专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明授权

US08768050B2 Accurate text classification through selective use of image data 有权
标题翻译：通过选择性使用图像数据来准确地进行文本分类
公开(公告)号：US08768050B2
公开(公告)日：2014-07-01
申请号：US13158484
申请日：2011-06-13
申请人： Anitha Kannan , Partha Pratim Talukdar , Nikhil Rasiwasia , Qifa Ke , Rakesh Agrawal
发明人： Anitha Kannan , Partha Pratim Talukdar , Nikhil Rasiwasia , Qifa Ke , Rakesh Agrawal
IPC分类号： G06K9/62
CPC分类号： G06K9/6268 , G06K9/6227 , G06K9/6293
摘要： Product images are used in conjunction with textual descriptions to improve classifications of product offerings. By combining cues from both text and image descriptions associated with products, implementations enhance both the precision and recall of product description classifications within the context of web-based commerce search. Several implementations are directed to improving those areas where text-only approaches are most unreliable. For example, several implementations use image signals to complement text classifiers and improve overall product classification in situations where brief textual product descriptions use vocabulary that overlaps with multiple diverse categories. Other implementations are directed to using text and images “training sets” to improve automated classifiers including text-only classifiers. Certain implementations are also directed to learning a number of three-way image classifiers focused only on “confusing categories” of the text signals to improve upon those specific areas where text-only classification is weakest.
摘要翻译：产品图像与文本描述结合使用，以改进产品分类。通过结合来自与产品相关的文本和图像描述的提示，实现在基于网络的商业搜索的上下文中增强了产品描述分类的精度和回收。几个实现旨在改进那些仅文本方法最不可靠的领域。例如，在简短的文本产品描述使用与多个不同类别重叠的词汇的情况下，多个实现使用图像信号来补充文本分类器并改进整体产品分类。其他实现涉及使用文本和图像“训练集”来改进自动分类器，包括纯文本分类器。某些实现也针对学习一些三维图像分类器，仅针对文本信号的“混淆类别”，以改善文本分类最弱的特定领域。

52. 发明授权

US08751502B2 Visually-represented results to search queries in rich media content 有权
标题翻译：在富媒体内容中搜索查询的视觉化结果
公开(公告)号：US08751502B2
公开(公告)日：2014-06-10
申请号：US11321044
申请日：2005-12-30
申请人： Rakesh Agrawal
发明人： Rakesh Agrawal
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/3005 , G06F17/30017 , G06F17/30044 , G06F17/30746 , G06F17/30769 , G06F17/30796 , G06F17/3084 , Y10S707/913 , Y10S707/914
摘要： When executed, a computer program product generates a graphical user interface that renders results that are responsive to a search query of a rich media file. The graphical user interface includes a chronological representation of the rich media file, one or more occurrence markers along the chronological representation corresponding to actual occurrences of a desired term at an indicated chronological location in the rich media file, and an execution icon configured to launch a rich media application that renders a relevant portion that is responsive to the search query.
摘要翻译：当执行时，计算机程序产品生成图形用户界面，其呈现响应于富媒体文件的搜索查询的结果。图形用户界面包括富媒体文件的时间顺序表示，沿着时间表示的一个或多个出现标记，其对应于在富媒体文件中指示的时间顺序位置处的期望术语的实际出现，以及被配置为发送富媒体应用程序，呈现响应搜索查询的相关部分。

53. 发明授权

US08423568B2 Query classification using implicit labels 有权
标题翻译：使用隐式标签的查询分类
公开(公告)号：US08423568B2
公开(公告)日：2013-04-16
申请号：US12560427
申请日：2009-09-16
申请人： Ariel D. Fuxman , Anitha Kannan , Andrew Brian Goldberg , Rakesh Agrawal
发明人： Ariel D. Fuxman , Anitha Kannan , Andrew Brian Goldberg , Rakesh Agrawal
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30693
摘要： Described is a technology for automatically generating labeled training data for training a classifier based upon implicit information associated with the data. For example, whether a query has commercial intent can be classified based upon whether the query was submitted at a commercial website's search portal, as logged in a toolbar log. Positive candidate query-related data is extracted from the toolbar log based upon the associated implicit information. A click log is processed to obtain negative query-related data. The labeled training data is automatically generated by separating at least some of the positive candidate query data from the remaining positive candidate query data based upon the negative query data. The labeled training data may be used to train a classifier, such as to classify an online search query as having a certain type of intent or not.
摘要翻译：描述了一种用于根据与数据相关联的隐含信息自动生成用于训练分类器的标记训练数据的技术。例如，查询是否具有商业意图可以根据在商业网站的搜索门户网站上提交的查询进行分类，如登录在工具栏日志中。基于相关联的隐含信息，从工具栏日志中提取正候选查询相关数据。处理点击日志以获取负查询相关数据。基于负查询数据，将剩余的正候选查询数据中的至少一些正候选查询数据分离出来，自动生成标示训练数据。标记的训练数据可以用于训练分类器，例如将在线搜索查询分类为具有某种类型的意图。

54. 发明授权

US08275726B2 Object classification using taxonomies 有权
标题翻译：使用分类法的对象分类
公开(公告)号：US08275726B2
公开(公告)日：2012-09-25
申请号：US12414065
申请日：2009-03-30
申请人： Panayiotis Tsaparas , Panagiotis Papadimitriou , Ariel D. Fuxman , Lise C. Getoor , Rakesh Agrawal
发明人： Panayiotis Tsaparas , Panagiotis Papadimitriou , Ariel D. Fuxman , Lise C. Getoor , Rakesh Agrawal
IPC分类号： G06E1/00 , G06E3/00 , G06F15/18 , G06G7/00
CPC分类号： G06N99/005
摘要： As provided herein objects from a source catalog, such as a provider's catalog, can be added to a target catalog, such as an enterprise master catalog, in a scalable manner utilizing catalog taxonomies. A baseline classifier determines probabilities for source objects to target catalog classes. Source objects can be assigned to those classes with probabilities that meet a desired threshold and meet a desired rate. A classification cost for target classes can be determined for respective unassigned source objects, which can comprise determining an assignment cost and separation cost for the source objects for respective desired target classes. The separation and assignment costs can be combined to determine the classification cost, and the unassigned source objects can be assigned to those classes having a desired classification cost.
摘要翻译：如本文所提供的，可以使用目录分类法将来自源目录的诸如提供者目录的对象以可扩展的方式添加到目标目录，例如企业主目录。基准分类器确定源对象到目标目录类的概率。可以将源对象分配给具有满足期望阈值且满足期望速率的概率的那些类。可以针对相应的未分配的源对象来确定目标类别的分类成本，其可以包括确定用于各个期望目标类别的源对象的分配成本和分离成本。分离和分配成本可以组合以确定分类成本，并且未分配的源对象可以被分配给具有期望的分类成本的那些类。

55. 发明申请

US20120115312A1 THIN FILMS FOR PHOTOVOLTAIC CELLS 审中-公开
标题翻译：光伏电池薄膜
公开(公告)号：US20120115312A1
公开(公告)日：2012-05-10
申请号：US13321834
申请日：2010-05-26
申请人： Rakesh Agrawal , Hugh W. Hillhouse , Qijie Guo , Mahaprasad Kar
发明人： Rakesh Agrawal , Hugh W. Hillhouse , Qijie Guo , Mahaprasad Kar
IPC分类号： H01L21/20
CPC分类号： H01L31/0322 , B82Y30/00 , C09D11/36 , H01L21/02485 , H01L21/02568 , H01L21/02601 , H01L21/02614 , H01L21/02628 , H01L31/0749 , H01L31/1864 , Y02E10/541 , Y02P70/521
摘要： In one aspect, a method for forming CIGSSe-based thin films includes depositing at least two layers of particles on a substrate. At least one layer includes a CIGSSe particle having a chemical composition denoted by Cu(InI-xGax)(S1-ySey)2 where 0≦x ≦1 and 0≦y≦1. The particle layers are annealed individually or in combination to form a CIGSSe thin film having a composition profile along the depth of the film In addition, one or more of the particle layers may be also deposited on a pre-existing absorber and annealed to form a film having a composition profile along the depth of the film After depositing thin film precursor layers containing CIGSSe nanoparticles (and/or any other particles) on a suitable substrate in accordance with a desired concentration profile, a subsequent treatment under an Se and/or S containing atmosphere at elevated temperature may be used to convert the precursor layers into a CIGSSe absorber film In a further aspect, a method for forming multinary metal chalcogenide semiconductor layers directly on a substrate from a solution of precursors, includes depositing a plurality of metal chalcogenide particles onto a substrate to form a precursor film A species containing a metal, chalcogen, or combination thereof is dissolved in a solution containing one or more solvents to form a liquid chalcogen medium. The precursor film is contacted with the liquid chalcogen medium at a temperature of at least 50 C to form a multinary metal chalcogenide thin film
摘要翻译：一方面，用于形成CIGSSe的薄膜的方法包括在衬底上沉积至少两层颗粒。至少一层包括具有由Cu（InI-xGax）（S1-ySey）2表示的化学组成的CIGSSe颗粒，其中0和nlE; x和nlE; 1和0＆amp; nlE; y＆nlE; 1。颗粒层单独地或组合地退火以形成具有沿着膜的深度的组成分布的CIGSSe薄膜。此外，一个或多个颗粒层也可以沉积在预先存在的吸收体上并退火以形成具有沿着膜深度的组成轮廓的膜根据期望的浓度分布，在合适的底物上沉积含有CIGSSe纳米颗粒（和/或任何其它颗粒）的薄膜前体层，然后在Se和/或S 可以使用高温下的含氮气氛将前体层转化为CIGSSe吸收膜。在另一方面，从前体溶液直接在基底上形成多金属硫族化物半导体层的方法包括沉积多个金属硫族化物颗粒在基材上形成前体膜A含有金属，硫族元素或其组合的物质是溶解的在含有一种或多种溶剂以形成液体硫属培养基的溶液中。前体膜与液态硫属培养基在至少50℃的温度下接触以形成多元金属硫族化物薄膜

56. 发明授权

US07829059B2 Rapid synthesis of ternary, binary and multinary chalcogenide nanoparticles 有权
标题翻译：三元，二元和多元硫族化物纳米粒子的快速合成
公开(公告)号：US07829059B2
公开(公告)日：2010-11-09
申请号：US12301317
申请日：2007-05-21
申请人： Qijie Guo , Rakesh Agrawal , Hugh W. Hillhouse
发明人： Qijie Guo , Rakesh Agrawal , Hugh W. Hillhouse
IPC分类号： C01B17/00 , C01B19/00
CPC分类号： C01G1/02 , B82Y30/00 , C01B19/002 , C01B19/007 , C01G1/12 , C01P2002/72 , C01P2002/84 , C01P2004/03 , C01P2004/04 , C01P2004/24 , C01P2004/64 , Y10S977/773 , Y10S977/774
摘要： A method for synthesizing a chalcogenide nanoparticle is provided. The method comprises reacting a metal component with an elemental chalcogen precursor in the presence of an organic solvent. The chalcogenide nanoparticles include ternary, binary and/or multinary chalcogenide nanoparticles and the metal component comprises metal halides or elemental metal precursors. The alkylamine solvent has a normal boiling temperature of above about 220° C. and an average particle size of from about 5 nm to about 1000 nm.
摘要翻译：提供了一种合成硫族化物纳米颗粒的方法。该方法包括在有机溶剂存在下使金属组分与元素硫族前体反应。硫族化物纳米颗粒包括三元，二元和/或多元硫族化物纳米颗粒，金属组分包括金属卤化物或元素金属前体。烷基胺溶剂的正常沸腾温度高于约220℃，平均粒度为约5nm至约1000nm。

57. 发明申请

US20100146054A1 Indicating Recent Content Publication Activity by a User 有权
标题翻译：指示用户的最近内容出版活动
公开(公告)号：US20100146054A1
公开(公告)日：2010-06-10
申请号：US12707159
申请日：2010-02-17
申请人： Christopher Armstrong , Alan Keister , Lark Dunham , Jennifer Granito , Steven Greenberg , Rakesh Agrawal , Michael Sommers , Carol A. Glover
发明人： Christopher Armstrong , Alan Keister , Lark Dunham , Jennifer Granito , Steven Greenberg , Rakesh Agrawal , Michael Sommers , Carol A. Glover
IPC分类号： G06F15/16
CPC分类号： H04L67/306 , G06F3/0482 , G06F17/30867 , G06F17/3089 , G06Q10/107 , G06Q50/01 , H04L51/04 , H04L51/32 , H04L65/403 , H04L67/02 , H04L67/26
摘要： Collecting and distributing information related to recent content publication activity of an instant messaging (IM) user provides other users in a network with timely, relevant information about people known to the user or within the same social network. A user participating in a social network can quickly and efficiently perceive new information related to other users (referred to as co-users) in a social network by reviewing the co-users' recent content publication activity. A user may be made able to do so without requiring the co-user to send a communication directly to the user regarding the new facts or new content, and also without requiring the user to actively browse or request information about the co-user.
摘要翻译：收集和分发与即时消息（IM）用户的近期内容发布活动相关的信息，向网络中的其他用户提供关于用户已知或在相同社交网络内的人的及时，相关的信息。参与社交网络的用户可以通过审查合作者最近的内容出版活动来快速有效地感知在社交网络中与其他用户（称为共同用户）相关的新信息。可以使用户能够这样做，而不需要共同用户直接向用户发送关于新事实或新内容的通信，并且还可以不要求用户主动地浏览或请求关于共同用户的信息。

58. 发明授权

US07702617B2 System and method for distributed querying and presentation of information from heterogeneous data sources 失效
标题翻译：用于从异构数据源分发查询和呈现信息的系统和方法
公开(公告)号：US07702617B2
公开(公告)日：2010-04-20
申请号：US10286300
申请日：2002-10-31
申请人： Rakesh Agrawal , Amit Somani
发明人： Rakesh Agrawal , Amit Somani
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06Q10/06 , G06Q30/0282
摘要： A method, system, business method, and computer program product for retrieving and organizing networked data, wherein fetch rules and extraction rules enable a user to automatically collect and extract information from a remote network site. The fetch rules reproduce the interaction a client executes if interacting directly with the remote site, so a server cannot be shut out. The extraction rules allow the client, preferably via an applet, to glean relevant information from the acquired pages for presentation in a general interface. As an electronic commerce business method, information about remote site responsiveness, fetch rules, and extraction rules may be shared between server and client for a fee. The server accumulates vendor contacts, stores query rules, and provides common interface rules. The invention can gather statistics on vendor responsiveness and can resell information to vendors or others.
摘要翻译：一种用于检索和组织网络数据的方法，系统，业务方法和计算机程序产品，其中获取规则和提取规则使得用户能够从远程网站自动收集和提取信息。获取规则重现客户端直接与远程站点交互时执行的交互，因此无法关闭服务器。提取规则允许客户端，优选地通过小应用程序从所获取的页面中收集相关信息，以便在通用接口中呈现。作为电子商务业务方法，有关远程站点响应，获取规则和提取规则的信息可能会在服务器和客户端之间共享一段费用。服务器累积供应商联系人，存储查询规则，并提供通用接口规则。本发明可以收集关于供应商响应能力的统计信息，并可以向供应商或其他人转售信息。

59. 发明申请

US20090313286A1 GENERATING TRAINING DATA FROM CLICK LOGS 审中-公开
标题翻译：从点击记录生成培训数据
公开(公告)号：US20090313286A1
公开(公告)日：2009-12-17
申请号：US12140272
申请日：2008-06-17
申请人： Nina Mishra , Rakesh Agrawal , Sreenivas Gollapudi , Alan Halverson , Krishnaram N. G. Kenthapadi , Rina Panigrahy , John C. Shafer , Panayiotis Tsaparas
发明人： Nina Mishra , Rakesh Agrawal , Sreenivas Gollapudi , Alan Halverson , Krishnaram N. G. Kenthapadi , Rina Panigrahy , John C. Shafer , Panayiotis Tsaparas
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F16/9535
摘要： Data from a click log may be used to generate training data for a search engine. The pages clicked as well as the pages skipped by a user may be used to assess the relevance of a page to a query. Labels for training data may be generated based on data from the click log. The labels may pertain to the relevance of a page to a query.
摘要翻译：来自点击日志的数据可用于生成搜索引擎的训练数据。可以使用点击的页面以及用户跳过的页面来评估页面与查询的相关性。可以根据点击日志的数据生成训练数据的标签。标签可能与页面与查询的相关性有关。

60. 发明授权

US07444132B2 Apparatus, and associated method, for facilitating dynamic filtering of a receive signal 有权
标题翻译：装置和相关方法，用于促进接收信号的动态滤波
公开(公告)号：US07444132B2
公开(公告)日：2008-10-28
申请号：US10407931
申请日：2003-04-04
申请人： Li Pan , Rakesh Agrawal
发明人： Li Pan , Rakesh Agrawal
IPC分类号： H04M11/00
CPC分类号： H04B1/123
摘要： Apparatus, and an associated method, for adaptively controlling filter characteristics of a filter forming part of a receive station, such as a mobile station operable in a cellular communication system. An adaptive parameter unit is provided with signal representations of signals that are to be applied to the filter element. The adaptive parameter unit, responsive to measurement or other analysis of the signal indicia, selects the filter characteristics to be exhibited by the filter. And, the filter characteristics are caused to be selected responsive thereto. Dynamic selection and reselection of the filter characteristics is effectuated in which the response time of the filter is minimized during good signal conditions and increased, to permit increased filter operations, during weak signal conditions.
摘要翻译：用于自适应地控制形成诸如在蜂窝通信系统中操作的移动站的接收站的一部分的滤波器的滤波器特性的装置和相关联的方法。自适应参数单元被提供有要施加到滤波器元件的信号的信号表示。响应于信号标记的测量或其他分析的自适应参数单元选择滤波器要呈现的滤波器特性。并且，响应于此而选择滤波器特性。实现了滤波器特性的动态选择和重新选择，其中滤波器的响应时间在良好的信号条件下被最小化并且在弱信号条件下增加以允许增加的滤波器操作。

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