90)，[90,100])[40,50), [50,60), [60,70), [70,80), [80,90), [90,100])
通过多次试验或多个专家打分，统计打分在[0,10)、[10,20)、……、[90,100]分数区间的占比，计算出该项指标对应的评判集。Through multiple tests or scores by multiple experts, the proportion of scores in the range of [0,10), [10,20), ..., [90,100] is calculated, and the judgment set corresponding to this indicator is calculated.
(3)确定分级指标评判隶属矩阵R，即用评判集V中的分数，为指标因素集U中的每个指标因素进行评分，形成分级指标评判隶属矩阵R。(3) Determine the grading index evaluation membership matrix R, that is, use the scores in the evaluation set V to score each index factor in the index factor set U, and form the grading index evaluation membership matrix R.
(4)确定分级指标权重向量W。构造比较评判矩阵A，对指标因素集U中的元素进行两两比较，得到评判矩阵A中的各个元素值。评判矩阵A中的元素用aij表示，若因素i与因素j比较得aij，那么因素j与因素i比较得1/aij。aij的取值一般取正整数1、3、5、7、9及其倒数。以某个因素为准则，本层次因素i与因素j相比，1、3、5、7、9分别表示i比j同样重要、稍微重要、明显重要、强烈重要和极端重要。将得到的评判矩阵A，按行、列进行归一化后，得到权重向量W。(4) Determine the weight vector W of the grading index. Construct a comparison judgment matrix A, and compare the elements in the index factor set U pairwise to obtain the value of each element in the judgment matrix A. The elements in the judgment matrix A are represented by aij. If the factor i and the factor j are compared to aij, then the factor j and the factor i are compared to be 1/aij. The value of aij generally takes positive integers 1, 3, 5, 7, 9 and their reciprocals. Taking a certain factor as a criterion, compared with factor j at this level, 1, 3, 5, 7, and 9 indicate that i is equally important, slightly important, obviously important, strongly important and extremely important than j, respectively. After normalizing the obtained judgment matrix A by row and column, the weight vector W is obtained.
(5)计算得到模糊决策集B(5) Calculate the fuzzy decision set B
采用权重指标向量W和评判隶属矩阵R进行合成运算，得到V上的模糊子集B，即B＝W·R。按此方法进行各级指标的运算。The weight index vector W and the judgment membership matrix R are used to perform a composite operation, and the fuzzy subset B on V is obtained, that is, B=W·R. According to this method, the calculation of indicators at all levels is carried out.
最后，将B与一级指标对应的评判集V相乘，得到最终分数值，通过此分数对自主无人系统的分数进行量化评估。Finally, multiply B by the evaluation set V corresponding to the first-level index to obtain the final score value, and use this score to quantitatively evaluate the score of the autonomous unmanned system.
综上所述，以上仅为本发明的较佳实例而已，并非用于限定本发明的保护范围。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。To sum up, the above are only preferred examples of the present invention, and are not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111611666.7ACN114490284A (en) | 2021-12-27 | 2021-12-27 | A test method for autonomous unmanned systems |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111611666.7ACN114490284A (en) | 2021-12-27 | 2021-12-27 | A test method for autonomous unmanned systems |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114490284Atrue CN114490284A (en) | 2022-05-13 |
Family
ID=81496562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111611666.7APendingCN114490284A (en) | 2021-12-27 | 2021-12-27 | A test method for autonomous unmanned systems |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114490284A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102829980A (en)* | 2012-03-29 | 2012-12-19 | 中国科学院自动化研究所 | Intelligent degree evaluation method of intelligent vehicle |
| CN103234763A (en)* | 2013-04-09 | 2013-08-07 | 北京理工大学 | System and method for quantitatively evaluating unmanned vehicles |
| CN106651169A (en)* | 2016-12-19 | 2017-05-10 | 国家电网公司 | Fuzzy comprehensive evaluation-based distribution automation terminal state evaluation method and system |
| CN107609730A (en)* | 2017-07-27 | 2018-01-19 | 广西电网有限责任公司电力科学研究院 | A kind of method being classified based on AHP Fuzzy Evaluation Methods to sale of electricity company |
| CN109063976A (en)* | 2018-07-12 | 2018-12-21 | 李振轩 | Intelligence manufacture capability maturity evaluation method based on Fuzzy AHP |
| CN111932066A (en)* | 2020-07-02 | 2020-11-13 | 中国电子技术标准化研究院 | Intelligent degree evaluation method of intelligent household product based on fuzzy analytic hierarchy process |
- 2021
- 2021-12-27CNCN202111611666.7Apatent/CN114490284A/enactivePending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102829980A (en)* | 2012-03-29 | 2012-12-19 | 中国科学院自动化研究所 | Intelligent degree evaluation method of intelligent vehicle |
| CN103234763A (en)* | 2013-04-09 | 2013-08-07 | 北京理工大学 | System and method for quantitatively evaluating unmanned vehicles |
| CN106651169A (en)* | 2016-12-19 | 2017-05-10 | 国家电网公司 | Fuzzy comprehensive evaluation-based distribution automation terminal state evaluation method and system |
| CN107609730A (en)* | 2017-07-27 | 2018-01-19 | 广西电网有限责任公司电力科学研究院 | A kind of method being classified based on AHP Fuzzy Evaluation Methods to sale of electricity company |
| CN109063976A (en)* | 2018-07-12 | 2018-12-21 | 李振轩 | Intelligence manufacture capability maturity evaluation method based on Fuzzy AHP |
| CN111932066A (en)* | 2020-07-02 | 2020-11-13 | 中国电子技术标准化研究院 | Intelligent degree evaluation method of intelligent household product based on fuzzy analytic hierarchy process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hu | Teaching evaluation system by use of machine learning and artificial intelligence methods | |
| CN107273490A (en) | A kind of combination mistake topic recommendation method of knowledge based collection of illustrative plates | |
| CN107967254A (en) | Knowledge point prediction method and device, storage medium and electronic equipment | |
| CN109242223A (en) | The quantum support vector machines of city Public Buildings Fire Risk is assessed and prediction technique | |
| CN113221332B (en) | Coastal erosion vulnerability assessment method based on cloud model theory | |
| Lonij et al. | Open-world visual recognition using knowledge graphs | |
| Costa et al. | Automatic classification of computational thinking skills in elementary school math questions | |
| Liu | Research on Balanced Allocation of English Educational Resources Based on Multi-objective Optimisation and NSGA-II | |
| Tiruneh et al. | Feature selection for construction organizational competencies impacting performance | |
| CN109685133A (en) | The data classification method of prediction model low cost, high discrimination based on building | |
| Tang et al. | Classification of Chinese Herbal Medicines by deep neural network based on orthogonal design | |
| CN110046667B (en) | A teaching evaluation method based on deep neural network learning and scoring data pairs | |
| CN114490284A (en) | A test method for autonomous unmanned systems | |
| CN117291463A (en) | Comprehensive evaluation method and device for interpretive technology of intelligent model | |
| Verma | Machine Learning Model for Applicability of Hybrid Learning in Practical Laboratory | |
| Shou et al. | Learning path planning algorithm based on kl divergence and d-value matrix similarity | |
| Zhao et al. | Research on multiattribute comprehensive evaluation of intelligent judicial decision system | |
| CN115953055A (en) | Empowerment system of cognitive ability assessment model of civil aviation pilot | |
| CN115204475A (en) | Drug rehabilitation place security incident risk assessment method | |
| Huang | MOOC English online learning resource recommendation algorithm based on spectral clustering and matrix decomposition | |
| Li et al. | Evaluation of the Quality of Sustainable Entrepreneurship Education in Universities Based on the Grey Correlation Algorithm | |
| Shen | Research on the application of RBF neural network in the evaluation of college English teaching quality | |
| Liu et al. | Cognitive Support System for Collaborative Learning and Blended Learning Based on Fuzzy Logic. | |
| Jia | [Retracted] Random Algorithm and Skill Evaluation System Based on the Combing of Construction Mechanism of Higher Vocational Professional Group | |
| Wang et al. | Model of normal university students’ education quality based on artificial neural networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |