公开(公告)号：US20090234734A1

公开(公告)日：2009-09-17

申请号：US12049384

申请日：2008-03-17

申请人： Sreenivas Gollapudi ,  Frank McSherry ,  Rina Panigrahy ,  Kunal Talwar

发明人： Sreenivas Gollapudi ,  Frank McSherry ,  Rina Panigrahy ,  Kunal Talwar

IPC分类号： G06Q30/00 ,  G06F7/06

CPC分类号： G06Q30/08 ,  G06Q30/02 ,  G06Q30/0256

摘要： Advertising slots on a search engine results page may be determined based on keywords and/or results to a user query. Advertisers may use the keywords and/or the results to the query to place their ads into the advertising slots. Rules may be applied to determine how ads are displayed or not displayed. For example, a larger set of keywords may be inferred from the initial set of keywords on which the ad provider placed her bids. This greatly increases the potential reach of an advertiser's ad campaign or a search engine provider's revenue from ad placement.

摘要翻译： 搜索引擎结果页面上的广告位可以基于用户查询的关键字和/或结果来确定。 广告商可以使用查询的关键字和/或结果将广告投放到广告位。 可以应用规则来确定广告的显示方式或不显示。 例如，可以从广告提供商将其出价的关键字的初始集合推断出一组较大的关键字。 这大大增加了广告客户广告系列或搜索引擎提供商的广告展示位置的收入潜力。

公开(公告)号：US20090182797A1

公开(公告)日：2009-07-16

申请号：US11972618

申请日：2008-01-10

申请人： Cynthia Dwork ,  Frank McSherry ,  Kunal Talwar ,  Boaz Barak ,  Kamalika Chaudhuri ,  Satyen Kale

发明人： Cynthia Dwork ,  Frank McSherry ,  Kunal Talwar ,  Boaz Barak ,  Kamalika Chaudhuri ,  Satyen Kale

IPC分类号： G06F17/14 ,  G06F17/30

CPC分类号： G06F16/2465

摘要： Techniques for contingency table release provide an accurate and consistent set of tables while guaranteeing that privacy is preserved. A positive and integral database is constructed that corresponds to these tables. Therefore, a database can be generated that preserves low-order marginals up to a small error. Moreover, a gracefully degrading version of the results is provided as a database can be computed such that the error in the low-order marginals is small, and increases smoothly with the order of the marginal.

摘要翻译： 应急表释放技术提供准确一致的表格，同时确保保护隐私。 构建对应于这些表的正数和整数数据库。 因此，可以生成一个数据库，可以保留低到一个小错误的边缘。 此外，提供了优雅的结果版本，因为可以计算数据库，使得低阶边缘的误差小，并且以边际的顺序顺利增加。

公开(公告)号：US20070174314A1

公开(公告)日：2007-07-26

申请号：US11326884

申请日：2006-01-06

申请人： Frank McSherry ,  John MacCormick

发明人： Frank McSherry ,  John MacCormick

IPC分类号： G06F7/00

CPC分类号： G06F17/30286

摘要： While consulting indexes to conduct a search, a determination is made from time to time as to whether it is more efficient to consult individual indexes in a set or to merge the indexes and consult the merged index. The cost of merging indexes is compared with the cost of individually querying indexes. In accordance with the result of this comparison, the indexes are merged and the merged index is consulted, or the indexes are individually consulted. A cost-balance invariant in the form of an inequality is used to equate the cost of merging indexes to a weighted cost of individually querying indexes. As query events are received, the costs are updated. As long as the cost-balance invariant is not violated, indexes are merged and the merged index is queried. If the cost-balance invariant is violated, indexes are not merged, and the indexes are individually queried.

摘要翻译： 在咨询索引进行搜索时，不时决定是否更有效地查询一个集合中的各个索引或合并索引并查看合并的索引。 将合并索引的成本与单独查询索引的成本进行比较。 根据比较结果，合并指数，查询合并指数，或单独查询指标。 以不平等形式的成本平衡不变性用于将合并指数的成本等同于单独查询索引的加权成本。 当接收到查询事件时，更新成本。 只要不违反成本平衡不变性，就会合并索引，查询合并索引。 如果违反成本平衡不变性，则不合并索引，并对索引进行单独查询。

公开(公告)号：US20070061315A1

公开(公告)日：2007-03-15

申请号：US11227301

申请日：2005-09-15

申请人： Frank McSherry

发明人： Frank McSherry

IPC分类号： G06F17/30

CPC分类号： G06F17/30864 ,  Y10S707/99933 ,  Y10S707/99934

摘要： An input or query is determined for which a search engine's static ranking computation is the answer. By understanding how this input or query differs from the posed input or query, the precise termination point of an iterative convergence problem can be determined. An iterative process provides the following inputs to the system: a graph of hyperlinks, and a vector of how the probability mass is redistributed. Given the set of ranks (the output results), it is determined how the input (e.g., the query) would have to be changed to get the rank(s) as the answer or result. Backward answer analysis is provided in the web page context. The difference between what was asked and what should have been asked is determined. After the difference is computed, it is determined if the iterative process should be stopped or not.

摘要翻译： 确定搜索引擎的静态排名计算是答案的输入或查询。 通过了解这种输入或查询与提出的输入或查询的不同，可以确定迭代收敛问题的精确终止点。 迭代过程为系统提供以下输入：超链接图，以及概率质量如何重新分配的向量。 给定一组等级（输出结果），确定输入（例如，查询）如何被改变以获得等级作为答案或结果。 向后回答分析在网页上下文中提供。 所提出的问题和应该提出的内容之间的区别是确定的。 在计算差值之后，确定是否应该停止迭代过程。

公开(公告)号：US20060026191A1

公开(公告)日：2006-02-02

申请号：US10903345

申请日：2004-07-30

申请人： Frank McSherry

发明人： Frank McSherry

IPC分类号： G06F7/00

CPC分类号： G06F17/30864 ,  G06F17/30607 ,  Y10S707/99935 ,  Y10S707/99937 ,  Y10S707/99943

摘要： Methods and systems are described for computing page rankings more efficiently. Using an interconnectivity matrix describing the interconnection of web pages, a new matrix is computed. The new matrix is used to compute the average of values associated with each web page's neighboring web pages. The secondary eigenvector of this new matrix is computed, and indices for web pages are relabeled according to the eigenvector. The data structure storing the interconnectivity information is preferably also physically sorted according to the eigenvector. By reorganizing the matrix used in the web page ranking computations, caching is performed more efficiently, resulting in faster page ranking techniques. Methods for efficiently allocating the distribution of resources are also described.

摘要翻译： 描述了更有效地计算页面排名的方法和系统。 使用描述网页互连的互连矩阵，计算出一个新的矩阵。 新矩阵用于计算与每个网页的相邻网页相关联的值的平均值。 计算该新矩阵的次特征向量，并根据特征向量重新标记网页索引。 存储互连信息的数据结构优选地也根据特征向量进行物理分类。 通过重新组织网页排名计算中使用的矩阵，可以更有效地执行缓存，从而实现更快的页面排名技术。 还描述了有效分配资源分配的方法。

公开(公告)号：US20050149502A1

公开(公告)日：2005-07-07

申请号：US10752384

申请日：2004-01-05

申请人： Frank McSherry

发明人： Frank McSherry

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30867 ,  Y10S707/99933

摘要： Methods and systems are provided for efficiently computing personalized rankings of web pages or other interconnected objects. The personalized rankings are produced by efficiently computing an approximation matrix to an ideal personalized page ranking matrix. The methods and systems provided herein can be used to produce search results with particular relevance to an individual searcher.

摘要翻译： 提供了用于有效地计算网页或其他互连对象的个性化排名的方法和系统。 通过有效地将近似矩阵计算到理想的个性化页面排序矩阵来产生个性化排名。 本文提供的方法和系统可用于产生与个体搜索者特别相关的搜索结果。

公开(公告)号：US20050033708A1

公开(公告)日：2005-02-10

申请号：US10944142

申请日：2004-09-17

申请人： Dimitris Achlioptas ,  Frank McSherry

发明人： Dimitris Achlioptas ,  Frank McSherry

IPC分类号： G06F17/16 ,  G06K9/62 ,  G06G7/00

CPC分类号： G06K9/6247 ,  G06F17/16

摘要： Methods and systems for finding a low rank approximation for an m×n matrix A are described. The described embodiments can independently sample and/or quantize the entries of an input matrix A, and can thus speed up computation by reducing the number of non-zero entries and/or their representation length. The embodiments can be used in connection with Singular Value Decomposition techniques to greatly benefit the processing of high-dimensional data sets in terms of storage, transmission and computation.

摘要翻译： 描述了用于找到m×n矩阵A的低秩近似的方法和系统。 所描述的实施例可以独立地对输入矩阵A的条目进行采样和/或量化，并且因此可以通过减少非零条目的数量和/或其表示长度来加速计算。 这些实施例可以与奇异值分解技术结合使用，以在存储，传输和计算方面大大有益于高维数据集的处理。

公开(公告)号：US08209664B2

公开(公告)日：2012-06-26

申请号：US12406826

申请日：2009-03-18

申请人： Yuan Yu ,  Ulfar Erlingsson ,  Michael A Isard ,  Frank McSherry

发明人： Yuan Yu ,  Ulfar Erlingsson ,  Michael A Isard ,  Frank McSherry

IPC分类号： G06F9/44

CPC分类号： H04L12/44 ,  G06F8/314 ,  G06F9/5066

摘要： General-purpose distributed data-parallel computing using high-level computing languages is described. Data parallel portions of a sequential program that is written by a developer in a high-level language are automatically translated into a distributed execution plan. A set of extensions to a sequential high-level computing language are provided to support distributed parallel computations and to facilitate generation and optimization of distributed execution plans. The extensions are fully integrated with the programming language, thereby enabling developers to write sequential language programs using known constructs while providing the ability to invoke the extensions to enable better generation and optimization of the execution plan for a distributed computing environment.

摘要翻译： 描述了使用高级计算语言的通用分布式数据并行计算。 由开发者以高级语言编写的顺序程序的数据并行部分将自动转换为分布式执行计划。 提供了一组连续高级计算语言的扩展，以支持分布式并行计算，并促进分布式执行计划的生成和优化。 扩展与编程语言完全集成，从而使开发人员可以使用已知构造编写顺序语言程序，同时提供调用扩展的能力，以实现更好的生成和优化分布式计算环境的执行计划。

公开(公告)号：US20100241827A1

公开(公告)日：2010-09-23

申请号：US12406826

申请日：2009-03-18

申请人： Yuan Yu ,  Ulfar Erlingsson ,  Michael A. Isard ,  Frank McSherry

发明人： Yuan Yu ,  Ulfar Erlingsson ,  Michael A. Isard ,  Frank McSherry

IPC分类号： G06F15/76 ,  G06F9/06

CPC分类号： H04L12/44 ,  G06F8/314 ,  G06F9/5066

摘要： General-purpose distributed data-parallel computing using high-level computing languages is described. Data parallel portions of a sequential program that is written by a developer in a high-level language are automatically translated into a distributed execution plan. A set of extensions to a sequential high-level computing language are provided to support distributed parallel computations and to facilitate generation and optimization of distributed execution plans. The extensions are fully integrated with the programming language, thereby enabling developers to write sequential language programs using known constructs while providing the ability to invoke the extensions to enable better generation and optimization of the execution plan for a distributed computing environment.

摘要翻译： 描述了使用高级计算语言的通用分布式数据并行计算。 由开发者以高级语言编写的顺序程序的数据并行部分将自动转换为分布式执行计划。 提供了一组连续高级计算语言的扩展，以支持分布式并行计算，并促进分布式执行计划的生成和优化。 扩展与编程语言完全集成，从而使开发人员可以使用已知构造编写顺序语言程序，同时提供调用扩展的能力，以实现更好的生成和优化分布式计算环境的执行计划。

公开(公告)号：US20070143289A1

公开(公告)日：2007-06-21

申请号：US11305800

申请日：2005-12-16

申请人： Cynthia Dwork ,  Frank McSherry

发明人： Cynthia Dwork ,  Frank McSherry

IPC分类号： G06F17/30

CPC分类号： G06F17/30477 ,  G06F21/6245

摘要： Systems and methods are provided for controlling privacy loss associated with database participation. In general, privacy loss can be evaluated based on information available to a hypothetical adversary with access to a database under two scenarios: a first scenario in which the database does not contain data about a particular privacy principal, and a second scenario in which the database does contain data about the privacy principal. Such evaluation can be made for example by a mechanism for determining sensitivity of at least one database query output to addition to the database of data associated with a privacy principal. An appropriate noise distribution can be calculated based on the sensitivity measurement and optionally a privacy parameter. A noise value is selected from the distribution and added to query outputs.

摘要翻译： 提供系统和方法来控制与数据库参与相关的隐私损失。 一般来说，可以根据在两种情况下访问数据库的假设对手可用的信息来评估隐私损失：第一种情况，其中数据库不包含关于特定隐私主体的数据，以及第二种情况，其中数据库 确实包含有关隐私主体的数据。 可以例如通过用于确定至少一个数据库查询输出对与隐私主体相关联的数据的数据库的灵敏度的机制来进行评估。 可以基于灵敏度测量和可选的隐私参数来计算适当的噪声分布。 从分布中选择一个噪声值，并将其添加到查询输出。