中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

54 records (took 0.02 seconds)

    Multi-layer information fusing for prediction
    1.
    发明授权
    Multi-layer information fusing for prediction 有权

    公开(公告)号：US10679143B2

    公开(公告)日：2020-06-09

    申请号：US15200509

    申请日：2016-07-01

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Wei Shan Dong ,  Peng Gao ,  Chang Sheng Li ,  Chun Yang Ma ,  Junchi Yan ,  Ren Jie Yao

    IPC: G06N20/00

    Abstract: A method of generating a predictor to classify data includes: training each of a plurality of first classifiers arranged in a first level on current training data; operating each classifier of the first level on the training data to generate a plurality of predictions; combining the current training data with the predictions to generated new training data; and training each of a plurality of second classifiers arranged in a second level on the new training data. The first classifiers are classifiers of different classifier types, respectively and the second classifiers are classifiers of the different classifier types, respectively.

    SCALABLE STREAMING DECISION TREE LEARNING
    3.
    发明申请
    SCALABLE STREAMING DECISION TREE LEARNING 审中-公开
    可定量流动决策树的学习

    公开(公告)号：US20170061327A1

    公开(公告)日：2017-03-02

    申请号：US14953457

    申请日：2015-11-30

    Applicant: International Business Machines Corporation

    Inventor： Wei Shan Dong ,  Peng Gao ,  Guo Qiang Hu ,  Chang Sheng LI ,  Xu Liang Li ,  Chun Yang Ma ,  Zhi Wang ,  Xin Zhang

    IPC: G06N99/00 ,  G06N5/02

    CPC classification number: G06N5/02 ,  G06N5/025

    Abstract: In one embodiment, a computer-implemented method includes receiving training data including a plurality of records, each record having a plurality of attributes. The training data is horizontally parallelized across two or more processing elements. This horizontal parallelizing includes dividing the training data into two or more subsets of records; assigning each subset of records to a corresponding processing element of the two or more processing elements; transmitting each subset of records to its assigned processing element; and sorting, at the two or more processing elements, the two or more subsets of records to two or more candidate leaves of a decision tree. The output from horizontally parallelizing is converted into input for vertically parallelizing the training data. The training data is vertically parallelized across the two or more processing elements. The decision tree is grown based at least in part on the horizontally parallelizing, the converting, and the vertically parallelizing.

    Abstract translation: 在一个实施例中，计算机实现的方法包括接收包括多个记录的训练数据，每个记录具有多个属性。 训练数据在两个或多个处理元件之间水平并行化。 这种水平并行化包括将训练数据分成两个或更多个记录子集; 将每个记录子集分配给所述两个或多个处理元件的相应处理元件; 将每个记录子集传送到其分配的处理元件; 并且在所述两个或更多个处理元素处将所述两个或多个记录子集分类到决策树的两个或更多个候选叶。 水平并行化的输出被转换为用于垂直并行化训练数据的输入。 训练数据跨越两个或多个处理元件垂直并行化。 决策树至少部分地基于水平并行化，转换和垂直并行化生长。

    SCALABLE STREAMING DECISION TREE LEARNING
    4.
    发明申请
    SCALABLE STREAMING DECISION TREE LEARNING 审中-公开

    公开(公告)号：US20170061318A1

    公开(公告)日：2017-03-02

    申请号：US14833397

    申请日：2015-08-24

    Applicant: International Business Machines Corporation

    Inventor： Wei Shan Dong ,  Peng Gao ,  Guo Qiang Hu ,  Cheng Sheng LI ,  Xu Liang Li ,  Chun Yang Ma ,  Zhi Wang ,  Xin Zhang

    IPC: G06N99/00

    Abstract: In one embodiment, a computer-implemented method includes receiving training data including a plurality of records, each record having a plurality of attributes. The training data is horizontally parallelized across two or more processing elements. This horizontal parallelizing includes dividing the training data into two or more subsets of records; assigning each subset of records to a corresponding processing element of the two or more processing elements; transmitting each subset of records to its assigned processing element; and sorting, at the two or more processing elements, the two or more subsets of records to two or more candidate leaves of a decision tree. The output from horizontally parallelizing is converted into input for vertically parallelizing the training data. The training data is vertically parallelized across the two or more processing elements. The decision tree is grown based at least in part on the horizontally parallelizing, the converting, and the vertically parallelizing.

    DETERMINING A LOCATION OF A MOBILE DEVICE
    5.
    发明申请
    DETERMINING A LOCATION OF A MOBILE DEVICE 审中-公开
    确定移动设备的位置

    公开(公告)号：US20170013522A1

    公开(公告)日：2017-01-12

    申请号：US15273751

    申请日：2016-09-23

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Heng Cao ,  Wei Shan Dong ,  Chun Yang Ma ,  Ju Wei Shi ,  Chun Hua Tian ,  Yu Wang ,  Chao Zhang

    IPC: H04W36/00 ,  H04W36/32 ,  H04W64/00

    CPC classification number: H04W36/0094 ,  G01S5/0278 ,  H04M3/2218 ,  H04W36/0083 ,  H04W36/32 ,  H04W64/00 ,  H04W64/006

    Abstract: A method and an apparatus for determining a location of a mobile device. The location of a mobile device is determined accurately according to information which includes call data records of the mobile device. By employing a partial ellipse integral model, two physical world factors are taken into consideration in reducing the location uncertainty in call data records. The factors include: spatiotemporal constraints of the device's movement in the physical world and the telecommunication cell area's geometry information, which increase the accuracy of determining the location of a mobile device.

    Abstract translation: 一种用于确定移动设备的位置的方法和装置。 根据包括移动设备的呼叫数据记录的信息，准确地确定移动设备的位置。 通过采用部分椭圆积分模型，在减少呼叫数据记录中的位置不确定性时考虑了两个物理世界因素。 这些因素包括：物理世界中设备移动的时空约束和电信单元区域的几何信息，这增加了确定移动设备位置的准确性。

    Vehicle domain multi-level parallel buffering and context-based streaming data pre-processing system
    6.
    发明授权
    Vehicle domain multi-level parallel buffering and context-based streaming data pre-processing system 有权
    车载多级并行缓冲和基于上下文的流数据预处理系统

    公开(公告)号：US09537914B1

    公开(公告)日：2017-01-03

    申请号：US14955218

    申请日：2015-12-01

    Applicant: International Business Machines Corporation

    Inventor： Wei Shan Dong ,  Ning Duan ,  Peng Gao ,  Chang Sheng Li ,  Chun Yang Ma ,  Xin Zhang ,  Jun Zhu

    IPC: G06F15/16 ,  H04L29/06 ,  H04L12/861

    CPC classification number: H04L65/4069 ,  G06F9/4881 ,  G08G1/0112 ,  H04L67/12

    Abstract: A vehicle domain multi-level parallel buffering and context-based streaming data pre-processing system includes a first data processing level and a second data processing level. The first data processing level includes a first-level buffer configured to buffer data provided from a plurality of raw data streams output from a plurality of vehicles. The second data processing level includes an electronic task-queue-dictionary (TQD) module and a plurality of second-level data processing buffers. The TQD module is configured to create a plurality of tasks in response to receiving a serial data stream output from the first-level buffer. The TQD module is further configured to assign each task to a corresponding second-level buffer, and separate the serial data stream into individual data values that are delivered to a specific second-level buffer based on the task so as to generate a multi-level parallel context-based buffering operation.

    Abstract translation: 车载域多级并行缓冲和基于上下文的流数据预处理系统包括第一数据处理级和第二数据处理级。 第一数据处理级包括被配置为缓冲从多个车辆输出的多个原始数据流提供的数据的第一级缓冲器。 第二数据处理级包括电子任务队列字典（TQD）模块和多个第二级数据处理缓冲器。 TQD模块被配置为响应于接收从第一级缓冲器输出的串行数据流而创建多个任务。 TQD模块还被配置为将每个任务分配给相应的二级缓冲器，并且将串行数据流分离成基于该任务传送到特定二级缓冲器的单独数据值，以便生成多级 并行上下文缓冲操作。

    Method and apparatus of road location inference for moving object
    7.
    发明授权
    Method and apparatus of road location inference for moving object 有权
    运动物体道路位置推理方法与装置

    公开(公告)号：US09494694B1

    公开(公告)日：2016-11-15

    申请号：US14963409

    申请日：2015-12-09

    Applicant: International Business Machines Corporation

    Inventor： Wei Shan Dong ,  Ning Duan ,  Peng Gao ,  Chun Yang Ma ,  Zhi Hu Wang ,  Xin Zhang

    IPC: G01S19/42 ,  G01S19/43 ,  G01S19/52

    CPC classification number: G01S19/50 ,  G01C21/30 ,  G01S19/39

    Abstract: A method and apparatus of location sequence inferences for moving objects traveling along a path. The method and apparatus primarily concerns determining the location of a moving vehicle on a roadway in a roadway network. The inputs to the system include: raw GPS tracking sequence with timestamp, trajectory of the moving object inferred by map matching, accurate speed sequence from a reliable device, e.g. OBD (On-Board Diagnostics is an automotive term referring to a vehicle's self-diagnostic and reporting capability), historical map matching results and historical locations sequence inference results. The output of the system is a sequence of more accurate location (on road segments) sequences than raw GPS locations and map matching results.

    Abstract translation: 一种用于沿着路径行进的移动物体的位置序列推断的方法和装置。 该方法和设备主要涉及确定移动车辆在道路网中的道路上的位置。 系统的输入包括：具有时间戳的原始GPS跟踪序列，通过地图匹配推断的移动物体的轨迹，来自可靠设备的准确速度序列，例如。 OBD（车载诊断是汽车术语，指车辆的自我诊断和报告功能），历史地图匹配结果和历史位置序列推断结果。 系统的输出是比原始GPS位置更精确的位置（在路段上）序列的序列，并且映射匹配结果。

Patent Agency Ranking