专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20110055132A1 IDENTIFICATION AND MEASUREMENT OF SOCIAL INFLUENCE AND CORRELATION 有权
标题翻译：社会影响与相关性的识别与测量
公开(公告)号：US20110055132A1
公开(公告)日：2011-03-03
申请号：US12547960
申请日：2009-08-26
申请人： Mohammad Mahdian , Shanmugasundaram Ravikumar , Aris Anagnostopoulos
发明人： Mohammad Mahdian , Shanmugasundaram Ravikumar , Aris Anagnostopoulos
IPC分类号： G06N5/02
CPC分类号： G06Q10/00
摘要： Techniques for detecting social influence between users in a set of users with regard to an activity are provided. Data for each user of the set of users is received that includes a time value at which the user became active with regard to the activity, and includes at least one indication of another user in the set of users associated with the user. A first estimate of social correlation in the set of users is determined based on the data. The data is modified. For instance, the data may be modified according to a shuffle test and/or an edge reversal test. A second estimate of social correlation in the set of users is determined based on the modified data. The first estimate is compared to the second estimate to determine a degree of social influence in the set of users.
摘要翻译：提供了用于检测一组用户中关于活动的用户之间的社会影响的技术。接收包含用户关于该活动而变得活动的时间值的用户组的每个用户的数据，并且包括与该用户相关联的一组用户中的另一个用户的至少一个指示。基于数据确定用户组中的社会关联的第一估计。数据被修改。例如，可以根据洗牌测试和/或边缘反转测试来修改数据。基于修改的数据确定用户组中的社会关联的第二估计。将第一个估计值与第二个估计值进行比较，以确定一组用户的社会影响程度。

2. 发明授权

US08401984B2 Identification and measurement of social influence and correlation 有权
标题翻译：识别和衡量社会影响力和相关性
公开(公告)号：US08401984B2
公开(公告)日：2013-03-19
申请号：US12547960
申请日：2009-08-26
申请人： Mohammad Mahdian , Shanmugasundaram Ravikumar , Aris Anagnostopoulos
发明人： Mohammad Mahdian , Shanmugasundaram Ravikumar , Aris Anagnostopoulos
IPC分类号： G06N5/00
CPC分类号： G06Q10/00
摘要： Techniques for detecting social influence between users in a set of users with regard to an activity are provided. Data for each user of the set of users is received that includes a time value at which the user became active with regard to the activity, and includes at least one indication of another user in the set of users associated with the user. A first estimate of social correlation in the set of users is determined based on the data. The data is modified. For instance, the data may be modified according to a shuffle test and/or an edge reversal test. A second estimate of social correlation in the set of users is determined based on the modified data. The first estimate is compared to the second estimate to determine a degree of social influence in the set of users.
摘要翻译：提供了用于检测一组用户中关于活动的用户之间的社会影响的技术。接收包含用户关于该活动而变得活动的时间值的用户组的每个用户的数据，并且包括与该用户相关联的一组用户中的另一个用户的至少一个指示。基于数据确定用户组中的社会关联的第一估计。数据被修改。例如，可以根据洗牌测试和/或边缘反转测试来修改数据。基于修改的数据确定用户组中的社会关联的第二估计。将第一个估计值与第二个估计值进行比较，以确定一组用户的社会影响程度。

3. 发明申请

US20090319288A1 SUGGESTING CONTACTS FOR SOCIAL NETWORKS 审中-公开
标题翻译：建议社会网络联系人
公开(公告)号：US20090319288A1
公开(公告)日：2009-12-24
申请号：US12145436
申请日：2008-06-24
申请人： Malcolm Slaney , Alex Jaffe , Shanmugasundaram Ravikumar , Aris Anagnostopoulos , Michael Mahoney , Mohammad Mahdian , Matthew Rothenberg , Arpita Ghosh
发明人： Malcolm Slaney , Alex Jaffe , Shanmugasundaram Ravikumar , Aris Anagnostopoulos , Michael Mahoney , Mohammad Mahdian , Matthew Rothenberg , Arpita Ghosh
IPC分类号： G06Q99/00
CPC分类号： G06Q30/02 , G06Q10/10
摘要： A social network is managed by applying connectivity and similarity measures to social network information to identify possible new relationships between social network users, and then automatically suggest those identified relationships to the social network users. The social network information can include user profile information and indicate existing social relationships between the users in the social network. Users can provide feedback regarding the suggestions, including indications whether the relationship was accepted, consummated, or declined. The social network information can be updated using the feedback. Similarity measures can be based on one or more of shared contacts, or common interests or activities, or content associated with social network users, or ratings within the social network of users and/or their content. Possible relationships having similarity measures that suggest the users likely to already know each other, can be omitted and not suggested.
摘要翻译：通过对社交网络信息应用连通性和相似性度量来识别社交网络，以识别社交网络用户之间可能的新关系，然后自动向社交网络用户建议所识别的关系。社交网络信息可以包括用户简档信息并且指示社交网络中的用户之间的现有社会关系。用户可以提供有关建议的反馈意见，包括关系是否被接受，完成或拒绝。可以使用反馈更新社交网络信息。相似性度量可以基于一个或多个共享联系人，或共同兴趣或活动，或与社交网络用户相关联的内容，或用户社交网络内的评级和/或其内容。具有建议用户可能已经彼此认识的相似性度量的可能关系可以被省略并且不被建议。

4. 发明申请

US20100228745A1 SYSTEM, METHOD, AND APPARATUS FOR SORTING AT LEAST PARTIALLY DYNAMIC DATA 审中-公开
标题翻译：用于分配至少部分动态数据的系统，方法和装置
公开(公告)号：US20100228745A1
公开(公告)日：2010-09-09
申请号：US12396910
申请日：2009-03-03
申请人： Aris Anagnostopoulos , Shanmugasundaram Ravikumar , Mohammad Mahdian , Eli Upfal
发明人： Aris Anagnostopoulos , Shanmugasundaram Ravikumar , Mohammad Mahdian , Eli Upfal
IPC分类号： G06F17/30
CPC分类号： G06F16/951
摘要： Embodiments of methods, apparatuses, devices and systems associated with sorting candidate values are disclosed.
摘要翻译：公开了与排序候选值相关联的方法，装置，装置和系统的实施例。

5. 发明授权

US09558506B2 System and method for exploring new sponsored search listings of uncertain quality 有权
标题翻译：探索不确定质量的新赞助搜索列表的系统和方法
公开(公告)号：US09558506B2
公开(公告)日：2017-01-31
申请号：US12700530
申请日：2010-02-04
申请人： Deepak K. Agarwal , Dz-Mou Jung , Sai-Ming Li , Mohammad Mahdian , R. Preston McAfee , Shanmugasundaram Ravikumar , David Reiley
发明人： Deepak K. Agarwal , Dz-Mou Jung , Sai-Ming Li , Mohammad Mahdian , R. Preston McAfee , Shanmugasundaram Ravikumar , David Reiley
IPC分类号： G06Q30/00 , G06Q30/02
CPC分类号： G06Q30/0246 , G06Q30/0275
摘要： According to some example embodiments, a method includes calculating learning values associated with a plurality of listings, at least one of said learning values associated with one of said listings representing a value based, at least in part, on a probability distribution of selections of said listing. The method further includes applying said learning values to ranking scores associated with said listings to provide an updated ranking, and electronically auctioning advertising inventory to purchasers associated with said listings based, at least in part, on said updated ranking.
摘要翻译：根据一些示例性实施例，一种方法包括计算与多个列表相关联的学习值，所述学习值中的至少一个与所述列表中的一个相关联，表示至少部分地基于所述列表的选择的概率分布清单。该方法还包括将所述学习值应用于与所述列表相关联的排名分数以提供更新的排名，以及至少部分地基于所述更新的排名，向与所述列表相关联的购买者电子拍卖广告库存。

6. 发明申请

US20110191167A1 SYSTEM AND METHOD FOR EXPLORING NEW SPONSORED SEARCH LISTINGS OF UNCERTAIN QUALITY 有权
标题翻译：用于探索不确定质量的新赞助搜索列表的系统和方法
公开(公告)号：US20110191167A1
公开(公告)日：2011-08-04
申请号：US12700530
申请日：2010-02-04
申请人： Deepak K. Agarwal , Dz-Mou Jung , Sai-Ming Li , Mohammad Mahdian , R. Preston McAfee , Shanmugasundaram Ravikumar , David Reiley
发明人： Deepak K. Agarwal , Dz-Mou Jung , Sai-Ming Li , Mohammad Mahdian , R. Preston McAfee , Shanmugasundaram Ravikumar , David Reiley
IPC分类号： G06Q30/00 , G06Q10/00
CPC分类号： G06Q30/0246 , G06Q30/0275
摘要： According to some example embodiments, a method includes calculating learning values associated with a plurality of listings, at least one of said learning values associated with one of said listings representing a value based, at least in part, on a probability distribution of selections of said listing. The method further includes applying said learning values to ranking scores associated with said listings to provide an updated ranking, and electronically auctioning advertising inventory to purchasers associated with said listings based, at least in part, on said updated ranking.
摘要翻译：根据一些示例性实施例，一种方法包括计算与多个列表相关联的学习值，所述学习值中的至少一个与所述列表中的一个相关联，表示至少部分地基于所述列表的选择的概率分布清单。该方法还包括将所述学习值应用于与所述列表相关联的排名分数以提供更新的排名，以及至少部分地基于所述更新的排名，向与所述列表相关联的购买者电子拍卖广告库存。

7. 发明授权

US08452832B2 System and method for population-targeted advertising 有权
标题翻译：以人口为目标的广告系统和方法
公开(公告)号：US08452832B2
公开(公告)日：2013-05-28
申请号：US11495269
申请日：2006-07-27
申请人： Pavel Berkhin , Shanmugasundaram Ravikumar , Andrew Tomkins , John Anthony Tomlin
发明人： Pavel Berkhin , Shanmugasundaram Ravikumar , Andrew Tomkins , John Anthony Tomlin
IPC分类号： G06F15/16 , G06Q30/00
CPC分类号： G06F17/30702 , G06F17/30864 , G06F17/30867 , G06Q30/02 , H04L67/02 , H04L67/20 , H04L67/306
摘要： An improved system and method for web destination profiling for online population-targeted advertising is provided. A web destination profiler may be provided for generating web destination profiles. Traffic may be analyzed at a particular web destination in order to understand the population visiting the web destination. The analysis of user traffic, including differentiated clickstream data, may be applied for determining known characteristics of a web destination profile. Moreover, unknown characteristics of a web destination profile may be determined using a variety of techniques including inferring characteristics by modeling traffic flow through other web destinations, estimating characteristics from other web destination profiles by predicting traffic flow through other web destinations, propagating characteristics to a web destination profile by smoothing a joint distribution of characteristics of other web destination profiles, and so forth. Web destination profiles may be used by applications such as an online application for population-targeted advertising.
摘要翻译：提供了一种用于在线面向对象广告的Web目标分析的改进的系统和方法。可以提供web目的地分析器来生成web目的地简档。可以在特定的网络目的地分析流量，以了解访问网络目的地的人口。用户流量的分析（包括差分点击流数据）可以被应用于确定web目的地简档的已知特征。此外，可以使用各种技术来确定web目的地简档的未知特性，包括通过建模通过其他web目的地的业务流来推断特征，通过预测通过其他web目的地的业务流来估计来自其他web目的地简档的特征，将特征传播到web 通过平滑其他web目的地简档的特征的联合分布等来实现目的地简档。 Web目标配置文件可能被诸如在线应用程序的应用程序用于针对人口的广告。

8. 发明申请

US20130031059A1 METHOD AND SYSTEM FOR FAST SIMILARITY COMPUTATION IN HIGH DIMENSIONAL SPACE 有权
标题翻译：用于在高维空间中快速相似计算的方法和系统
公开(公告)号：US20130031059A1
公开(公告)日：2013-01-31
申请号：US13189696
申请日：2011-07-25
申请人： Shanmugasundaram Ravikumar , Anirban Dasgupta , Tamas Sarlos
发明人： Shanmugasundaram Ravikumar , Anirban Dasgupta , Tamas Sarlos
IPC分类号： G06F17/30
CPC分类号： G06F17/30628
摘要： Method, system, and programs for computing similarity. Input data is first received from one or more data sources and then analyzed to obtain an input feature vector that characterizes the input data. An index is then generated based on the input feature vector and is used to archive the input data, where the value of the index is computed based on an improved Johnson-Lindenstrass transformation (FJLT) process. With the improved FJLT process, first, the sign of each feature in the input feature vector is randomly flipped to obtain a flipped vector. A Hadamard transformation is then applied to the flipped vector to obtain a transformed vector. An inner product between the transformed vector and a sparse vector is then computed to obtain a base vector, based on which the value of the index is determined.
摘要翻译：用于计算相似度的方法，系统和程序。首先从一个或多个数据源接收输入数据，然后分析以获得表征输入数据的输入特征向量。然后基于输入特征向量生成索引，并且用于存档输入数据，其中基于改进的约翰逊 - 林登斯特拉斯变换（FJLT）处理来计算索引的值。随着改进的FJLT过程，首先，输入特征向量中的每个特征的符号被随机翻转以获得翻转矢量。然后将Hadamard变换应用于翻转矢量以获得变换矢量。然后计算变换向量和稀疏向量之间的内积，以获得基准向量，基于此确定索引的值。

9. 发明授权

US08005824B2 On the role of market economics in ranking search results 有权
标题翻译：关于市场经济学在排名搜索结果中的作用
公开(公告)号：US08005824B2
公开(公告)日：2011-08-23
申请号：US12193819
申请日：2008-08-19
申请人： Shanmugasundaram Ravikumar , Daniel M. Shiffman , Dandapani Sivakumar
发明人： Shanmugasundaram Ravikumar , Daniel M. Shiffman , Dandapani Sivakumar
IPC分类号： G06F17/30
CPC分类号： G06F17/30864 , G06F17/30696 , G06Q20/102 , G06Q40/04 , Y10S707/99935
摘要： A method of and service for searching computerized networks, such as the internet, that first performs a search based on a user query to produce results that are ranked. The results comprise references to entities (addresses on the network, such as web sites). Before reporting the results to the user, the invention provides that the search entity contacts the entities listed in the search results to determine whether entities listed in the search results desire to change their rank when compared to other entities listed in the results. If some entities do desire to change their rank, the invention charges fees to entities that increase their rank and credits (pays fees) to entities that decrease their rank. A portion of the amount charged to entities that increase their rank can be paid to the entity performing the search (helping to support the high quality search engines), and a portion will go to the entities that voluntarily decrease their rank within the search results (helping to support high-content web sites).
摘要翻译：用于搜索诸如因特网的计算机化网络的方法和服务，其首先基于用户查询执行搜索以产生被排序的结果。结果包括引用实体（网络上的地址，如网站）。在将结果报告给用户之前，本发明提供了搜索实体与搜索结果中列出的实体联系，以确定与结果中列出的其他实体相比，搜索结果中列出的实体是否希望改变其排名。如果一些实体希望改变他们的等级，那么这个发明会向降低排名的实体增加其排名和信用（支付费用）的实体收取费用。向提高其等级的实体收取的金额的一部分可以支付给执行搜索的实体（有助于支持高质量的搜索引擎），并且一部分将转到在搜索结果中自愿降低排名的实体（帮助支持高端网站）。

10. 发明授权

US07958363B2 Toolbar signature 有权
标题翻译：工具栏签名
公开(公告)号：US07958363B2
公开(公告)日：2011-06-07
申请号：US11924945
申请日：2007-10-26
申请人： Cameron Marlow , Shanmugasundaram Ravikumar , Andrew Tomkins
发明人： Cameron Marlow , Shanmugasundaram Ravikumar , Andrew Tomkins
IPC分类号： H04L9/00 , H04L9/32 , G06F7/04
CPC分类号： H04L63/12 , H04L63/0442
摘要： A method and system are provided for a web browser toolbar signature. In one example, the method includes receiving a submission of user content from a source webpage, receiving a producer identity of a producer who submitted the user content, receiving identifying information about the destination webpage, coding signed content using the user content and the producer identity, wherein the signed content includes a signature, and submitting the signed content to a server hosting the destination webpage.
摘要翻译：提供了一种用于web浏览器工具条签名的方法和系统。在一个示例中，该方法包括从源网页接收用户内容的提交，接收提交用户内容的制作者的制作者标识，接收关于目的地网页的标识信息，使用用户内容和生成者身份对签名的内容进行编码其中，所签署的内容包括签名，并将签名的内容提交给托管目的地网页的服务器。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式