公开(公告)号：US20140372623A1

公开(公告)日：2014-12-18

申请号：US14023304

申请日：2013-09-10

申请人： Microsoft Corporation

发明人： Mingyu Chen ,  Adriana Dumitras ,  Mattias Nilsson ,  Renat Vafin ,  Christoffer Asgaard Rödbro

IPC分类号： H04L29/06

CPC分类号： H04L65/4092 ,  H04L1/0002 ,  H04L43/0829 ,  H04L43/0852 ,  H04L43/0894 ,  H04L47/11 ,  H04L47/2416 ,  H04L47/25 ,  H04L47/263 ,  H04L47/30 ,  H04L65/604 ,  H04L65/608 ,  H04L65/80 ,  H04L69/24 ,  H04W28/22

摘要： There is provided a method of controlling a rate at which content data is received at a receiver over a network, wherein the receiver has caused a first stream of real-time communication event data to be received at the receiver, and a second stream of content data to be received at the receiver, the method comprising steps of: dynamically measuring network conditions of the network based on the real-time communication event data; and limiting the rate at which the content data is received at the receiver based on the dynamically measured network conditions.

摘要翻译： 提供了一种控制通过网络在接收机处接收内容数据的速率的方法，其中接收器已经使得在接收机处接收到第一实时通信事件数据流，并且第二内容流 在接收机处要接收的数据，该方法包括以下步骤：基于实时通信事件数据动态地测量网络的网络状况; 并且基于动态测量的网络条件限制在接收机处接收内容数据的速率。

公开(公告)号：US20150248765A1

公开(公告)日：2015-09-03

申请号：US14193079

申请日：2014-02-28

申请人： Microsoft Corporation

发明人： Antonio Criminisi ,  Duncan Paul Robertson ,  Peter Kontschieder ,  Pushmeet Kohli ,  Henrik Turbell ,  Adriana Dumitras ,  Indeera Munasinghe ,  Jamie Daniel Joseph Shotton

IPC分类号： G06T7/00

CPC分类号： G06T7/50 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20072 ,  G06T2207/20081

摘要： A method of sensing depth using an RGB camera. In an example method, a color image of a scene is received from an RGB camera. The color image is applied to a trained machine learning component which uses features of the image elements to assign all or some of the image elements a depth value which represents the distance between the surface depicted by the image element and the RGB camera. In various examples, the machine learning component comprises one or more entangled geodesic random decision forests.

摘要翻译： 使用RGB相机感测深度的方法。 在示例方法中，从RGB相机接收场景的彩色图像。 将彩色图像应用于训练有素的机器学习部件，其使用图像元素的特征来分配全部或部分图像元素，该深度值表示由图像元素和RGB相机所描绘的表面之间的距离。 在各种示例中，机器学习部件包括一个或多个缠结测地线随机决策树。

公开(公告)号：US20140273990A1

公开(公告)日：2014-09-18

申请号：US13828721

申请日：2013-03-14

申请人： Microsoft Corporation

发明人： Christoffer Asgaard Rödbro ,  Mingyu Chen ,  Adriana Dumitras ,  Jonathan David Rosenberg

IPC分类号： H04W76/02

CPC分类号： H04W76/14 ,  H04W28/20

摘要： Observation assisted bandwidth management techniques are described. In one or more implementations, a request is received at a terminal to initiate a call with another terminal. Responsive to the request, a communication is formed to be communicated to a service provider for bandwidth parameters, the request including network parameters associated with the terminal. The bandwidth parameters, received form the service provider, are used as part of a model to estimate an amount of bandwidth that is available for the call. The call with the other terminal is initiated, the call configured to at least initially consume the estimated amount of bandwidth.

摘要翻译： 描述了观察辅助带宽管理技术。 在一个或多个实现中，在终端处接收到请求以与另一终端发起呼叫。 响应于该请求，形成通信以向服务提供商传送带宽参数，该请求包括与终端相关联的网络参数。 从服务提供商接收的带宽参数被用作模型的一部分，以估计可用于该呼叫的带宽量。 启动与另一终端的呼叫，该呼叫被配置为至少最初消耗估计的带宽量。

公开(公告)号：US20150142702A1

公开(公告)日：2015-05-21

申请号：US14199752

申请日：2014-03-06

申请人： Microsoft Corporation

发明人： Mattias Nilsson ,  Ando Saabas ,  Renat Vafin ,  Markus Vaalgamaa ,  Adriana Dumitras ,  Teele Tamme ,  Andre Veski

IPC分类号： G06N5/04 ,  G06N99/00 ,  H04M3/22

CPC分类号： G06N5/048 ,  G06K9/6218 ,  G06N99/005 ,  H04L41/00 ,  H04L41/5025 ,  H04L41/5067 ,  H04L41/509 ,  H04L65/00 ,  H04L65/1069 ,  H04L65/4069 ,  H04L65/607 ,  H04L65/80 ,  H04M3/2227

摘要： The disclosure relates to a communication client application for running on a user terminal to conduct calls over a network. The client is configured to access a model which models quality of user experience for calls based on a set of technical parameters of each call. The model itself is based on user feedback indicating subjective quality of multiple past calls as experienced by multiple users, modeled with respect to the technical parameters collected from each of the past calls. The model generates a predicted call quality score predicting the quality of user experience for the call given its technical parameters. Based on this process, one or more of the technical parameters of the call can be adapted to try to increase the quality experienced by the user.

摘要翻译： 本公开涉及一种用于在用户终端上运行以通过网络进行呼叫的通信客户端应用。 客户端被配置为基于每个呼叫的一组技术参数来访问对呼叫的用户体验质量进行建模的模型。 模型本身是基于用户反馈，指示由多个用户经历的多个过去呼叫的主观质量，关于从每个过去呼叫收集的技术参数进行建模。 该模型产生预测的呼叫质量得分，根据其技术参数预测用户体验的质量。 基于该过程，可以调用呼叫的一个或多个技术参数来尝试增加用户所经历的质量。