利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

82 条记录 (耗时 0.016 秒)

    PROBABILISTIC CLASSIFIER MAXIMUM CERTAINTY FACTOR CORRECTION
    65.
    发明公开
    PROBABILISTIC CLASSIFIER MAXIMUM CERTAINTY FACTOR CORRECTION 审中-公开

    公开(公告)号：EP4099204A1

    公开(公告)日：2022-12-07

    申请号：EP22162660.9

    申请日：2022-03-17

    申请人： FUJITSU LIMITED

    发明人： MAEDA, Wakana

    IPC分类号： G06F21/62 ,  G06N7/02 ,  G06N20/00 ,  G06N7/00

    摘要： An information processing program that causes at least one computer to execute a process, the process includes acquiring each of a plurality of certainty factors representing a possibility that classification target data belongs to a class of a plurality of classes for each of the plurality of classes by using a trained model; determining whether a maximum certainty factor having a maximum value among the plurality of certainty factors of the plurality of classes is within a certain value range; correcting a value of the maximum certainty factor to a value within the certain value range when the maximum certainty factor is not within the certain value range; and outputting the plurality of certainty factors after the correcting as a result of class classification for the classification target data.

    SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR MACHINE-LEARNING-BASED TRAFFIC PREDICTION
    67.
    发明公开
    SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR MACHINE-LEARNING-BASED TRAFFIC PREDICTION 审中-公开

    公开(公告)号：EP3825654A1

    公开(公告)日：2021-05-26

    申请号：EP20212822.9

    申请日：2018-06-21

    申请人： Visa International Service Association

    发明人： SESHADRI, Madhavan

    IPC分类号： G01C21/34 ,  G06N20/00 ,  G06N5/04 ,  G06N7/02 ,  G06Q30/06 ,  G06Q30/02 ,  G01C21/36

    摘要： Described are a system, method, and computer program product for machine-learning-based traffic prediction. The method includes receiving at least one message associated with at least one transaction between at least one consumer and at least one point-of-sale terminal in a region. The method also includes identifying, based on the at least one message, at least one geographic node of activity in the region comprising the at least one point-of-sale terminal. The method further includes generating, based at least partially on a transportation categorization of the at least one consumer, an estimate of traffic intensity for the at least one geographic node of activity. The method also includes comparing the estimate of traffic intensity for the at least one geographic node of activity to a threshold of traffic intensity. In response to determining that the estimate of traffic intensity for the at least one geographic node of activity satisfies the threshold, the method includes generating, a communication to at least one navigation device configured to cause the at least one navigation device to modify a navigation route and communicating the communication to the at least one navigation device.

    MACHINE LEARNING DATA FEATURE REDUCTION AND MODEL OPTIMIZATION
    68.
    发明公开
    MACHINE LEARNING DATA FEATURE REDUCTION AND MODEL OPTIMIZATION 审中-公开

    公开(公告)号：EP3822869A2

    公开(公告)日：2021-05-19

    申请号：EP20207070.2

    申请日：2020-11-12

    申请人： Rockwell Automation Technologies, Inc.

    发明人： MATURANA, Francisco P. ,  LACASSE, Phillip

    IPC分类号： G06N7/02 ,  G06N20/00

    摘要： For machine learning data reduction and model optimization a method randomly assigns each data feature of a training data set to a plurality of solution groups. Each solution group has no more than a solution group number k of data features and each data feature is assigned to a plurality of solution groups. The method identifies each solution group as a high-quality solution group or a low-quality solution group. The method further calculates data feature scores for each data feature comprising a high bin number and a low bin number. The method determines level data for each data feature from the data feature scores using a fuzzy inference system. The method identifies an optimized data feature set based on the level data. The method further trains a production model using only the optimized data feature set. The method predicts a result using the production model.