LÓGICA DIFUSA

VolverVolver

Resultados 102 resultados LastUpdate Última actualización 26/03/2019 [17:56:00] pdf PDF

Solicitudes publicadas en los últimos 360 días / Applications published in the last 360 days

Página1 de 5 nextPage   por página


种基于模糊时间序列的高陡边坡形变预测的方法

NºPublicación: CN109460608A 12/03/2019

Solicitante:

\u4E1C\u5317\u5927\u5B66

Resumen de: CN109460608A

本发明提供种基于模糊时间序列的高陡边坡形变预测的方法,包括:获得多组天顶距、斜距、方位角的测量数据,其中根据数据的范围合理的划分论域,根据整体分布优化算法将论域合理的分为i个连续区间,通过三角模糊隶属度函数定义i个论域区间的隶属度函数;模糊化历史数据,将测量数据分配至各个模糊区间实施模糊化;通过定连续时间序列的模糊集建立以个模糊关系,将数据中所有相同初始状态的全部模糊关系放到同个模糊关系组中,建立模糊矩阵;根据建立好的模糊矩阵去模糊化预测。上述方法在坡度突变时准确率依然较高,整体分布优化算法避免了平均值分论域的片面性,整体提高了预测精度。

traducir

种基于不定长模糊信息粒的时间序列预测方法和装置

NºPublicación: CN109447333A 08/03/2019

Solicitante:

\u5C71\u4E1C\u5E08\u8303\u5927\u5B66

Resumen de: CN109447333A

本发明提供了种基于不定长模糊信息粒的时间序列预测方法和装置,采用K线图构造方法处理原始时间序列,基于K线分笔思想的不等长划分论域方法划分模糊时间序列;基于划分后的模糊时间序列构造带状高斯模糊信息粒,形成模糊时间序列的不定长模糊信息粒群体;构建循环模糊神经网络,并进行结构学习和参数学习;利用循环模糊神经网络对模糊时间序列进行长期预测,并将预测结果去模糊化。本发明基于信息颗粒和循环模糊神经网络实现时间序列长期预测,预测的多个值可以在步内完成,而不是迭代地分别预测每个值,即可以实现长期预测。

traducir

种基于弃光条件判断的储能容量计算方法

NºPublicación: CN109446479A 08/03/2019

Solicitante:

\u56FD\u7F51\u8FBD\u5B81\u7701\u7535\u529B\u6709\u9650\u516C\u53F8\u7535\u529B\u79D1\u5B66\u7814\u7A76\u9662,
\u6C88\u9633\u5DE5\u4E1A\u5927\u5B66,
\u56FD\u5BB6\u7535\u7F51\u6709\u9650\u516C\u53F8

Resumen de: CN109446479A

本发明属于电网技术领域,尤其涉及种基于弃光条件判断的储能容量计算方法,在当前大量光伏不断并网的电力系统中,为保证电网安全稳定运行,对弃光条件的判定及对弃光容量的判断尤为重要。本发明首先对电网内的数据参数进行采集,在微网通过配电网与外部电网进行并网时需要保证两者之间的平衡稳定,在光伏电站出力达到定程度或波动较大时,需要弃光,使电网保持稳定,需进行弃光条件标准判定;弃光量计算;计算弃光量;计算所需储能系统容量。根据电网在不同天气条件下针对光伏电站出力大小的不确定性及波动的不稳定性,对电网内负荷不能完全消纳光伏电站发电量时,及储能系统处于饱和状态时,对弃光量判断,使电网内发出功率与负荷保持平衡。

traducir

种承担调峰任务的库多级式梯级库群短期计划制定方法

NºPublicación: CN109447405A 08/03/2019

Solicitante:

\u4E2D\u56FD\u5357\u65B9\u7535\u7F51\u6709\u9650\u8D23\u4EFB\u516C\u53F8,
\u5927\u8FDE\u7406\u5DE5\u5927\u5B66

Resumen de: CN109447405A

本发明涉及电网规划和调度运行领域,特别涉及种承担调峰任务的库多级式梯级库群短期计划制定方法。首先,依据电网负荷曲线分布特征采用模糊半梯级隶属度函数划分峰谷时段,调节电站峰平谷比例确定电站典型调峰曲线;然后,采用粒子群算法求解厂间电量分配的过程;最后,计算过程中为减少弃水的发生采用弃水调整策略对各电站出力过程进行修正,最大限度减少弃水。本发明的方法实现上下游电站出力匹配,平衡调峰及蓄能的关系,改进短期调峰因复杂约束带来时效性不强的问题。本发明的方法原理清晰、易于操作、计算效率高,为解决实际工程调度问题提供了切实可行的新思路。

traducir

种工业编组站确定车列解体顺序的量化方法

NºPublicación: CN109447414A 08/03/2019

Solicitante:

\u897F\u5B89\u8D22\u7ECF\u5B66\u9662

Resumen de: CN109447414A

本发明公开了种工业编组站确定车列解体顺序的量化方法。运用模糊数学的原理和方法对工业编组站优选解体车列的确定过程进行数学描述,提出了种量化方法。针对模糊分析过程中优选矩阵的各个特性指标参量,结合工业编组站工作实际从理论上进行定量分析,提出套描述特性指标参量的量化模型。本发明方法步骤简单,操作方便,能够对车列解体顺序进行优选且结果更客观地接近实际,提高了该项工作的科学性和有效性,实用性强,使用效果好,便于推广使用。

traducir

种基于模糊椭球数的模糊模式识别方法

NºPublicación: CN109409436A 01/03/2019

Solicitante:

\u676D\u5DDE\u7535\u5B50\u79D1\u6280\u5927\u5B66

Resumen de: CN109409436A

本发明公开了种基于模糊椭球书的模糊识别方法,其按如下步骤进行:第步:获取待辨识的目标或l个标准类别的观测数据组;第二步:计算第步中标准类别各个特征的均值u、左离散度Lσ和右离散度Rσ;第三步:构造标准类别的抛物模糊椭球数u;第四步:利用联合隶属度逼近算法,计算待辨识目标分别对应各标准类别的隶属度;第五步:根据最大隶属度原则,判定待辨识目标的模式分类。本发明可以合理构造模糊对象的隶属函数,准确地对模糊对象的识别问题进行模糊模式识别。

traducir

种科技资源服务构件的优化配置方法

NºPublicación: CN109408039A 01/03/2019

Solicitante:

\u6606\u660E\u7406\u5DE5\u5927\u5B66

Resumen de: CN109408039A

本发明公开了种科技资源服务构件的优化配置方法,属于资源服务构件的优化配置领域。该方法包括步骤:首先,构建科技资源服务构件多目标优化配置模型;然后,基于模糊物元分析理论将多目标组合优化模型转化为单目标组合优化模型;最后,基于单目标组合优化模型使用改进的群集智能算法进行多层次多粒度科技服务构件的自适应优化组合。采用基于模糊物元分析和改进的群集智能算法的双层组合求解方法,实现了多层次多粒度科技资源服务构件的自适应优化组合,同时也实现了由服务需求到服务质量、资源利用率、服务效率的资源服务平台的动态构建模式。

traducir

琥珀砕片の種別および透明度の推定方法、推定装置、ならびに推定プログラム

NºPublicación: JP2019032231A 28/02/2019

Solicitante:

\u56FD\u7ACB\u5927\u5B66\u6CD5\u4EBA\u79CB\u7530\u5927\u5B66,
\u4E45\u6148\u7425\u73C0\u682A\u5F0F\u4F1A\u793E

Resumen de: JP2019032231A

【課題】珀砕片の種別および透明度を推定可能な推定方法を提供する。【解決手段】水平面に静置された琥珀砕片に上方から光を照射し、上部カラー画像を取得する工程と、上部カラー画像にマスク処理を施し、上部マスク画像を作成する工程と、上部マスク画像を解析し、上部マスク画像における琥珀画素のRGB成分およびHSV成分の情報を取得する工程と、R成分の平均値とV成分の平均値とが等しい画素の割合、および、S成分の平均値から、外皮物と琥珀との判別を行う工程と、琥珀と判別された琥珀砕片が写る上部マスク画像の琥珀画素を対象に、黄琥珀、茶琥珀および黒琥珀からなる琥珀種別の各琥珀への帰属度を算出し、帰属度が最も高い琥珀種別に琥珀砕片を判別する工程と、黄琥珀と判別された琥珀砕片の透明度を、ファジィ推論を用いて推定する工程と、を含む、琥珀砕片の種別および透明度の推定方法とする。【選択図】図1

traducir

ARTIFICIAL INTELLIGENCE TERMINAL SYSTEM, SERVER AND BEHAVIOR CONTROL METHOD THEREOF

NºPublicación: WO2019037076A1 28/02/2019

Solicitante:

SHENZHEN DEDAO HEALTH MAN CO LTD [CN]

CN_109313645_A

Resumen de: WO2019037076A1

The present invention relates to the technical field of computers. Disclosed are an artificial intelligence terminal system, a server and a behavior control method thereof. The method comprises: receiving data of a first behavior to be executed, the data of the first behavior being uploaded by an artificial intelligence terminal; performing matching on the basis of the data of the first behavior to be executed and behavior control data in a pre-established behavior control database to obtain a first feasibility; and transmitting the first feasibility to the artificial intelligence terminal, such that the artificial intelligence terminal can determine, according to the first feasibility, whether to execute the first behavior or not. In the embodiment of the present invention, the behavior control data can be used to regulate the behavior of the artificial intelligence terminal.

traducir

ENSURING VERACITY OF INPUT CORPUS FOR EFFECTIVE ARTIFICIAL INTELLIGENCE APPLICATIONS: VERACITY INDEX

NºPublicación: US2019057322A1 21/02/2019

Solicitante:

DESIRAJU NIHARIKA SEAL [US]

Resumen de: US2019057322A1

Artificially Intelligent systems are able to draw inferences and conclusions by analyzing information in natural language and then using such information to prove or disprove hypotheses. The quality of such inferences is directly dependent on the accuracy of the input data corpus. Given the proliferation of the Internet as well as the dubious data sources on social media, it is important to determine the truthfulness of the input information. Combining concepts of library classification, crowd-sourced curation and Google Scholar search, we propose the concept of the Veracity Index and an algorithm to calculate it. This index can be used in Artificial Systems to determine the confidence measurement of the inferences.

traducir

基于模糊算子的图像融合处理方法及系统、计算机程序

NºPublicación: CN109345497A 15/02/2019

Solicitante:

\u6DEE\u9634\u5E08\u8303\u5B66\u9662

Resumen de: CN109345497A

本发明属于图像处理技术领域,公开了种基于模糊算子的图像融合处理方法及系统、计算机程序;根据需要融合的两幅图像即源图1和源图2,通过Lukasiewicz蕴涵算子进行像素级学习训练,得到关系矩阵R;以源图1为输入信息,以R为关系矩阵,利用Lukasiewicz三角模算子T,得到融合的目标图像。本发明与现有图像融合方法相比较,省去了大量的复杂数学推算和前期工作,简洁高效易于实现,无论是亮度信息还是细节信息都能将待融合的图像信息很好地互补融合,融合后的图像视觉效果好,细节信息明显,目标清晰。从下实例测试在同台电脑相同运行环境下测得的融合图像,可以很清晰地比较出本发明融合方法的优于现有技术。

traducir

MULTI-MODE DATA COLLECTION AND TRAVELER PROCESSING

NºPublicación: US2019042961A1 07/02/2019

Solicitante:

SECURIPORT LLC [US]

Resumen de: US2019042961A1

A technique includes receiving, for a traveler, traveler information via a plurality of different information collection modes, determining a reliability score for each of the plurality of information collection modes, determining a cumulative score for the traveler based on the reliability score for each of the plurality of information collection modes, determining whether the cumulative score is greater than or equal to a threshold, performing traveler processing based on the received traveler information if the cumulative score is greater than or equal to the threshold, and otherwise, receiving for the traveler, traveler information via an additional different information collection mode if the cumulative score is less than the threshold.

traducir

MACHINE LEARNING DEVICE AND USER IDENTIFICATION DEVICE

NºPublicación: US2019034818A1 31/01/2019

Solicitante:

FANUC CORP [JP]

JP_2019025582_A

Resumen de: US2019034818A1

A machine learning device capable of preventing spoofing of an operator to secure safety during an operation of a robot is provided. A machine learning device includes: an input data acquisition means that acquires, as input data, operation data including a measurement value related to a movement of at least a portion of a body of the operator and a shape of the body, detected when the operator is caused to perform a predetermined operation associated with a training operation panel of the robot controller; a label acquisition means that acquires identification information of the operator as a label; and a learning means that constructs a learning model that performs user identification for authenticating operators of the robot controller by performing supervised learning using a pair of the input data and the label as training data.

traducir

BOOTSTRAPPING MULTIPLE VARIETIES OF GROUND TRUTH FOR A COGNITIVE SYSTEM

NºPublicación: US2019026654A1 24/01/2019

Solicitante:

IBM [US]

US_2019026650_A1

Resumen de: US2019026654A1

Curating high-quality ground truth is an important but difficult part of training a cognitive system. The invention greatly simplifies this process by determining the value that particular training data has in improving existing ground truth. Candidate training data of different types (text, audio, images) is extracted from an interaction log, and each entry is analyzed to arrive at a training value score. The analysis generates multiple component scores which are combined for the final score. The component scores may include a per-feature variability score, a cross-feature variability score, and an accuracy score. A set of the unverified entries may be presented to a user based on the training value scores, and the user can select which of the entries in the set should be included as new ground truths. The ground truths can then be updated by adding the selected entries.

traducir

BOOTSTRAPPING MULTIPLE VARIETIES OF GROUND TRUTH FOR A COGNITIVE SYSTEM

NºPublicación: US2019026650A1 24/01/2019

Solicitante:

IBM [US]

US_2019026654_A1

Resumen de: US2019026650A1

Curating high-quality ground truth is an important but difficult part of training a cognitive system. The invention greatly simplifies this process by determining the value that particular training data has in improving existing ground truth. Candidate training data of different types (text, audio, images) is extracted from an interaction log, and each entry is analyzed to arrive at a training value score. The analysis generates multiple component scores which are combined for the final score. The component scores may include a per-feature variability score, a cross-feature variability score, and an accuracy score. A set of the unverified entries may be presented to a user based on the training value scores, and the user can select which of the entries in the set should be included as new ground truths. The ground truths can then be updated by adding the selected entries.

traducir

EXPANDABILITY RETENTION DEVICE

NºPublicación: EP3432228A1 23/01/2019

Solicitante:

OMRON TATEISI ELECTRONICS CO [JP]

JP_WO2017159620_A1

Resumen de: EP3432228A1

A mechanism for increasing efficiency of development work for adding a new ability to a device is provided. Also, a device with excellent extensibility, having a mechanism for easily adding a new ability provided from the outside, is provided. A device with extensibility includes an architecture modeled as an ability acquisition model including an ability unit for implementing an ability, an data input unit that is an interface for an input from the ability unit, and a data output unit that is an interface for an output from the ability unit, as an architecture for additionally incorporating a new ability to a basic configuration of the device, and includes an ability setting unit for adding the new ability to the device by setting a function to each of the ability unit, the data input unit, and the data output unit, based on ability providing data including ability setting data, input setting data, and output setting data.

traducir

FRAUD DETECTION SYSTEM AND METHOD

NºPublicación: WO2019013974A1 17/01/2019

Solicitante:

VAIL SYSTEMS INC [US]

US_2019020757_A1

Resumen de: WO2019013974A1

A system and method for fraud detection for a telephony platform based on an analysis of call detail records (CDRs) that are generated by the telephony platform. The analysis is based on collecting, organizing, transforming, analyzing, and quantifying the CDR data into a plurality of data analytics and data correlations and then applying fuzzy logic to the data analytics to generate a fraud risk rating for each incoming call into the platform.

traducir

种有源无源数据融合方法

NºPublicación: CN109190647A 11/01/2019

Solicitante:

\u4E2D\u56FD\u7535\u5B50\u79D1\u6280\u96C6\u56E2\u516C\u53F8\u7B2C\u4E8C\u5341\u4E5D\u7814\u7A76\u6240

Resumen de: CN109190647A

本发明提供了种有源无源数据融合方法,通过模糊聚类的方法,在时间维度和空间维度上根据有源数据和无源数据之间的相似度,在时间维上数据对准,空间维上模糊聚类,进行数据子集划分和关联隶属度计算。与现有技术相比,灵活性好,相较于现有方法中融合结果的好坏取决于角度差阈值门限的选取,不再需要设置专门的融合门限,使用更加灵活化;融合误差低,大大提高了融合可靠性,降低了融合误差;适应性好,可适用于所有的有源/无源数据融合系统,对于多种传感器的数据融合系统也可适用,具有很好的系统适用性。

traducir

基于区间层次分析的产品子系统的故障时间计算方法

NºPublicación: CN109165740A 08/01/2019

Solicitante:

\u7535\u5B50\u79D1\u6280\u5927\u5B66

Resumen de: CN109165740A

本发明公开了种基于区间层次分析的产品子系统的故障时间计算方法,其包括将产品划分为若干子系统;采用专家对任意两个影响因素间相对重要程度的打分构建层次分析法中的1~9标度矩阵,并将矩阵扩展为连续型的0~9标度矩阵;当0~9标度矩阵满足致性检验时,计算0~9标度矩阵的权重向量;构建各子系统平均故障率所占比重的模糊关系矩阵;根据模糊关系矩阵,计算模糊因素的隶属函数矩阵;采用权重向量和隶属函数矩阵,计算产品可靠性对子系统的隶属程度;对每个子系统的隶属程度去模糊化,得到每个子系统的实数隶属程度;根据实数隶属程度和产品整机的平均故障时间,计算子系统的平均故障时间。

traducir

种应用于分布参数系统的时空模糊建模方法

NºPublicación: CN109145421A 04/01/2019

Solicitante:

\u4E2D\u5357\u5927\u5B66

Resumen de: CN109145421A

本发明公开了种应用于分布参数系统的时空模糊建模方法,用于加热过程温度场的建模分析,包括:选择样本点,并建立样本点各自随时间变化的模糊模型,以预测系统内未知时刻的输出;通过未知空间点与样本点之间的联系,建立分布参数系统的空间模糊模型,并优化模型中的参数以预测到系统内未知空间位置的输出;整合所述时间模糊模型和所述空间模糊模型形成时空模糊模型。本发明利用模糊逻辑原理,在不需要建立数学模型的情况下,可以建立系统的模型,且获得良好的建模精度;针对分布参数系统的状态与空间信息有关的特点,考虑了空间信息,使分布参数系统的模型建立得到了明显的改善;并且具有很好的鲁棒性。

traducir

EXPANDABILITY RETENTION DEVICE

NºPublicación: JPWO2017159620A1 27/12/2018

Solicitante:

\u30AA\u30E0\u30ED\u30F3\u682A\u5F0F\u4F1A\u793E

US_2018357078_A1

Resumen de: WO2017159620A1

Provided is a mechanism to make development work for adding a new ability to a device more efficient. Also provided is a device having superior expandability and having a mechanism that can simply add a new ability, said new ability being supplied from outside. This expandability retention device has, as an architecture for additionally installing a new ability in a basic structure of an own device, an architecture that is modeled by an ability acquisition model, said ability acquisition model including an ability unit that implements an ability, a data input unit that is an input interface of said ability unit, and a data output unit that is an output interface of said ability unit. The expandability retention device also has an ability setting unit that adds a new ability to the own device by setting respective functions for the ability unit, the data input unit, and the data output unit on the basis of ability imparting data, said ability imparting data including ability setting data, input setting data, and output setting data.

traducir

模糊概念格的种更新生成方法

NºPublicación: CN109086381A 25/12/2018

Solicitante:

\u90D1\u5DDE\u5927\u5B66,
\u9EC4\u6CB3\u6C34\u5229\u804C\u4E1A\u6280\u672F\u5B66\u9662

Resumen de: CN109086381A

本发明涉及完备模糊形式概念格的生成方法,具体涉及种关于模糊概念的基于集成技术的模糊概念的格更新方法。其利用两个模糊概念格之间的集成的技术方案,解决由于数据集更新而导致的‑模糊概念格更新问题。本发明不需要从更新后的数据集重新生成完备‑模糊概念格,而且新模糊概念格生成过程中使用更新前的原始模糊概念格,避免了资源浪费,从而改善了‑模糊概念格的更新效率。使用本发明由于避免重新从更新后的形式背景重生成模糊概念格,而是使用更新数据对原始模糊概念格进行更新操作,故更新效率大幅度提高。尤其对于稀疏数据集、小真值度集合的情况下,更新效率明显提高。

traducir

种基于模糊综合层次分析的弃渣场安全评价方法

NºPublicación: CN109034619A 18/12/2018

Solicitante:

\u957F\u6C5F\u52D8\u6D4B\u89C4\u5212\u8BBE\u8BA1\u7814\u7A76\u6709\u9650\u8D23\u4EFB\u516C\u53F8

Resumen de: CN109034619A

本发明提供种基于模糊综合层次分析的弃渣场安全评价方法,包括以下步骤:步骤A:调查和总结弃渣场安全的主要影响因子,建立层次结构模型;步骤B:根据层次结构模型,分别建立因子集和权重集,采用9标度法计算因子评价指标的权重;步骤C:根据水土保持设计与施工实践经验,建立评价等级集;步骤D:确定各影响因子评价指标隶属函数及模糊评价矩阵;步骤E:依据层次分析结果,结合评价等级集,综合评价弃渣场安全性。本发明基于模糊理论和层析分析理论,结合设计和施工实践经验,定性与定量相结合的评价弃渣场安全性,评价结果合理可靠,具有定的创新性,且本发明操作简单,易于实际应用,为弃渣场安全性评价提供了种新的方法和思路。

traducir

信息反馈RBF网络估值的不完整数据模糊聚类方法

NºPublicación: CN109034231A 18/12/2018

Solicitante:

\u8FBD\u5B81\u5927\u5B66

Resumen de: CN109034231A

本发明涉及种信息反馈RBF网络估值的不完整数据模糊聚类方法,步骤如下:1)提出信息反馈RBF网络模型;2),提出种信息反馈RBF数值型估值的不完整数据模糊聚类方法(IFRBF‑FCM);3)利用最近邻规则为不完整数据样本选取相应的训练样本集,利用最近邻训练样本集为每个缺失属性训练IFRBF网络,从而实现对不完整数据样本中缺失属性的估值预测,得到IFRBF网络估值恢复后的完整数据集;4)对不完整数据属性的估值区间进行确定,提出了种IFRBF区间型估值的不完整数据模糊聚类方法(IFRBF‑IFCM),得到模糊聚类结果。本发明采用IFRBF网络对不完整数据集进行估值得到的恢复完整的数据集的聚类结果与对比方法相比提高了准确率,比数值型估值的聚类结果更准确,鲁棒性也更好。

traducir

SCALABLE COMPUTING SYSTEMS AND METHODS FOR INTELLECTUAL PROPERTY RIGHTS AND ROYALTY MANAGEMENT

Nº publicación: US2018357734A1 13/12/2018

Solicitante:

OLE MEDIA MAN GP INC [CA]

CA_3008155_A1

Resumen de: US2018357734A1

Scalable computing systems and methods for the management of intellectual property assets and royalty payments. Income can be derived from a number of different sources in association with intellectual property assets. The data from these sources can be conformed into a common format to facilitate the management of intellectual property assets and royalty payments. Intellectual property assets can be organized into deals and can be stored in a database. The deals can also include parameters such as rate tables, rights holders associated with the assets of the deal. With the conformed data, the asset listings in the statements can be matched to the assets in the database. The matching can be done automatically, using fuzzy matching or manually if the automatic or fuzzy matching fails to produce a match. The royalties can then be calculated in parallel for all rights holders of a given asset across all jurisdictions using a dynamic flow network created for particular asset deal relationships.

traducir

Página1 de 5 nextPage por página

punteroimgVolver