会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 51. 发明申请
    • APPARATUS AND METHOD FOR A DIGITAL MEDICAL ASSISTANT
    • 数字医疗助理的装置和方法
    • US20140278528A1
    • 2014-09-18
    • US13827238
    • 2013-03-14
    • Vikram SimhaGang LiSteven H. Sandy
    • Vikram SimhaGang LiSteven H. Sandy
    • G06F19/00
    • G06F19/328
    • A digital medical assistant is configured to obtain authorization of a service request. The assistant includes: an input for receiving an electronic medical record (EMR) of a patient and identity of a benefit provider for the patient; a preauthorization engine configured for completing an application by identifying relevant clinical context from the EMR and correlating the relevant clinical context with preauthorization criteria; the preauthorization engine further configured for submitting a completed application as the request to the benefit provider, receiving a decision from the provider, and outputting the decision. A method of use in a computer program product are provided.
    • 数字医疗助理被配置为获得服务请求的授权。 该助理包括:用于接收患者的电子病历(EMR)的输入和患者的益处提供者的身份; 配置用于通过从EMR识别相关临床上下文并将相关临床背景与预授权标准相关联来完成应用的预授权引擎; 所述预授权引擎还被配置为将所述完成的应用作为所述请求提交给所述受益提供者,从所述提供者接收决定,并输出所述决定。 提供了一种在计算机程序产品中的使用方法。
    • 57. 发明申请
    • EXPLOITING SPARSENESS IN TRAINING DEEP NEURAL NETWORKS
    • 培训深层神经网络中的开发空间
    • US20130138589A1
    • 2013-05-30
    • US13305741
    • 2011-11-28
    • Dong YuLi DengFrank Torsten Bernd SeideGang Li
    • Dong YuLi DengFrank Torsten Bernd SeideGang Li
    • G06N3/08
    • G06N3/08
    • Deep Neural Network (DNN) training technique embodiments are presented that train a DNN while exploiting the sparseness of non-zero hidden layer interconnection weight values. Generally, a fully connected DNN is initially trained by sweeping through a full training set a number of times. Then, for the most part, only the interconnections whose weight magnitudes exceed a minimum weight threshold are considered in further training. This minimum weight threshold can be established as a value that results in only a prescribed maximum number of interconnections being considered when setting interconnection weight values via an error back-propagation procedure during the training. It is noted that the continued DNN training tends to converge much faster than the initial training.
    • 提出了深层神经网络(DNN)训练技术实施例,其训练DNN,同时利用非零隐藏层互连权重值的稀疏性。 通常,完全连接的DNN最初通过遍历完整的训练集多次进行训练。 那么,在大多数情况下,只有重量大小超过最小重量阈值的互连在进一步的训练中被考虑。 该最小权重阈值可以被建立为在训练期间通过错误反向传播过程设置互连权重值时仅考虑规定的最大数量的互连的值。 值得注意的是,继续进行的DNN训练往往比初始训练快得多。
    • 59. 发明申请
    • MOTION ANALYSIS THROUGH GEOMETRY CORRECTION AND WARPING
    • 运动分析通过几何校正和加温
    • US20130070967A1
    • 2013-03-21
    • US13584887
    • 2012-08-14
    • Yakup GencGang LiClifford Hatcher
    • Yakup GencGang LiClifford Hatcher
    • G06K9/78
    • G06T7/20G06T2207/10016G06T2207/30164
    • An object in a hot atmosphere with a temperature greater than 400 F in a gas turbine moves in a 3D space. The movement may include a vibrational movement. The movement includes a rotational movement about an axis and a translational movement along the axis. Images of the object are recorded with a camera, which may be a high-speed camera. The object s provided with a pattern that is tracked in images. Warpings of sub-patches in a reference image of the object are determined to form standard format warped areas. The warpings are applied piece-wise to areas in following images to create corrected images. Standard tracking such as SSD tracking is applied to the piece-wise corrected images to determine a movement of the object. The image correction and object tracking are performed by a processor.
    • 在燃气轮机中温度高于400°F的热气氛中的物体在3D空间中移动。 运动可以包括振动运动。 运动包括围绕轴的旋转运动和沿着轴的平移运动。 用相机拍摄物体的图像,摄像机可能是高速摄像机。 对象被提供有在图像中跟踪的图案。 确定对象的参考图像中的子补丁的变形以形成标准格式的扭曲区域。 将经线分段应用于以下图像中的区域以产生校正图像。 诸如SSD跟踪的标准跟踪被应用于分段校正图像以确定对象的移动。 图像校正和对象跟踪由处理器执行。