公开(公告)号：WO2008055020A1

公开(公告)日：2008-05-08

申请号：PCT/US2007/082052

申请日：2007-10-22

Applicant: MICROSOFT CORPORATION

Inventor： HECKERMAN, David E. ,  MUNDIE, Craig J. ,  JOJIC, Nebojsa ,  HINRICHS, Randy J.

IPC: G06Q50/00 ,  G06F17/00

CPC classification number: G06N99/005 ,  G06F19/00 ,  G06Q10/10 ,  G06Q50/22 ,  G16H50/20 ,  G16H50/70

Abstract: A tool for providing health and/or wellness services is described herein. Not necessarily clean or unclean data about a plurality of self-selected or non-selected or unselected subjects is received. The data can be aggregated and mined at least in part by employing a statistical algorithm, a data-mining algorithm and/or a machine-learning algorithm. The data can be further employed to provide health and/or wellness services to participants.

Abstract translation: 本文描述了用于提供健康和/或健康服务的工具。 不一定接收到关于多个自选或未选择的对象的干净或不洁净的数据。 数据可以至少部分地通过采用统计算法，数据挖掘算法和/或机器学习算法进行聚合和挖掘。 数据可以进一步用于向参与者提供健康和/或健康服务。

公开(公告)号：WO2009045819A2

公开(公告)日：2009-04-09

申请号：PCT/US2008/077572

申请日：2008-09-24

Applicant: MICROSOFT CORPORATION

Inventor： HORVITZ, Eric J. ,  BATHICHE, Steven ,  HECKERMAN, David E. ,  KARKANIAS, Chris Demetrios

IPC: A61B5/00 ,  C12N1/20 ,  C12N5/06 ,  A61B5/05

CPC classification number: A61B5/00 ,  A61B5/411 ,  A61B5/7264 ,  G06F19/28 ,  G16H50/20 ,  Y02A90/26

Abstract: Provided are systems and/or methods that facilitate sensing, detecting, or treatment of a condition or need of a living body using a genetically engineered symbiotic agent.

Abstract translation: 提供促进使用基因工程共生试剂感测，检测或治疗活体状况或需要的系统和/或方法。

公开(公告)号：WO2008157530A2

公开(公告)日：2008-12-24

申请号：PCT/US2008/067193

申请日：2008-06-17

Applicant: MICROSOFT CORPORATION

Inventor： KIROVSKI, Darko ,  HECKERMAN, David E. ,  JOJIC, Nebojsa

IPC: A61K39/12 ,  C12N7/04 ,  G06Q50/00

CPC classification number: G06F19/24 ,  A61K39/12 ,  A61K39/21 ,  C12N2740/16011 ,  G06F19/22 ,  G06F19/26

Abstract: Systems and methodologies for efficient vaccine design are disclosed herein. A methodology for efficient vaccine design in accordance with one or more embodiments disclosed herein may be operable to receive a graph having vertices corresponding to epitope sequences present in the pathogen population, weights for respective vertices corresponding to respective frequencies with which corresponding epitope sequences appear in the pathogen population, and directed edges that connect vertices that correspond to overlapping epitope sequences. Such a methodology may also be operable to determine a candidate vaccine sequence of overlapping epitope sequences by identifying a path though the graph corresponding to a series of connected vertices and directed edges that maximizes the total weight of the vertices in the path for a desired vaccine sequence length.

Abstract translation: 本文公开了用于高效疫苗设计的系统和方法。 根据本文公开的一个或多个实施例的有效疫苗设计的方法可以用于接收具有对应于病原体群体中存在的表位序列的顶点的图，对应于相应表位序列出现在其中的相应频率的各个顶点的权重 病原体群体以及连接对应于重叠表位序列的顶点的定向边缘。 这种方法还可以用于通过识别通过对应于一系列连接的顶点的图形的路径来确定重叠表位序列的候选疫苗序列和使所需疫苗序列的路径中的顶点的总重量最大化的有向边缘 长度。

公开(公告)号：EP2190348A2

公开(公告)日：2010-06-02

申请号：EP08835607.6

申请日：2008-09-24

Applicant: Microsoft Corporation

Inventor： HORVITZ, Eric J. ,  BATHICHE, Steven ,  HECKERMAN, David E. ,  KARKANIAS, Chris Demetrios

IPC: A61B5/00 ,  C12N1/20 ,  C12N5/06 ,  A61B5/05

CPC classification number: A61B5/00 ,  A61B5/411 ,  A61B5/7264 ,  G06F19/28 ,  G16H50/20 ,  Y02A90/26

Abstract: Provided are systems and/or methods that facilitate sensing, detecting, or treatment of a condition or need of a living body using a genetically engineered symbiotic agent.

公开(公告)号：EP1599781A2

公开(公告)日：2005-11-30

申请号：EP04714607.1

申请日：2004-02-25

Applicant: MICROSOFT CORPORATION

Inventor： ROUNTHWAITE, Robert L. ,  HECKERMAN, David E. ,  MEHR, John D. ,  HOWELL, Nathan D. ,  RUPERSBURG, Micah C. ,  SLAWSON, Dean A. ,  GOODMAN, Joshua T.

IPC: G06F1/00

CPC classification number: H04L51/12 ,  G06Q10/107

Abstract: The subject invention provides for a feedback loop system and method that facilitate classifying items in connection with spam prevention in server and/or client-based architectures. The invention makes uses of a machine-learning approach as applied to spam filters, and in particular, randomly samples incoming email messages so that examples of both legitimate and junk/spam mail are obtained to generate sets of training data. Users which are identified as spam-fighters are asked to vote on whether a selection of their incoming email messages is individually either legitimate mail or junk mail. A database stores the properties for each mail and voting transaction such as user information, message properties and content summary, and polling results for each message to generate training data for machine learning systems. The machine learning systems facilitate creating improved spam filter(s) that are trained to recognize both legitimate mail and spam mail and to distinguish between them.

Abstract translation: 本发明提供了一种反馈回路系统和方法，其有助于在服务器和/或基于客户端的体系结构中与垃圾邮件防止相关联的项目进行分类。 本发明利用机器学习方法应用于垃圾邮件过滤器，特别是随机抽取传入的电子邮件消息，以便获得合法和垃圾/垃圾邮件的示例以产生一组训练数据。 被要求被识别为垃圾邮件机的用户被要求对所接收的电子邮件的选择是否是合法邮件或垃圾邮件进行投票。 数据库存储每个邮件和投票交易的属性，例如用户信息，消息属性和内容摘要，以及每个消息的轮询结果以生成机器学习系统的训练数据。 机器学习系统便于创建改进的垃圾邮件过滤器，该过滤器被训练以识别合法邮件和垃圾邮件并区分它们。