会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明申请
    • Engineering design system using human interactive evaluation
    • 工程设计系统采用人工互动评估
    • US20060225003A1
    • 2006-10-05
    • US11099786
    • 2005-04-05
    • Alice AgoginoRaffi KamalianHideyuki Takagi
    • Alice AgoginoRaffi KamalianHideyuki Takagi
    • G06F17/50
    • G06F17/50
    • A design system includes a design engine for generating designs, an evaluation process for evaluating the generated designs based on human visual inspection and/or domain knowledge, and an optimization process for pruning based at least in part on the evaluation. Generation of additional designs is performed based on optimization. Newly-generated designs are then subjected to the same iterative steps. In one embodiment a simulator is also used to evaluate the generated designs, in part, with numerically designed specification. Subjective human evaluation is used fully or at least in part of an optimization process to obtain final designs. Human visual inspection and domain knowledge is used to evaluate and rate key designs at different points in the evolution of a design.
    • 设计系统包括用于生成设计的设计引擎,用于基于人类视觉检查和/或域知识来评估生成的设计的评估过程,以及至少部分地基于评估的修剪优化过程。 基于优化执行附加设计的生成。 然后对新生成的设计进行相同的迭代步骤。 在一个实施例中,模拟器也用于部分地通过数字设计的规范来评估所生成的设计。 完全或至少部分优化过程使用主观人类评估,以获得最终设计。 人类视觉检测和领域知识用于评估和评估设计演变过程中不同点的关键设计。
    • 6. 再颁专利
    • Inference rule determining method and inference device
    • 推理规则确定方法和推理装置
    • USRE36823E
    • 2000-08-15
    • US542852
    • 1995-10-13
    • Hideyuki TakagiIsao Hayashi
    • Hideyuki TakagiIsao Hayashi
    • G05B13/02G06N5/04G06N7/04G05B13/00
    • G06N7/046G05B13/0285G06N5/048
    • An inference rule determining process according to the present invention sequentially determines, using a learning function of a neural network model, a membership function representing a degree which the conditions of the IF part of each inference rule is satisfied when input data is received to thereby obtain an optimal inference result without using experience rules. The inventive inference device uses an inference rule of the type "IF . . . THEN . . ." and includes a membership value determiner (1) which includes all of IF part and has a neural network; individual inference quantity determiners (21)-(2r) which correspond to the respective THEN parts of the inference rules and determine the corresponding inference quantities for the inference rules; and a final inference quantity determiner which determines these inference quantities synthetically to obtain the final results of the inference. If the individual inference quantity determiners (2) each has a neural network structure, the non-linearity of the neural network models is used to obtain the result of the inference with high inference accuracy even if in object to be inferred is non-linear.
    • 根据本发明的推理规则确定过程顺序地确定使用神经网络模型的学习功能,表示在接收到输入数据时满足每个推理规则的IF部分的条件的程度的隶属函数,从而获得 没有使用经验规则的最佳推理结果。 本发明的推理装置使用类型“IF ... THEN ...”的推理规则。 并且包括隶属值确定器(1),其包括所有的IF部分并具有神经网络; 单个推理量确定器(21) - (2r),其对应于推理规则的相应THEN部分并且确定推理规则的相应推理量; 以及最终推理量确定器,其合成地确定这些推理量以获得推断的最终结果。 如果个体推理量确定器(2)各具有神经网络结构,则即使在被推断的对象是非线性的,也使用神经网络模型的非线性度来获得具有高推理精度的推理结果。
    • 7. 发明授权
    • Proportion predicting system and method of making mixture
    • 比例预测系统和混合方法
    • US6081796A
    • 2000-06-27
    • US875399
    • 1997-11-07
    • Hideyuki TakagiEiji MizutaniDavid M. Auslander
    • Hideyuki TakagiEiji MizutaniDavid M. Auslander
    • G01J3/46G06N3/08G06N3/12G06F15/00G06F7/00
    • G06N3/126G01J3/46G01J3/463G06N3/086
    • A proportion predicting system for realizing a predetermined target by mixing a predetermined number of elements at a predetermined proportion. The system includes a target characteristic extractor for extracting a characteristic of the predetermined target; an evaluating means operable upon receipt of proportion vectors, which are represented by the characteristic of the predetermined target and the quantity of each of the elements, respectively, to determine fitnesses of the proportion vectors based on the extracted characteristic of the predetermined target; and a GA processor for predicting the proportion vectors on the basis of the fitnesses according to a genetic algorithm in which the quantity of each of the elements and each of the proportion vectors are represented by a gene and a chromosome, respectively. The proportion vectors, which have been predicted by the GA processor, are inputted to the evaluating means to cause the evaluating means to repeat evaluation of the proportion vectors to determine optimum proportion vectors.
    • PCT No.PCT / US95 / 00972 Sec。 371日期:1997年11月7日 102(e)1997年11月7日日期PCT 1995年1月31日PCT PCT。 公开号WO96 / 24033 日期:1996年8月8日通过以预定比例混合预定数量的元素来实现预定目标的比例预测系统。 该系统包括用于提取预定目标的特征的目标特征提取器; 评估装置,在接收到由所述预定目标的特征和每个元素的数量分别表示的比例向量时可操作,以基于所提取的预定目标的特征来确定比例向量的适应度; 以及GA处理器,用于根据遗传算法基于适应度来预测比例向量,其中每个元素的量和每个比例向量的数量分别由基因和染色体表示。 已经由GA处理器预测的比例向量被输入到评估装置,以使得评估装置重复评估比例向量以确定最佳比例向量。