知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

86 条记录 (耗时 0.036 秒)

    COGNITIVE ASSISTANT FOR AIDING EXPERT DECISION
    71.
    发明申请
    COGNITIVE ASSISTANT FOR AIDING EXPERT DECISION 审中-公开

    公开(公告)号：US20200082940A1

    公开(公告)日：2020-03-12

    申请号：US16126559

    申请日：2018-09-10

    申请人： International Business Machines Corporation

    发明人： Mu Qiao ,  Dylan Fitzpatrick ,  Ramani Routray ,  Divyesh Jadav

    IPC分类号： G16H50/20 ,  G16H10/60 ,  G06N20/00 ,  G06N5/04

    摘要： Intelligent cognitive assistants for decision-making are provided. A first plurality of decisions made by a first healthcare provider during treatment of a first patient is monitored. For each respective decision of the first plurality of decisions, one or more corresponding medical attributes of the first patient that were present at a time when the respective decision was made are determined. A cognitive assistant is trained, using an imitation learning model, based on each of the first plurality of decisions and the corresponding one or more medical attributes of the first patient. Subsequently, one or more medical attributes of a second patient are received, and a first medical decision is generated by processing the one or more medical attributes of the second patient using the cognitive assistant.

    ACTIVE IMITATION LEARNING IN HIGH DIMENSIONAL CONTINUOUS ENVIRONMENTS
    72.
    发明申请
    ACTIVE IMITATION LEARNING IN HIGH DIMENSIONAL CONTINUOUS ENVIRONMENTS 审中-公开

    公开(公告)号：US20200082257A1

    公开(公告)日：2020-03-12

    申请号：US16124138

    申请日：2018-09-06

    申请人： International Business Machines Corporation

    发明人： Mu Qiao ,  Dylan J. Fitzpatrick ,  Divyesh Jadav

    IPC分类号： G06N3/08 ,  G06N3/04

    摘要： According to one embodiment, a computer-implemented method for active, imitation learning, includes: providing training data comprising an expert trajectory to a processor; querying the expert trajectory during an iterative, active learning process; generating a decision policy based at least in part on the expert trajectory and a result of querying the expert trajectory; attempting to distinguish the decision policy from the expert trajectory; in response to distinguishing the decision policy from the expert trajectory, outputting a policy update and generating a new decision policy based at least in part on the policy update; and in response to not distinguishing the decision policy from the expert trajectory, outputting the decision policy. Importantly, the expert trajectory is queried for only a subset of iterations of the iterative, active learning process, wherein the most uncertain state/action pair(s) from the expert trajectory are determined using one or more disagreement functions.

    Identification of volumes for thin provisioning
    73.
    发明授权
    Identification of volumes for thin provisioning 有权

    公开(公告)号：US10552076B2

    公开(公告)日：2020-02-04

    申请号：US15377614

    申请日：2016-12-13

    申请人： International Business Machines Corporation

    发明人： Mirza S. Baig ,  Paul Lawrence Bradshaw ,  Divyesh Jadav ,  Bryan Steward Langston ,  Nagapramod S. Mandagere ,  Aameek Singh

    IPC分类号： G06F3/06

    摘要： One embodiment provides a method, including: generating, for each of a plurality of storage volumes, an actual used storage capacity model and identifying a potential storage capacity savings using the actual used capacity model, wherein each of the plurality of storage volumes has been identified as a candidate for migration to a thin provisioned volume; generating, for each of the plurality of storage volumes, an input/output profile model and identifying a potential change in performance of an application accessing the storage volume using the input/output profile model; generating, for each of the plurality of storage volumes, a growth profile and identifying a potential change in capacity using the growth profile; and determining, using an optimization algorithm, a subset of the plurality of storage volumes to be migrated to thin provisioned volumes based upon the volume capacity model, the performance model, and the volume growth profile.

    DRONE AIR TRAFFIC CONTROL AND FLIGHT PLAN MANAGEMENT
    74.
    发明申请
    DRONE AIR TRAFFIC CONTROL AND FLIGHT PLAN MANAGEMENT 审中-公开

    公开(公告)号：US20200035111A1

    公开(公告)日：2020-01-30

    申请号：US16588920

    申请日：2019-09-30

    申请人： International Business Machines Corporation

    发明人： Eric K. Butler ,  Anca A. Chandra ,  Pawan R. Chowdhary ,  Susanne M. Glissmann-Hochstein ,  Thomas D. Griffin ,  Divyesh Jadav ,  Sunhwan Lee ,  Hovey R. Strong, JR.

    IPC分类号： G08G5/00

    摘要： One embodiment provides a method comprising receiving a flight plan request for a drone. The flight plan request comprises a drone identity, departure information, and arrival information. The method further comprises constructing a modified flight plan for the drone based on the flight plan request, wherein the modified flight plan represents an approved, congestion reducing, and executable flight plan for the drone, and the modified flight plan comprises a sequence of four-dimensional (4D) cells representing a planned flight path for the drone. For each 4D cell of the modified flight plan, the method further comprises attempting to place an exclusive lock on behalf of the drone on the 4D cell, and in response to a failure to place the exclusive lock on behalf of the drone on the 4D cell, rerouting the modified flight plan around the 4D cell to a random neighboring 4D cell.

    DRONE MANAGEMENT DATA STRUCTURE
    75.
    发明申请
    DRONE MANAGEMENT DATA STRUCTURE 审中-公开

    公开(公告)号：US20190355261A1

    公开(公告)日：2019-11-21

    申请号：US16427180

    申请日：2019-05-30

    申请人： International Business Machines Corporation

    发明人： Jeanette L. Blomberg ,  Eric K. Butler ,  Anca A. Chandra ,  Pawan R. Chowdhary ,  Thomas D. Griffin ,  Divyesh Jadav ,  Robert J. Moore ,  Hovey R. Strong, JR.

    IPC分类号： G08G5/00

    摘要： One embodiment provides a method comprising maintaining a multi-dimensional data structure partitioned into cells utilizing a tree data structure (“tree”) comprising intervals for each dimension of a multi-dimensional space. To partition an interval for a node of the tree into multiple subintervals, multiple leaf nodes (“leaves”) are generated, each leaf descending from the node. To merge multiple intervals for multiple nodes of the tree, a parent node (“parent”) and multiple leaves descending from the parent are generated, the parent and the leaves are time constrained, and the leaves are scheduled for a merger. When transient data in cells included in a list that corresponds to a leaf scheduled for merger expires, each cell in the list is converted into a cell for inclusion in a different list corresponding to a parent of the leaf, each leaf of the parent removed, and the parent turned into a leaf.