-
公开(公告)号：US08751559B2
公开(公告)日：2014-06-10
申请号：US12211113
申请日：2008-09-16
Applicant: Matthew Richardson , Ryen W. White , Eric D. Brill
Inventor： Matthew Richardson , Ryen W. White , Eric D. Brill
IPC: G06F15/16
CPC classification number: H04L67/306 , G06Q10/06 , H04L51/14
Abstract: A question processing system routes questions among participants in a balanced and sustainable manner. Any participant can act as an inquirer (who poses questions) and an expert (who answers questions). In one illustrative case, the question processing system operates by: receiving a question from an inquirer; determining at least one expert that is appropriate to answer the question; and routing the question to the expert. The receiving, determining, and routing are repeated with respect to other inquirers and other experts to achieve a desired balance of information exchange among the plurality of participants of the electronic question processing system.
Abstract translation: 问题处理系统以平衡和可持续的方式将参与者的问题提交给参与者。 任何参与者都可以作为询问者（提出问题）和专家（谁回答问题）。 在一个说明性情况下，问题处理系统通过以下操作：从查询者接收问题; 决定至少一名适合回答问题的专家; 并将问题路由到专家。 相对于其他查询者和其他专家重复接收，确定和路由以实现电子问题处理系统的多个参与者之间的信息交换的期望的平衡。
-
公开(公告)号：US20120158623A1
公开(公告)日：2012-06-21
申请号：US12973916
申请日：2010-12-21
Applicant: Mikhail Bilenko , Matthew Richardson
Inventor： Mikhail Bilenko , Matthew Richardson
IPC: G06F15/18
CPC classification number: G06N20/00
Abstract: The claimed subject matter provides a method for visualizing machine learning accuracy. The method includes receiving a plurality of training instances for the machine learning system. The method also includes receiving a plurality of results for the machine learning system. The plurality of results corresponds to the plurality of training instances. The method further includes providing an interactive representation of the training instances and the results. The interactive representation supports identifying inaccuracies of the machine learning system attributable to the training instances, the features used to obtain a featurized form of the training instance, and/or a model implemented by the machine learning system.
Abstract translation: 所要求保护的主题提供了一种用于可视化机器学习精度的方法。 该方法包括接收机器学习系统的多个训练实例。 该方法还包括为机器学习系统接收多个结果。 多个结果对应于多个训练实例。 该方法还包括提供训练实例和结果的交互式表示。 交互式表示支持识别归因于训练实例的机器学习系统的不准确性，用于获得训练实例的特征形式的特征和/或由机器学习系统实现的模型。
-
公开(公告)号：US20100287156A1
公开(公告)日：2010-11-11
申请号：US12839916
申请日：2010-07-20
Applicant: Matthew Richardson , Wisam Dakka
Inventor： Matthew Richardson , Wisam Dakka
IPC: G06F17/30
CPC classification number: G06F16/951 , Y10S707/99943
Abstract: Providing updates to a computing device having a search engine capable of searching a local data store having an index with data related to a plurality of sites located on a wide area network. A first index builder capable of accessing sites on a wide area network is provided. The first index builder retrieves and analyzes data from the sites to create index data related to the sites. The method further includes communicating index data to the locally stored database for incrementally updating the index. A computing device capable of accessing a local data storage device is also provided. The device includes an index stored on the storage device including information related to data stored on the wide area network, a search engine capable of searching the index to retrieve information in response to a query, and a display.
Abstract translation: 向具有搜索引擎的计算设备提供更新，所述搜索引擎能够搜索具有与位于广域网上的多个站点相关的数据的索引的本地数据存储。 提供了能够访问广域网上的站点的第一个索引构建器。 第一个索引构建器检索和分析站点中的数据，以创建与站点相关的索引数据。 该方法还包括将索引数据传送到本地存储的数据库以逐渐更新索引。 还提供了能够访问本地数据存储设备的计算设备。 该设备包括存储在存储设备上的索引，包括与存储在广域网中的数据相关的信息，能够搜索索引以响应于查询来检索信息的搜索引擎和显示。
-
公开(公告)号：US20100057675A1
公开(公告)日：2010-03-04
申请号：US12199568
申请日：2008-08-27
Applicant: Ryen W. White , Mikhail Bilenko , Eric D. Brill , Raman Chandrasekar , Scott K. Imig , Matthew Richardson , Robert L. Rounthwaite
Inventor： Ryen W. White , Mikhail Bilenko , Eric D. Brill , Raman Chandrasekar , Scott K. Imig , Matthew Richardson , Robert L. Rounthwaite
IPC: G06F17/30
CPC classification number: G06Q30/02
Abstract: A component presents access to a recommended search provider via a user interface element. In an example embodiment, a device-implemented method for recommending a search provider includes acts of receiving, ascertaining, and modifying. A search query input is received. A recommended search provider is ascertained at least partially responsive to the search query input. A user interface is modified to indicate the recommended search provider.
Abstract translation: 组件通过用户界面元素显示对推荐的搜索提供者的访问。 在示例实施例中，用于推荐搜索提供者的设备实现的方法包括接收，确定和修改的动作。 接收到搜索查询输入。 确定推荐的搜索提供者至少部分地响应于搜索查询输入。 修改用户界面以指示推荐的搜索提供程序。
-
5.发明授权Method and apparatus for probabilistic matching to authenticate hosts during distributed denial of service attack 有权在分布式拒绝服务攻击期间进行概率匹配以验证主机的方法和装置公开(公告)号：US08661522B2
公开(公告)日：2014-02-25
申请号：US13193254
申请日：2011-07-28
Applicant: Lawrence Bruce Huston, III , Matthew Richardson , Aaron Campbell
Inventor： Lawrence Bruce Huston, III , Matthew Richardson , Aaron Campbell
CPC classification number: H04L63/1458 , H04L63/0236 , H04L63/0254 , H04L67/02
Abstract: A system and method to track external devices attempting to connect to a protected network using probabilistic filters. When a connection from a new external device attempts to access the protected network, the memory of a protection system, which is organized as a probabilistic filter, is searched to determine if the IP address already exists in the memory of protection system. If the search locates the IP address, the protection system terminates the connection to the external device. If the search is negative, then protection device begins the authentication process for the external device.
Abstract translation: 跟踪使用概率过滤器尝试连接到受保护网络的外部设备的系统和方法。 当来自新的外部设备的连接尝试访问受保护的网络时，搜索被组织为概率过滤器的保护系统的存储器，以确定IP地址是否已经存在于保护系统的存储器中。 如果搜索查找IP地址，则保护系统将终止与外部设备的连接。 如果搜索为负，则保护设备开始外部设备的认证过程。
-
Patent Agency Ranking
6.发明申请Method and Apparatus for Probabilistic Matching to Authenticate Hosts During Distributed Denial of Service Attack 有权用于在分布式拒绝服务攻击期间对主机进行认证的概率匹配的方法和装置公开(公告)号：US20130031605A1
公开(公告)日：2013-01-31
申请号：US13193254
申请日：2011-07-28
Applicant: Lawrence Bruce Huston III , Matthew Richardson , Aaron Campbell
Inventor： Lawrence Bruce Huston III , Matthew Richardson , Aaron Campbell
CPC classification number: H04L63/1458 , H04L63/0236 , H04L63/0254 , H04L67/02
Abstract: A system and method to track external devices attempting to connect to a protected network using probabilistic filters. When a connection from a new external device attempts to access the protected network, the memory of a protection system, which is organized as a probabilistic filter, is searched to determine if the IP address already exists in the memory of protection system. If the search locates the IP address, the protection system terminates the connection to the external device. If the search is negative, then protection device begins the authentication process for the external device.
Abstract translation: 跟踪使用概率过滤器尝试连接到受保护网络的外部设备的系统和方法。 当来自新的外部设备的连接尝试访问受保护的网络时，搜索被组织为概率过滤器的保护系统的存储器，以确定IP地址是否已经存在于保护系统的存储器中。 如果搜索查找IP地址，则保护系统将终止与外部设备的连接。 如果搜索为负，则保护设备开始外部设备的认证过程。
-
公开(公告)号：US20100208984A1
公开(公告)日：2010-08-19
申请号：US12371541
申请日：2009-02-13
Applicant: Mikhail Bilenko , Matthew Richardson , Sonal Gupta
Inventor： Mikhail Bilenko , Matthew Richardson , Sonal Gupta
CPC classification number: G06Q30/0277 , G06F16/3338 , G06Q30/0256
Abstract: A source keyword may be received multiple times and each time, in response, a machine-learning algorithm may be used to identify and rank respective matching-keywords that have been determined to match the source keyword. A portion or unit of content may be generated based on one of the ranked matching-keywords. The content is transmitted via a network to a client device and a user's impression of the content is recorded. The machine-learning algorithm may continue to rank matching-keywords for arbitrary source keywords while the recorded impressions and corresponding matched-keywords, respectively, are used to train the machine-learning algorithm. The training alters how the machine-learning algorithm ranks matching-keywords determined to match the source keyword.
Abstract translation: 可以多次接收源关键字，并且每次可以接收每个源关键字，作为响应，可以使用机器学习算法来识别和排列已经被确定为匹配源关键字的各个匹配关键字。 可以基于一个排名匹配关键词生成内容的一部分或单位。 将内容通过网络发送到客户端设备，并记录用户的内容印象。 机器学习算法可以继续对任意源关键词进行匹配关键词的排名，而记录的印象和相应的匹配关键词分别用于训练机器学习算法。 训练改变了机器学习算法如何排列匹配关键字，以匹配源关键字。
-
公开(公告)号：US20110295687A1
公开(公告)日：2011-12-01
申请号：US12787410
申请日：2010-05-26
Applicant: Mikhail Bilenko , Matthew Richardson
Inventor： Mikhail Bilenko , Matthew Richardson
CPC classification number: G06Q30/0269 , G06F16/24575 , G06Q30/0241 , G06Q30/0256
Abstract: Described is using per-user profile data (e.g., maintained in a browser cookie) as a factor in selecting advertisements to be presented to a user for a current context such as containing query keywords. For example, an advertiser may be willing to bid more if the current context's keywords match the user profile data that indicates a particular area of interest to the user and advertiser. Also described is updating the per-user profile data with the current context if doing so increases the expected utility of the per-user profile data, e.g., increases the predicted amount of revenue from advertisement clicking. Also described is other advertisement personalization based upon the per-user profile data, e.g., the ranking and/or appearance of the advertisements.
Abstract translation: 描述的是使用每用户简档数据（例如，维护在浏览器cookie中）作为选择要呈现给用户的当前上下文（例如包含查询关键字）的广告的因素。 例如，如果当前上下文的关键字与用户简档数据匹配以指示用户和广告商感兴趣的特定区域，则广告商可能愿意出价更高。 还描述的是，如果这样做增加了每个用户简档数据的预期效用，例如增加了广告点击的预测收入量，则用当前上下文来更新每个用户简档数据。 还描述了基于每个用户简档数据的其他广告个性化，例如广告的排名和/或外观。
-
公开(公告)号：US20100317444A1
公开(公告)日：2010-12-16
申请号：US12481595
申请日：2009-06-10
Applicant: Raman Chandrasekar , Christopher Brian Quirk , Sarthak Deepak Shah , Matthew Richardson , Christopher John Champness Burges , Abhishek Gupta , Hao Ma
Inventor： Raman Chandrasekar , Christopher Brian Quirk , Sarthak Deepak Shah , Matthew Richardson , Christopher John Champness Burges , Abhishek Gupta , Hao Ma
CPC classification number: G06F17/30864
Abstract: Human computation games are provided wherein a player is shown a page, such as a web page. The player is then asked to provide one or more terms that are intended to cause a search engine to return the page in response to performing a query using the terms. The terms provided by the player during game play are then collected, stored, and utilized to improve the performance of the search engine.
Abstract translation: 提供了人类计算游戏，其中玩家被显示为诸如网页的页面。 然后要求播放器提供一个或多个术语，其旨在使搜索引擎返回页面以响应于使用该术语执行查询。 然后收集，存储和利用玩家在游戏中提供的术语来提高搜索引擎的性能。
-
公开(公告)号：US20090187540A1
公开(公告)日：2009-07-23
申请号：US12017346
申请日：2008-01-22
Applicant: Matthew Richardson , Lilyana Simeonova Mihalkova , Robert L. Rounthwaite , Mikhail Bilenko
Inventor： Matthew Richardson , Lilyana Simeonova Mihalkova , Robert L. Rounthwaite , Mikhail Bilenko
IPC: G06F17/30
CPC classification number: G06F16/9535
Abstract: Described herein is a system that includes a receiver component that receives an indication that a user has accessed a search engine to initiate a search session. An analyzer component predicts informational interests of the user upon receipt of the indication and outputs an informational item that corresponds to the predicted informational interests of the user, wherein the analyzer component is configured to output the informational item prior to the user issuing a query to the search engine.
Abstract translation: 这里描述的是一种系统，其包括接收组件，其接收用户已经访问了搜索引擎以发起搜索会话的指示。 分析器组件在接收到指示时预测用户的信息兴趣，并且输出与用户的预测的信息兴趣相对应的信息项，其中分析器组件被配置为在用户发出查询之前输出信息项 搜索引擎。
-
-
-
-
-
-
-
-
-
Search Results
33
records
(took 0.037 seconds)
