利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

1211 条记录 (耗时 0.032 秒)

    COMPUTER-READABLE RECORDING MEDIUM, DETECTION METHOD, AND DETECTION DEVICE
    2.
    发明申请
    COMPUTER-READABLE RECORDING MEDIUM, DETECTION METHOD, AND DETECTION DEVICE 审中-公开

    公开(公告)号：US20190236407A1

    公开(公告)日：2019-08-01

    申请号：US16262974

    申请日：2019-01-31

    申请人： FUJITSU LIMITED

    发明人： Masaru TODORIKI ,  Yuhei UMEDA ,  Ken KOBAYASHI

    IPC分类号： G06K9/62 ,  G06K9/00

    CPC分类号： G06K9/6232 ,  G06K9/00523 ,  G06K9/00536

    摘要： A detection device adds, with regard to each of a plurality of sets of time-series data including a plurality of items, a time-shift term to at least any of the plurality of items included in each of the plurality of sets of time-series data. The detection device generates a plurality of attractors from the plurality of sets of time-series data to which the time-shift term has been added. The detection device generates a plurality of Betti sequences from each of the plurality of attractors by executing a persistent homology transformation on each of the plurality of attractors, each of the plurality of Betti sequences indicating a correspondence relationship between a Betti number and a scale value has been used for the persistent homology transformation. The detection device detects a state change in the plurality of sets of time-series data based on a time change in the plurality of Betti sequences.

    METHOD AND SYSTEM FOR EVENT PATTERN GUIDED MOBILE CONTENT SERVICES
    6.
    发明申请
    METHOD AND SYSTEM FOR EVENT PATTERN GUIDED MOBILE CONTENT SERVICES 审中-公开

    公开(公告)号：US20180288119A1

    公开(公告)日：2018-10-04

    申请号：US15524434

    申请日：2015-10-28

    申请人： INTERDIGITAL TECHNOLOGY CORPORATION

    发明人： Kuo-Chu Lee ,  Shoshana Loeb

    IPC分类号： H04L29/06 ,  H04L29/08 ,  G06K9/00

    CPC分类号： H04L65/4084 ,  G06K9/00536 ,  H04L67/125 ,  H04L67/22 ,  H04L67/38

    摘要： A method and system for event pattern (EP) guided content services are disclosed. A service entity may receive sensor events from a plurality of users, the sensor events corresponding to behavior data detected from the plurality of users, identify content creator candidates from among the plurality of users based on a pattern of events which correspond to sensor events received from an active user, select a content creator from among the content creator candidates based on a best match to the pattern of events, transmit a request for content of the selected content creator, deliver content created by the content creator to the active user, and monitor progress of the active user based on a playback of the content by the active user.

    ANALYSIS-DATA ANALYZING DEVICE AND ANALYSIS-DATA ANALYZING METHOD
    9.
    发明申请
    ANALYSIS-DATA ANALYZING DEVICE AND ANALYSIS-DATA ANALYZING METHOD 审中-公开

    公开(公告)号：US20180268293A1

    公开(公告)日：2018-09-20

    申请号：US15921107

    申请日：2018-03-14

    申请人： SHIMADZU CORPORATION

    发明人： Akira NODA

    IPC分类号： G06N3/08 ,  G06N5/04 ,  G06N7/08 ,  G06F17/18 ,  G06N3/04

    CPC分类号： G06N3/08 ,  G01N30/86 ,  G06F17/18 ,  G06K9/00536 ,  G06N3/0436 ,  G06N3/084 ,  G06N5/048 ,  G06N7/005 ,  G06N7/08 ,  G06N20/10

    摘要： Using training data, machine learning is performed to construct a learning model which is a non-linear function for discrimination or regression analysis (S2). A degree of contribution of each input dimension is calculated from a partial differential value of that function. Input dimensions to be invalidated are determined using a threshold defined by a Gaussian distribution function based on the degrees of contribution (S3-S5). Machine learning is once more performed using the training data with the partially-invalidated input dimensions (S6). A new value of the degree of contribution of each input dimension is determined from the obtained learning model, and the degree of contribution is updated using the old and new values (S7-S8). After the processes of Steps S5-S8 are iterated a specified number of times (S9), useful dimensions are determined based on the finally obtained degrees of contribution, and the machine-learning model is constructed (S10).