中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

24 records (took 0.018 seconds)

    Input data correction
    1.
    发明授权
    Input data correction 有权

    公开(公告)号：US11119842B2

    公开(公告)日：2021-09-14

    申请号：US16681761

    申请日：2019-11-12

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Hung-Yang Chang ,  James V. Codella ,  Subhro Das

    IPC: G06F11/00 ,  G06F11/07 ,  G06F11/34 ,  G06F11/30 ,  G06N20/00 ,  G05B23/02

    Abstract: Technical solutions are described that address correcting input time-series data provided for analysis and predictions. An example computer-implemented method includes receiving, by a processor, a time-series data input by a user. The computer-implemented method also includes computing, by the processor, a first plurality of predicted values based on the time-series data input by the user; computing, by the processor, a second plurality of predicted values by. The computer-implemented method also includes determining estimated time-series data based on the time-series data input by the user. The computer-implemented method also includes computing the second plurality of predicted values based on the estimated time-series data. The computer-implemented method also includes determining, by the processor, a defect in the time-series data input by the user based on a distribution of a plurality of differences between respective values from the first plurality of predicted values and the second plurality of predicted values.

    CONTINUOUS PHYSIOLOGICAL SENSING IN ENERGY-CONSTRAINED WEARABLES
    2.
    发明申请
    CONTINUOUS PHYSIOLOGICAL SENSING IN ENERGY-CONSTRAINED WEARABLES 审中-公开

    公开(公告)号：US20190130076A1

    公开(公告)日：2019-05-02

    申请号：US15794329

    申请日：2017-10-26

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Hung-Yang Chang ,  Tian HAO ,  Xinxin ZHU

    IPC: G06F19/00 ,  G06Q10/10 ,  A61B5/00

    Abstract: Embodiments of the present invention are directed to physiological sensing in a wearable device. Aspects include generating a multi-faceted feedback for a user. Generating the multi-faceted feedback includes generating a baseline physiological sampling schedule for a user, generating a quality-aware feedback of the user, generating a user-state-aware feedback of the user, and generating a context-aware feedback of the user. Aspects also include generating an adjusted physiological sampling schedule for the user based at least in part upon the multi-faceted feedback.

    Computer-implemented method for recommending booths-to-visit
    7.
    发明授权
    Computer-implemented method for recommending booths-to-visit 有权

    公开(公告)号：US10393535B2

    公开(公告)日：2019-08-27

    申请号：US15799844

    申请日：2017-10-31

    Applicant: International Business Machines Corporation ,  Industry Technology Research Institute (ITRI)

    Inventor： Hung-Yang Chang ,  Li-Ju Chen ,  Chia-Wen Ho ,  Kuo-shu Luo ,  Yi-Chang Molly Wang

    IPC: G01C21/36 ,  G06Q30/02 ,  G06F16/9535

    Abstract: Disclosed is a computer-implemented method for recommending booths-to-visit to a user, comprising the following steps: accessing a user record, wherein the user record includes data indicative of booths which a user corresponding to the user record has visited in an exhibition; determining similarity level between records in a history database and the user record, the records in the history database including data indicative of the booths visited by previous visitors in the exhibition; selecting one of the records according to the determined similarity level; determining the booths in the selected record not yet visited by the user; obtaining the user's current location in the exhibition; determining a target booth, from the booths not yet visited by the user, by referring to the current location and a map database; and sending to the user a message indicative of the target booth.

    CONSTRAINT-AWARE HEALTH MANAGEMENT
    8.
    发明申请
    CONSTRAINT-AWARE HEALTH MANAGEMENT 审中-公开

    公开(公告)号：US20180314805A1

    公开(公告)日：2018-11-01

    申请号：US15497802

    申请日：2017-04-26

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Hung-Yang Chang ,  Ching-Hua Chen ,  Zhiguo Li ,  Kun Lin

    IPC: G06F19/00

    Abstract: Embodiments of technical solutions are described for a health management system that facilitates adaptively tracking a health-management goal. An example computer-implemented method includes receiving a cumulative target for a predetermined duration for a user, and generating a target activity time-series for the predetermined duration to meet the cumulative target. The method further includes receiving a user-activity time-series for the user that indicates activity performed by the user to meet the cumulative target and monitoring a difference between the target activity time-series and the user-activity time-series. The method further includes determining, based on the difference, a probability value that indicates the user missing the cumulative target, and generating an updated target activity time-series for the user in response to the probability value being above a predetermined threshold.

    INPUT DATA CORRECTION
    9.
    发明申请
    INPUT DATA CORRECTION 审中-公开

    公开(公告)号：US20180314573A1

    公开(公告)日：2018-11-01

    申请号：US15581869

    申请日：2017-04-28

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Hung-Yang Chang ,  James V. Codella ,  Subhro Das

    IPC: G06F11/07 ,  G06N99/00 ,  G06F11/34 ,  G06F11/30

    Abstract: Technical solutions are described that address correcting input time-series data provided for analysis and predictions. An example computer-implemented method includes receiving, by a processor, a time-series data input by a user. The computer-implemented method also includes computing, by the processor, a first plurality of predicted values based on the time-series data input by the user; computing, by the processor, a second plurality of predicted values by. The computer-implemented method also includes determining estimated time-series data based on the time-series data input by the user. The computer-implemented method also includes computing the second plurality of predicted values based on the estimated time-series data. The computer-implemented method also includes determining, by the processor, a defect in the time-series data input by the user based on a distribution of a plurality of differences between respective values from the first plurality of predicted values and the second plurality of predicted values.

Patent Agency Ranking