公开(公告)号：US06457047B1

公开(公告)日：2002-09-24

申请号：US09566675

申请日：2000-05-08

申请人： Ashok Chandra ,  Neil LaTarche ,  Jianchang Mao ,  Prabhakar Raghavan

发明人： Ashok Chandra ,  Neil LaTarche ,  Jianchang Mao ,  Prabhakar Raghavan

IPC分类号： G06F15167

CPC分类号： G06F17/30902

摘要： An application caching system and method are provided wherein one or more applications may be cached throughout a distributed computer network. The system may include a central cache directory server, one or more distributed master application servers and one or more distributed application cache servers. The system may permit a service, such as a search, to be provided to the user more quickly.

摘要翻译： 提供了应用缓存系统和方法，其中可以在整个分布式计算机网络中缓存一个或多个应用。 该系统可以包括中央缓存目录服务器，一个或多个分布式主应用服务器和一个或多个分布式应用缓存服务器。 系统可以允许更快地向用户提供诸如搜索的服务。

公开(公告)号：US06738764B2

公开(公告)日：2004-05-18

申请号：US09851618

申请日：2001-05-08

申请人： Jianchang Mao ,  Mani Abrol ,  Rajat Mukherjee ,  Michel Tourn ,  Prabhakar Raghavan

发明人： Jianchang Mao ,  Mani Abrol ,  Rajat Mukherjee ,  Michel Tourn ,  Prabhakar Raghavan

IPC分类号： G06F1730

CPC分类号： G06F17/3069 ,  Y10S707/99933 ,  Y10S707/99934 ,  Y10S707/99935

摘要： A method of ranking search results includes producing a relevance score for a document in view of a query. A similarity score is calculated for the query utilizing a feature vector that characterizes attributes and query words associated with the document. A rank value is assigned to the document based upon the relevance score and the similarity score.

摘要翻译： 搜索结果排序的方法包括鉴于查询产生文档的相关性得分。 使用表征与文档相关联的属性和查询词的特征向量来计算查询的相似性得分。 基于相关性得分和相似度得分，将等级值分配给文档。

公开(公告)号：US06728704B2

公开(公告)日：2004-04-27

申请号：US09940600

申请日：2001-08-27

申请人： Jianchang Mao ,  Rajat Mukherjee ,  Prabhakar Raghavan ,  Panayiotis Tsaparas

发明人： Jianchang Mao ,  Rajat Mukherjee ,  Prabhakar Raghavan ,  Panayiotis Tsaparas

IPC分类号： G06F1730

CPC分类号： G06F17/30864 ,  Y10S707/99933

摘要： This invention includes the step of transmitting a query to a set of search engines. Any result lists returned from these search engines is received, and a subset of entries in each result list is selected. Each entry in this subset is assigned a scoring value according to a scoring function, and each result list is then assigned a representative value according to the scoring values assigned to its entries. A merged list of entries is produced based upon the representative value assigned to each result list.

摘要翻译： 本发明包括将查询发送到一组搜索引擎的步骤。 接收到从这些搜索引擎返回的任何结果列表，并且选择每个结果列表中的条目子集。 根据评分函数向该子集中的每个条目分配评分值，然后根据分配给其条目的评分值为每个结果列表分配代表值。 根据分配给每个结果列表的代表值生成合并的条目列表。

公开(公告)号：US20130085852A1

公开(公告)日：2013-04-04

申请号：US13252558

申请日：2011-10-04

申请人： Jianchang Mao

发明人： Jianchang Mao

IPC分类号： G06Q30/02

CPC分类号： G06Q10/107 ,  G06Q30/0251

摘要： Techniques are provided which improve deal and advertisement targeting of users. Methods and systems may detect if an email contains deal information related to one or more deals. If an email contains deal information, the deal information may be extracted. If the user clicks on a link in the email, one or more additional deals which may be similar or related to the one or more deals received in the email may be selected based at least in part on the extracted deal information. The additional deals and/or advertisements related to the additional deals may be targeted to the user via email or via the user's browser application.

摘要翻译： 提供了改进用户的交易和广告定位的技术。 方法和系统可以检测电子邮件是否包含与一个或多个交易相关的交易信息。 如果电子邮件包含交易信息，则可以提取交易信息。 如果用户点击电子邮件中的链接，则可以至少部分地基于所提取的交易信息来选择可能与电子邮件中接收的一个或多个交易相似或相关的一个或多个附加交易。 与额外交易有关的额外交易和/或广告可以通过电子邮件或通过用户的浏览器应用向用户定向。

公开(公告)号：US20130085845A1

公开(公告)日：2013-04-04

申请号：US13252471

申请日：2011-10-04

申请人： Jianchang Mao

发明人： Jianchang Mao

IPC分类号： G06Q30/02

CPC分类号： G06Q30/02 ,  G06Q10/107

摘要： Techniques are provided which improve deal and advertisement targeting of users, and which may include facilitating user comparison of deals. Methods and systems may detect if an email contains deal information related to one or more deals. If an email contains deal information, the deal information may be extracted. When the email is opened by the user, a link may be displayed on top of (e.g., overlaid on) the email. The link may be configured such that clicking on the link transmits a search query comprising the extracted deal information to a deal service. The deal service may retrieve one or more additional deals which may be similar or related to the one or more deals received in the email. The additional deals may be selected by the deal service based at least in part on the extracted deal information.

摘要翻译： 提供了改进用户的交易和广告定位的技术，其可以包括促进用户对交易的比较。 方法和系统可以检测电子邮件是否包含与一个或多个交易相关的交易信息。 如果电子邮件包含交易信息，则可以提取交易信息。 当用户打开电子邮件时，链接可能会显示在电子邮件的顶部（例如，覆盖）上。 链接可以被配置为使得点击链接将包括提取的交易信息的搜索查询发送到交易服务。 交易服务可以检索可能与电子邮件中接收的一个或多个交易相似或相关的一个或多个附加交易。 交易服务可以至少部分地基于提取的交易信息来选择附加交易。

公开(公告)号：US20120084142A1

公开(公告)日：2012-04-05

申请号：US12895773

申请日：2010-09-30

申请人： Wei Li ,  Ying Grace Cui ,  Ruofei Zhang ,  Jianchang Mao

发明人： Wei Li ,  Ying Grace Cui ,  Ruofei Zhang ,  Jianchang Mao

IPC分类号： G06Q30/00

CPC分类号： G06Q30/0247 ,  G06Q30/02 ,  G06Q30/0202

摘要： Techniques are provided for advertiser bid forecasting in online advertising, including display advertising. Methods are provided in which key targeting-related user segments are determined from bidding statistics. A feature set is extracted from an impression opportunity, based at least in part on the bidding statistics. A gradient boosting descent tree technique is utilized in determining an initial bid forecasting result. A linear regression-based model is used in post-tuning to arrive at a post-tuned result. For short-term forecasting, this may be the final result. For long-term forecasting, a hybrid approach may be utilized with further processing including utilization of a publisher-specific model.

摘要翻译： 提供技术用于在线广告中的广告客户出价预测，包括展示广告。 提供了根据投标统计确定与关键目标相关的用户细分的方法。 至少部分地基于出价统计信息，从展示机会中提取要素集。 在确定初始出价预测结果时，采用梯度提升下降树技术。 基于线性回归的模型用于后调整以得到后调整结果。 对于短期预测，这可能是最终结果。 对于长期预测，可以使用混合方法进一步处理，包括使用发布者特定模型。

公开(公告)号：US07761436B2

公开(公告)日：2010-07-20

申请号：US11325254

申请日：2006-01-03

申请人： Kenneth Norton ,  Chung-Man Tam ,  Jianchang Mao ,  Zhichen Xu ,  Adrienne Bassett ,  Ashley Hall ,  Nathan Arnold

发明人： Kenneth Norton ,  Chung-Man Tam ,  Jianchang Mao ,  Zhichen Xu ,  Adrienne Bassett ,  Ashley Hall ,  Nathan Arnold

IPC分类号： G06F7/00

CPC分类号： G06F17/30867 ,  G06F17/30997

摘要： A method for sharing content with a user includes receiving from a user a first set of keywords for annotating an annotated user; receiving from the user a second set of keywords that designate whether annotated content annotated by at least one keyword included in the second set of keywords may be shared with the annotated user; storing in a data store a first association of the first set of keywords with the annotated user, and a second association of the second set of keywords with the annotated user; receiving a keyword selection for a select keyword and an identifier for the annotated user; and displaying on the client system content annotated by the select keyword if the annotated user is annotated by at least one keyword in the first set of keywords, and if the select keyword is included in the second set of keywords.

摘要翻译： 用于与用户共享内容的方法包括从用户接收用于注释注释用户的第一组关键字; 从所述用户接收第二组关键字，所述第二组关键字指定由所述第二组关键字中包括的至少一个关键字注释的注释内容是否可以与所注注的用户共享; 在数据存储器中存储第一关键字集合与注释用户的第一关联，以及第二关键字集合与注释用户的第二关联; 接收关键字选择用于选择关键字和标注用户的标识符; 以及如果所述注释用户在所述第一组关键字中由至少一个关键字注释，并且所述选择关键字是否包括在所述第二组关键字中，则在所述客户端系统上显示由所述选择关键字注释的内容。

公开(公告)号：US07031909B2

公开(公告)日：2006-04-18

申请号：US10096048

申请日：2002-03-12

申请人： Jianchang Mao ,  Sumit Taank ,  Christina Chung ,  Alpha Luk

发明人： Jianchang Mao ,  Sumit Taank ,  Christina Chung ,  Alpha Luk

IPC分类号： G06F17/20 ,  G06F17/28

CPC分类号： G06F17/2775 ,  G06F17/2715 ,  G06F17/2785 ,  G06F17/2795 ,  G06F17/30705 ,  Y10S707/99933

摘要： The present invention provides a method, system and computer program for naming a cluster, or a hierarchy of clusters, of words and phrases that have been extracted from a set of documents. The invention takes these clusters as the input and generates appropriate labels for the clusters using a lexical database. Naming involves first finding out all possible word senses for all the words in the cluster, using the lexical database; and then augmenting each word sense with words that are semantically similar to that word sense to form respective definition vectors. Thereafter, word sense disambiguation is done to find out the most relevant sense for each word. Definition vectors are clustered into groups. Each group represents a concept. These concepts are thereafter ranked based on their support. Finally, a pre-specified number of words and phrases from the definition vectors of the dominant concepts are selected as labels, based on their generality in the lexical database. Therefore, the labels may not necessarily consist of the original words in the cluster. A hierarchy of clusters is named in a recursive fashion starting from leaf clusters. Dominant concepts in child clusters are propagated into their parent to reduce the labeling complexity of parent clusters.

公开(公告)号：US06327386B1

公开(公告)日：2001-12-04

申请号：US09635200

申请日：2000-08-09

申请人： Jianchang Mao ,  Matthias Zimmerman

发明人： Jianchang Mao ,  Matthias Zimmerman

IPC分类号： G06K962

CPC分类号： G06K9/00872

摘要： A method, apparatus, and article of manufacture employing lexicon reduction using key characters and a neural network, for recognizing a line of cursive text. Unambiguous parts of a cursive image, referred to as “key characters,” are identified. If the level of confidence that a segment of a line of cursive text is a particular character is higher than a threshold, and is also sufficiently higher than the level of confidence of neighboring segments, then the character is designated as a key character candidate. Key character candidates are then screened using geometric information. The key character candidates that pass the screening are designated key characters. Two-stages of lexicon reduction are employed. The first stage of lexicon reduction uses a neural network to estimate a lower bound and an upper bound of the number of characters in a line of cursive text. Lexicon entries having a total number of characters outside of the bounds are eliminated. For the second stage of lexicon reduction, the lexicon is fitter reduced by comparing character strings using the key characters, with lexicon entries. For each of the key characters in the character strings, it is determined whether there is a mismatch between the key character and characters in a corresponding search range in the lexicon entry. If the number of mismatches for all of the key characters in a search string is greater than (1+(the number of key characters in the search string/4)), then the lexicon entry is eliminated. Accordingly, the invention advantageously accomplishes lexicon reduction, thereby decreasing the time required to recognize a line of cursive text, without reducing accuracy.

摘要翻译： 一种使用关键字符和神经网络来进行词典缩减的方法，装置和制品，用于识别草书文本。 识别草书图像的明确部分，称为“关键字符”。 如果一行草图文本的一段是特定字符的置信度高于阈值，并且也足够高于相邻段的置信度，则该字符被指定为关键字符候选。 然后使用几何信息对关键字候选进行筛选。 通过筛选的关键角色候选人被指定为关键角色。 采用两个阶段的词典缩小。 词典缩减的第一阶段使用神经网络来估计草图文本行中的字符数的下限和上限。 消除了界限外的字符总数的词典条目。 对于词典缩减的第二阶段，通过使用关键字符与词典条目比较字符串来缩小词典。 对于字符串中的每个关键字符，确定在词典条目中的相应搜索范围中的关键字符和字符之间是否存在不匹配。 如果搜索字符串中所有关键字符的匹配数量大于（1+（搜索字符串/ 4中的关键字符数）），则排除词典条目。 因此，本发明有利地实现词典缩减，从而减少了识别草稿文本行所需的时间，而不降低精确度。

公开(公告)号：US5835633A

公开(公告)日：1998-11-10

申请号：US561509

申请日：1995-11-20

申请人： Tetsunosuke Fujisaki ,  Jianchang Mao ,  Kottappuram Mohamedali Mohiuddin

发明人： Tetsunosuke Fujisaki ,  Jianchang Mao ,  Kottappuram Mohamedali Mohiuddin

IPC分类号： G06K9/62 ,  G06K9/68 ,  G06K9/00

CPC分类号： G06K9/6292 ,  G06K9/6293 ,  G06K9/6807 ,  G06K9/6857

摘要： A multi-stage multi-network character recognition system decomposes the estimation of a posteriori probabilities into coarse-to-fine stages. Classification is then based on the estimated a posteriori probabilities. This classification process is especially suitable for the tasks that involve a large number of categories. The multi-network system is implemented in two stages: a soft pre-classifier and a bank of multiple specialized networks. The pre-classifier performs coarse evaluation of the input character, developing different probabilities that the input character falls into different predefined character groups. The bank of specialized networks, each corresponding to a single group of characters, performs fine evaluation of the input character, where each develops different probabilities that the input character represents each character in that specialized network's respective predefined character group. A network selector is employed to increase the system's efficiency by selectively invoking certain specialized networks selected, using a combination of prior external information and outputs of the pre-classifier. Relative to known single network or one-stage multiple network recognition systems, the invention provides improved recognition, accuracy, confidence measure, speed, and flexibility.

摘要翻译： 多级多网络字符识别系统将后验概率的估计分解为粗略到精细阶段。 然后根据估计的后验概率分类。 这种分类过程特别适用于涉及大量类别的任务。 多网络系统分为两个阶段：软预分类器和多个专用网络组。 预分类器对输入字符进行粗略评估，发展输入字符落入不同预定义字符组的不同概率。 专用网络的每一行对应于单个字符组，对输入字符进行精细评估，其中每个字符都产生不同的概率，即输入字符表示专用网络各自的预定义字符组中的每个字符。 采用网络选择器来通过使用先前的外部信息和预分类器的输出的组合选择性地调用所选择的某些专用网络来提高系统的效率。 相对于已知的单网络或一级多网络识别系统，本发明提供了改进的识别，准确性，可信度测量，速度和灵活性。