WO2021056733A1 - 智能逻辑分析系统 - Google Patents

智能逻辑分析系统 Download PDF

Info

Publication number
WO2021056733A1
WO2021056733A1 PCT/CN2019/117549 CN2019117549W WO2021056733A1 WO 2021056733 A1 WO2021056733 A1 WO 2021056733A1 CN 2019117549 W CN2019117549 W CN 2019117549W WO 2021056733 A1 WO2021056733 A1 WO 2021056733A1
Authority
WO
WIPO (PCT)
Prior art keywords
causal
axis direction
cause
dimensional
dimensional corresponding
Prior art date
Application number
PCT/CN2019/117549
Other languages
English (en)
French (fr)
Inventor
祝青
Original Assignee
苏州车付通信息科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 苏州车付通信息科技有限公司 filed Critical 苏州车付通信息科技有限公司
Publication of WO2021056733A1 publication Critical patent/WO2021056733A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/448Execution paradigms, e.g. implementations of programming paradigms
    • G06F9/4482Procedural
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28Databases characterised by their database models, e.g. relational or object models
    • G06F16/284Relational databases
    • G06F16/285Clustering or classification

Definitions

  • the invention specifically relates to an intelligent logic analysis system.
  • the technical problem to be solved by the present invention is to provide an intelligent logic analysis system.
  • the present invention provides an intelligent logic analysis system, including: a causal definition set, a causal analysis algorithm set and a data set, in which:
  • the set of causal definitions is a set of causal classifications with definite meanings, any one of which can be a cause, an effect, or both a cause and an effect, and each classification contains an individual object;
  • the set of causal analysis algorithms It is a set of algorithms for analyzing the effect objects from the cause and effect set; the data set is different data required by the causality analysis algorithm.
  • the set of causal analysis algorithms forms a three-dimensional corresponding reasoning structure; one axis direction in the three-dimensional corresponding reasoning structure corresponds to all possible causes in the set of causality; one axis direction in the three-dimensional corresponding reasoning structure corresponds to all causes and effects Concentrated results; one axis in the three-dimensional corresponding reasoning structure corresponds to a variety of causal analysis algorithms for paired cause-to-effects.
  • the causal analysis algorithms for the corresponding causal-to-effect relationship in this direction can be used for the corresponding cause
  • the object analyzes the analyzed fruit object.
  • the longitudinal Y-axis direction in the three-dimensional corresponding reasoning structure corresponds to all possible causal concentrated causes; the horizontal X-axis direction in the three-dimensional corresponding reasoning structure corresponds to all causal concentrated effects; the three-dimensional corresponding reasoning structure deep A variety of causal analysis algorithms that correspond to the paired cause-to-effect in the Z-axis direction.
  • the deep Z-axis direction in the three-dimensional corresponding reasoning structure corresponds to all possible causes in the causal concentration;
  • the horizontal X-axis direction in the three-dimensional corresponding reasoning structure corresponds to all the results in the causal concentration;
  • the three-dimensional corresponding reasoning structure The longitudinal Y-axis direction corresponds to a variety of causal analysis algorithms for paired cause-to-effects.
  • the longitudinal Y-axis direction in the three-dimensional corresponding reasoning structure corresponds to all possible causes in the causal concentration; the deep Z-axis direction in the three-dimensional corresponding reasoning structure corresponds to all the results in the causal concentration; the three-dimensional corresponding reasoning structure
  • the horizontal X-axis direction corresponds to a variety of causal analysis algorithms for paired cause-to-effects.
  • the horizontal X-axis direction in the three-dimensional corresponding reasoning structure corresponds to all possible causal concentrated causes; the longitudinal Y-axis direction in the three-dimensional corresponding reasoning structure corresponds to all the results in the causal concentration; the three-dimensional corresponding reasoning structure deep A variety of causal analysis algorithms that correspond to the paired cause-to-effect in the Z-axis direction.
  • the cause object or the effect object may be single or multiple.
  • the causal analysis algorithm in the three-dimensional corresponding inference structure in each inference process is described in sequence to form an inference graph.
  • each causal analysis algorithm may be another causal analysis algorithm in any one of the intelligent logic analysis systems.
  • the system also includes a machine learning system, the input of which is the input of any one of the intelligent logic analysis system and the corresponding correct output after screening, and the corresponding three-dimensional corresponding reasoning structure;
  • the training of the learning system produces a model that selects the three-dimensional corresponding inference structure.
  • the intelligent logic analysis system can determine the three-dimensional inference structure according to the input of the intelligent logic analysis system and use this three-dimensional inference structure to form an output result.
  • the present invention implements different analysis algorithms on various data to obtain different results of the three-dimensional algorithm construction, so that each algorithm corresponding to the data can interact in a three-dimensional space, so that each analysis and reasoning path can use the same series of analysis
  • the algorithm is described, which lays the foundation for analysis, reasoning and quantification. Based on this basic analysis and reasoning method, cluster analysis and deep learning can be used as objects to realize the self-learning intelligent reasoning of machine learning machines.
  • Figure 1 is a schematic diagram of the structure of the intelligent logic analysis system of the present invention.
  • an intelligent logic analysis system including: a set of causal definitions, a set of causal analysis algorithms and a set of data, in which:
  • the set of causal definitions is a set of causal classifications with definite meanings, any one of which can be a cause, an effect, or both a cause and an effect, and each classification contains an individual object;
  • the set of causal analysis algorithms It is a set of algorithms for analyzing the effect objects from the cause and effect set; the data set is different data required by the causality analysis algorithm.
  • the set of causal analysis algorithms forms a three-dimensional corresponding reasoning structure; one axis direction in the three-dimensional corresponding reasoning structure corresponds to all possible cause and effect sets; one axis direction in the three-dimensional corresponding reasoning structure corresponds to all The classification of the effects in the causal concentration; one axis in the three-dimensional corresponding reasoning structure corresponds to a variety of causal analysis algorithms for the paired cause-to-effects.
  • the causal analysis algorithms for the corresponding causal-to-effect relationships in this direction can be used for the corresponding causal analysis algorithms.
  • the causal object analyzes the analyzed result object.
  • the longitudinal Y-axis direction in the three-dimensional corresponding reasoning structure corresponds to all possible causal concentrated causes; the horizontal X-axis direction in the three-dimensional corresponding reasoning structure corresponds to all causal concentrated effects; the three-dimensional corresponding reasoning structure deep A variety of causal analysis algorithms that correspond to the paired cause-to-effect in the Z-axis direction.
  • the deep Z-axis direction in the three-dimensional corresponding reasoning structure corresponds to all possible causes in the causal concentration;
  • the horizontal X-axis direction in the three-dimensional corresponding reasoning structure corresponds to all the results in the causal concentration;
  • the three-dimensional corresponding reasoning structure The longitudinal Y-axis direction corresponds to a variety of causal analysis algorithms for paired cause-to-effects.
  • the longitudinal Y-axis direction in the three-dimensional corresponding reasoning structure corresponds to all possible causes in the causal concentration; the deep Z-axis direction in the three-dimensional corresponding reasoning structure corresponds to all the results in the causal concentration; the three-dimensional corresponding reasoning structure
  • the horizontal X-axis direction corresponds to a variety of causal analysis algorithms for paired cause-to-effects.
  • the horizontal X-axis direction in the three-dimensional corresponding reasoning structure corresponds to all possible causal concentrated causes; the longitudinal Y-axis direction in the three-dimensional corresponding reasoning structure corresponds to all the results in the causal concentration; the three-dimensional corresponding reasoning structure deep A variety of causal analysis algorithms that correspond to the paired cause-to-effect in the Z-axis direction.
  • the cause object or the effect object may be single or multiple.
  • the causal analysis algorithm in the three-dimensional corresponding inference structure in each inference process is described in sequence to form an inference graph.
  • each causal analysis algorithm may be another causal analysis algorithm in any one of the intelligent logic analysis systems.
  • the system further includes a machine learning system, the input of which is the input of any one of the intelligent logic analysis system and the corresponding correct output after screening, and the corresponding three-dimensional corresponding reasoning structure;
  • the training of the learning system produces a model that selects the three-dimensional corresponding inference structure.
  • the intelligent logic analysis system can determine the three-dimensional inference structure according to the input of the intelligent logic analysis system and use this three-dimensional inference structure to form an output result.
  • the present invention implements different analysis algorithms on various data to obtain different results of the three-dimensional algorithm construction, so that each algorithm corresponding to the data can interact in a three-dimensional space, so that each analysis reasoning path can use the same series of analysis
  • the algorithm is described, which lays the foundation for analysis, reasoning and quantification. Based on this basic analysis and reasoning method, cluster analysis and deep learning can be used as the object to realize the self-learning intelligent reasoning of machine learning machines.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

一种智能逻辑分析系统,包括:一个因果定义集,一个因果分析算法集和一个数据集,其中的因果定义集为一个具有确定涵义的因果分类集合,其中的任何一个分类可以是因,也可以是果,也可以既是因也是果,每个分类中包含个体对象;其中的因果分析算法集为一个从因果集中的因对象分析出果对象的算法集合;其中的数据集则是因果分析算法所需的不同数据。由此,通过对各种数据实施不同的分析算法得出不同的结果的算法三维构建,使每种对应数据的算法能在一个三维空间中交互。

Description

智能逻辑分析系统 技术领域
本发明具体涉及一种智能逻辑分析系统。
背景技术
在利用大数据进行多门类多种类的数据推理分析时,往往一个(或多个)输出可能导致无数中分析和推理的路径,有些分析路径可以得出想要的结论。而大部分分析及推理路径却不能得出有用的结论,因此浪费大量的计算资源。
发明内容
本发明要解决的技术问题是提供一种智能逻辑分析系统。
为了解决上述技术问题,本发明提供了一种智能逻辑分析系统,包括:一个因果定义集,一个因果分析算法集和一个数据集,其中:
所述因果定义集为一个具有确定涵义的因果分类集合,其中的任何一个分类可以是因,也可以是果,也可以既是因也是果,每个分类中包含个体对象;所述因果分析算法集为一个从所述因果集中的因对象分析出果对象的算法集合;所述数据集则是因果分析算法所需的不同数据。
在其中一个实施例中,所述因果分析算法集组成一个三维对应推理结构;三维对应推理结构中的一个轴方向对应所有可能的因果集中的因;三维对应推理结构中的一个轴方向对应所有因果集中的果;三维对应推理结构中的一个轴方向对应所成对的因到果的多种因果分析算法,该方向上所对应的因到果关系的因果分析算法都可用于由所对应的因对象分析出所分析的果对象。
在其中一个实施例中,三维对应推理结构中的纵向Y轴方向对应所有可能的因果集中的因;三维对应推理结构中的横向X轴方向对应所有因果集中的果;三维对应推理结构中的深向Z轴方向对应所成对的因到果的多种因果分析算法。
在其中一个实施例中,三维对应推理结构中的深向Z轴方向对应所有可能的因果集中的因;三维对应推理结构中的横向X轴方向对应所有因果集中的果;三维对应推理结构中的纵向Y轴方向对应所成对的因到果的多种因果分析算法。
在其中一个实施例中,三维对应推理结构中的纵向Y轴方向对应所有可能的因果集中的因;三维对应推理结构中的深向Z轴方向对应所有因果集中的果;三维对应推理结构中的横向X轴方向对应所成对的因到果的多种因果分析算法。
在其中一个实施例中,三维对应推理结构中的横向X轴方向对应所有可能的因果集中的因;三维对应推理结构中的纵向Y轴方向对应所有因果集中的果;三维对应推理结构中的深向Z轴方向对应所成对的因到果的多种因果分析算法。
在其中一个实施例中,因对象或果对象可以是单个也可以是多个。
在其中一个实施例中,每个推理过程中的三维对应推理结构中的因果分析算法使用顺序来描述,形成推理图。
在其中一个实施例中,每个因果分析算法可以是另一个任一项所述的智能逻辑分析系统中的因果分析算法。
在其中一个实施例中,该系统还包含一个机器学习系统,其输入为任一项所述的智能逻辑分析系统的输入和经过筛选的相应的正确输出,以及相应的三维对应推理结构;经过机器学习系统的训练,产生选择三维对应推理结构的模型,利用这一模型,智能逻辑分析系统可以根据智能逻辑分析系统的输入确定 三维推理结构并利用这一三维推理结构形成输出结果。
本发明的有益效果:
本发明通过对各种数据实施不同的分析算法得出不同的结果的算法三维构建,使每种对应数据的算法能在一个三维空间中交互,从而使每一个分析推理路径可以用同一连串的分析算法进行描述,从而奠定了分析推理量化的基础。基于这个基础分析推理方法得以做为对象进行聚类分析和深度学习,实现机器学习机器的自学习智能推理。
附图说明
图1是本发明智能逻辑分析系统的结构示意图。
具体实施方式
下面结合附图和具体实施例对本发明作进一步说明,以使本领域的技术人员可以更好地理解本发明并能予以实施,但所举实施例不作为对本发明的限定。
参阅图1,一种智能逻辑分析系统,包括:一个因果定义集,一个因果分析算法集和一个数据集,其中:
所述因果定义集为一个具有确定涵义的因果分类集合,其中的任何一个分类可以是因,也可以是果,也可以既是因也是果,每个分类中包含个体对象;所述因果分析算法集为一个从所述因果集中的因对象分析出果对象的算法集合;所述数据集则是因果分析算法所需的不同数据。
在其中一个实施例中,所述因果分析算法集组成一个三维对应推理结构;三维对应推理结构中的一个轴方向对应所有可能的因果集中的因分类;三维对应推理结构中的一个轴方向对应所有因果集中的果分类;三维对应推理结构中 的一个轴方向对应所成对的因到果的多种因果分析算法,该方向上所对应的因到果关系的因果分析算法都可用于由所对应的因对象分析出所分析的果对象。
在其中一个实施例中,三维对应推理结构中的纵向Y轴方向对应所有可能的因果集中的因;三维对应推理结构中的横向X轴方向对应所有因果集中的果;三维对应推理结构中的深向Z轴方向对应所成对的因到果的多种因果分析算法。
在其中一个实施例中,三维对应推理结构中的深向Z轴方向对应所有可能的因果集中的因;三维对应推理结构中的横向X轴方向对应所有因果集中的果;三维对应推理结构中的纵向Y轴方向对应所成对的因到果的多种因果分析算法。
在其中一个实施例中,三维对应推理结构中的纵向Y轴方向对应所有可能的因果集中的因;三维对应推理结构中的深向Z轴方向对应所有因果集中的果;三维对应推理结构中的横向X轴方向对应所成对的因到果的多种因果分析算法。
在其中一个实施例中,三维对应推理结构中的横向X轴方向对应所有可能的因果集中的因;三维对应推理结构中的纵向Y轴方向对应所有因果集中的果;三维对应推理结构中的深向Z轴方向对应所成对的因到果的多种因果分析算法。
在其中一个实施例中,因对象或果对象可以是单个也可以是多个。
在其中一个实施例中,每个推理过程中的三维对应推理结构中的因果分析算法使用顺序来描述,形成推理图。
在其中一个实施例中,每个因果分析算法可以是另一个任一项所述的智能逻辑分析系统中的因果分析算法。
在其中一个实施例中,该系统还包含一个机器学习系统,其输入为任一项所述的智能逻辑分析系统的输入和经过筛选的相应的正确输出,以及相应的三 维对应推理结构;经过机器学习系统的训练,产生选择三维对应推理结构的模型,利用这一模型,智能逻辑分析系统可以根据智能逻辑分析系统的输入确定三维推理结构并利用这一三维推理结构形成输出结果。
本发明的有益效果:
本发明通过对各种数据实施不同的分析算法得出不同的结果的算法三维构建,使每种对应数据的算法能在一个三维空间中交互,从而使每一个分析推理路径可以用同一连串的分析算法进行描述,从而奠定了分析推理量化的基础。基于这个基础分析推理方法得以做为对象进行聚类分析和深度学习,实现机器学习机器的自学习智能推理。
以上所述实施例仅是为充分说明本发明而所举的较佳的实施例,本发明的保护范围不限于此。本技术领域的技术人员在本发明基础上所作的等同替代或变换,均在本发明的保护范围之内。本发明的保护范围以权利要求书为准。

Claims (10)

  1. 一种智能逻辑分析系统,其特征在于,包括:一个因果定义集,一个因果分析算法集和一个数据集,其中:
    所述因果定义集为一个具有确定涵义的因果分类集合,其中的任何一个分类可以是因,也可以是果,也可以既是因也是果,每个分类中包含个体对象。所述因果分析算法集为一个从所述因果集中的因对象分析出果对象的算法集合;所述数据集则是因果分析算法所需的不同数据。
  2. 如权利要求1所述的智能逻辑分析系统,其特征在于,所述因果分析算法集组成一个三维对应推理结构;三维对应推理结构中的一个轴方向对应所有可能的因果集中的因;三维对应推理结构中的一个轴方向对应所有因果集中的果;三维对应推理结构中的一个轴方向对应所成对的因到果的多种因果分析算法,该方向上所对应的因到果关系的因果分析算法都可用于由所对应的因对象分析出所分析的果对象。
  3. 如权利要求2所述的智能逻辑分析系统,其特征在于,三维对应推理结构中的纵向Y轴方向对应所有可能的因果集中的因;三维对应推理结构中的横向X轴方向对应所有因果集中的果;三维对应推理结构中的深向Z轴方向对应所成对的因到果的多种因果分析算法。
  4. 如权利要求2所述的智能逻辑分析系统,其特征在于,三维对应推理结构中的深向Z轴方向对应所有可能的因果集中的因;三维对应推理结构中的横向X轴方向对应所有因果集中的果;三维对应推理结构中的纵向Y轴方向对应所成对的因到果的多种因果分析算法。
  5. 如权利要求2所述的智能逻辑分析系统,其特征在于,三维对应推理结构中的纵向Y轴方向对应所有可能的因果集中的因;三维对应推理结构中的深向Z轴方向对应所有因果集中的果;三维对应推理结构中的横向X轴方向对应 所成对的因到果的多种因果分析算法。
  6. 如权利要求2所述的智能逻辑分析系统,其特征在于,三维对应推理结构中的横向X轴方向对应所有可能的因果集中的因;三维对应推理结构中的纵向Y轴方向对应所有因果集中的果;三维对应推理结构中的深向Z轴方向对应所成对的因到果的多种因果分析算法。
  7. 如权利要求2到6任一项所述的智能逻辑分析系统,其特征在于,因对象或果对象可以是单个也可以是多个。
  8. 如权利要求2到7任一项所述所述的智能逻辑分析系统,其特征在于,每个推理过程中的三维对应推理结构中的因果分析算法使用顺序来描述,形成推理图。
  9. 如权利要求2-8任一项所述的智能逻辑分析系统,其特征在于,每个因果分析算法可以是另一个权利要求2-8任一项所述的智能逻辑分析系统中的因果分析算法。
  10. 如权利要求2到9任一项所述的智能逻辑分析系统,其特征在于,该系统还包含一个机器学习系统,其输入为权利要求2到9任一项所述的智能逻辑分析系统的输入和经过筛选的相应的正确输出,以及相应的三维对应推理结构;经过机器学习系统的训练,产生选择三维对应推理结构的模型,利用这一模型,智能逻辑分析系统可以根据智能逻辑分析系统的输入确定三维推理结构并利用这一三维推理结构形成输出结果。
PCT/CN2019/117549 2019-09-23 2019-11-12 智能逻辑分析系统 WO2021056733A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910899100.5A CN110825462A (zh) 2019-09-23 2019-09-23 智能逻辑分析系统
CN201910899100.5 2019-09-23

Publications (1)

Publication Number Publication Date
WO2021056733A1 true WO2021056733A1 (zh) 2021-04-01

Family

ID=69548125

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/117549 WO2021056733A1 (zh) 2019-09-23 2019-11-12 智能逻辑分析系统

Country Status (2)

Country Link
CN (1) CN110825462A (zh)
WO (1) WO2021056733A1 (zh)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103262103A (zh) * 2010-07-13 2013-08-21 M8公司 用于情景分析的处理器
US20140095425A1 (en) * 2012-09-28 2014-04-03 Sphere Of Influence, Inc. System and method for predicting events
CN106648862A (zh) * 2015-12-08 2017-05-10 Tcl集团股份有限公司 一种向用户推荐个性化调度的功能项序列的方法和系统
CN107662617A (zh) * 2017-09-25 2018-02-06 重庆邮电大学 基于深度学习的车载交互控制算法
CN109598347A (zh) * 2017-09-30 2019-04-09 日本电气株式会社 用于确定因果关系的方法、系统和计算机程序产品
CN109621422A (zh) * 2018-11-26 2019-04-16 腾讯科技(深圳)有限公司 电子棋牌决策模型训练方法及装置、策略生成方法及装置
CN109948678A (zh) * 2019-03-08 2019-06-28 国网浙江省电力有限公司 一种基于模糊贝叶斯理论的长期用电量预测方法
CN109947898A (zh) * 2018-11-09 2019-06-28 中国电子科技集团公司第二十八研究所 基于智能化的装备故障测试方法
CN110110043A (zh) * 2019-04-11 2019-08-09 中山大学 一种多跳视觉问题推理模型及其推理方法
WO2019160138A1 (ja) * 2018-02-19 2019-08-22 日本電信電話株式会社 因果推定装置、因果推定方法、及びプログラム

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103262103A (zh) * 2010-07-13 2013-08-21 M8公司 用于情景分析的处理器
US20140095425A1 (en) * 2012-09-28 2014-04-03 Sphere Of Influence, Inc. System and method for predicting events
CN106648862A (zh) * 2015-12-08 2017-05-10 Tcl集团股份有限公司 一种向用户推荐个性化调度的功能项序列的方法和系统
CN107662617A (zh) * 2017-09-25 2018-02-06 重庆邮电大学 基于深度学习的车载交互控制算法
CN109598347A (zh) * 2017-09-30 2019-04-09 日本电气株式会社 用于确定因果关系的方法、系统和计算机程序产品
WO2019160138A1 (ja) * 2018-02-19 2019-08-22 日本電信電話株式会社 因果推定装置、因果推定方法、及びプログラム
CN109947898A (zh) * 2018-11-09 2019-06-28 中国电子科技集团公司第二十八研究所 基于智能化的装备故障测试方法
CN109621422A (zh) * 2018-11-26 2019-04-16 腾讯科技(深圳)有限公司 电子棋牌决策模型训练方法及装置、策略生成方法及装置
CN109948678A (zh) * 2019-03-08 2019-06-28 国网浙江省电力有限公司 一种基于模糊贝叶斯理论的长期用电量预测方法
CN110110043A (zh) * 2019-04-11 2019-08-09 中山大学 一种多跳视觉问题推理模型及其推理方法

Also Published As

Publication number Publication date
CN110825462A (zh) 2020-02-21

Similar Documents

Publication Publication Date Title
Abu et al. A study on Image Classification based on Deep Learning and Tensorflow
Yang et al. A bio-inspired self-learning coevolutionary dynamic multiobjective optimization algorithm for internet of things services
Wenk et al. Fast Gaussian process based gradient matching for parameter identification in systems of nonlinear ODEs
GB2604263A (en) Processor and system to identify out-of-distribution input data in neural networks
Pak et al. An empirical study on software defect prediction using over-sampling by SMOTE
CN105678381A (zh) 一种性别分类网络训练方法、性别分类方法及相关装置
Mishra et al. Analysis of the effect of elite count on the behavior of genetic algorithms: A perspective
WO2021056733A1 (zh) 智能逻辑分析系统
Singh et al. Stl-based synthesis of feedback controllers using reinforcement learning
CN104461861B (zh) 基于efsm模型的路径测试数据生成方法
TWM592123U (zh) 推論系統或產品品質異常的智能系統
Mönks et al. Fast evidence-based information fusion
Karmakar et al. Multilevel Random Forest algorithm in image recognition for various scientific applications
Diallo et al. An explainable deep learning approach for adaptation space reduction
Shyamala et al. Defect prediction in medical software using hybrid genetic optimized support vector machines
Tanuska et al. Data mining model building as a support for decision making in production management
Abdelbari et al. Model learning using genetic programming under full and partial system information conditions
Xu et al. Multi-objective cost-sensitive attribute reduction
Ahmadizadeh et al. Analytic synchronization conditions for a network of Wilson and Cowan oscillators
CN104932847A (zh) 一种空间网络3d打印算法
Lin et al. A double learning models-based multi-objective estimation of distribution algorithm
Lutton et al. Gridvis: Visualisation of island-based parallel genetic algorithms
Haluszczynski Prediction and control of nonlinear dynamical systems using machine learning
Zhang et al. Classifying feature description for software defect prediction
Cheng et al. Demonstrator selection in a social learning particle swarm optimizer

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19946492

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19946492

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19946492

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 210922)

122 Ep: pct application non-entry in european phase

Ref document number: 19946492

Country of ref document: EP

Kind code of ref document: A1