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. 发明授权

US07693865B2 Techniques for navigational query identification 有权
标题翻译：导航查询识别技术
公开(公告)号：US07693865B2
公开(公告)日：2010-04-06
申请号：US11514076
申请日：2006-08-30
申请人： Yumao Lu , Fuchun Peng , Xin Li , Nawaaz Ahmed
发明人： Yumao Lu , Fuchun Peng , Xin Li , Nawaaz Ahmed
IPC分类号： G06F17/00
CPC分类号： G06K9/623 , G06F17/30707 , G06F17/30864 , G06K9/6278
摘要： To accurately classify a query as navigational, thousands of available features are explored, extracted from major commercial search engine results, user Web search click data, query log, and the whole Web's relational content. To obtain the most useful features for navigational query identification, a three level system is used which integrates feature generation, feature integration, and feature selection in a pipeline. Because feature selection plays a key role in classification methodologies, the best feature selection method is coupled with the best classification approach to achieve the best performance for identifying navigational queries. According to one embodiment, linear Support Vector Machine (SVM) is used to rank features and the top ranked features are fed into a Stochastic Gradient Boosting Tree (SGBT) classification method for identifying whether or not a particular query is a navigational query.
摘要翻译：为了将查询精确地分类为导航，从主要商业搜索引擎结果，用户Web搜索点击数据，查询日志和整个Web的关系内容中提取出数千种可用功能。为了获得导航查询识别最有用的功能，使用了一个三级系统，将特征生成，特征集成和特征选择集成在一条流水线中。因为特征选择在分类方法中起着关键作用，因此最好的特征选择方法与最佳分类方法相结合，以实现识别导航查询的最佳性能。根据一个实施例，使用线性支持向量机（SVM）对特征进行排序，并且将顶级特征馈送到用于识别特定查询是否是导航查询的随机渐变增强树（SGBT）分类方法中。

2. 发明申请

US20090132515A1 Method and Apparatus for Performing Multi-Phase Ranking of Web Search Results by Re-Ranking Results Using Feature and Label Calibration 审中-公开
标题翻译：通过使用特征和标签校准重新排列结果来执行网页搜索结果的多阶段排序的方法和装置
公开(公告)号：US20090132515A1
公开(公告)日：2009-05-21
申请号：US11942410
申请日：2007-11-19
申请人： Yumao Lu , Fuchun Peng , Xin Li , Nawaaz Ahmed
发明人： Yumao Lu , Fuchun Peng , Xin Li , Nawaaz Ahmed
IPC分类号： G06F17/30
CPC分类号： G06F16/951 , G06F16/335
摘要： A method and apparatus for performing multi-phase ranking of web search results by re-ranking results using feature and label calibration are provided. According to one embodiment of the invention, a ranking function is trained by using machine learning techniques on a set of training samples to produce ranking scores. The ranking function is used to rank the set of training samples according to its ranking score, in order of its relevance to a particular query. Next, a re-ranking function is trained by the same training samples to re-rank the documents from the first ranking. The features and labels of the training samples are calibrated and normalized before they are reused to train the re-ranking function. By this method, training data and training features used in past trainings are leveraged to perform additional training of new functions, without requiring the use of additional training data or features.
摘要翻译：提供了一种通过使用特征和标签校准重新排列结果来执行网络搜索结果的多阶段排序的方法和装置。根据本发明的一个实施例，通过在一组训练样本上使用机器学习技术来训练排名功能以产生排名分数。排序函数用于根据其与特定查询的相关性，根据其排名得分对训练样本集进行排序。接下来，通过相同的训练样本来训练重新排序功能以从第一等级重新排列文档。培训样本的特征和标签在重新使用之前进行校准和归一化，以训练重新排序功能。通过这种方法，可以利用过去培训中使用的训练数据和训练特征来执行新功能的附加训练，而不需要使用额外的训练数据或特征。

3. 发明申请

US20080189262A1 Word pluralization handling in query for web search 有权
标题翻译：在Web搜索查询中的Word复数处理
公开(公告)号：US20080189262A1
公开(公告)日：2008-08-07
申请号：US11701736
申请日：2007-02-01
申请人： Fuchun Peng , Nawaaz Ahmed , Xin Li , Yumao Lu
发明人： Fuchun Peng , Nawaaz Ahmed , Xin Li , Yumao Lu
IPC分类号： G06F17/30
CPC分类号： G06F17/30864
摘要： Techniques for determining when and how to transform words in a query to its plural or non-plural form in order to provide the most relevant search results while minimizing computational overhead are provided. A dictionary is generated based upon the words used in a specified number of previous most frequent search queries and comprises lists of transformations from plural to singular and singular to plural. Unnecessary transformations are removed from the dictionary based upon language modeling. The word to transform is determined by finding the last non-stop re-writable word of the query. The context of the transformed word is confirmed in the search documents and a version of the query is executed using both the original form of the word and the transformation of the word.
摘要翻译：提供了用于确定何时以及如何将查询中的单词转换为多个或非复数形式的技术，以便在最小化计算开销的同时提供最相关的搜索结果。基于在指定数量的先前最频繁的搜索查询中使用的词来生成字典，并且包括从多个到单数和单数到多个的变换的列表。基于语言建模，从字典中删除不必要的转换。要转换的词是通过查找查询的最后一个不间断的可重写词来确定的。在搜索文档中确认转换词的上下文，并且使用单词的原始形式和单词的转换来执行查询的版本。

4. 发明授权

US07996410B2 Word pluralization handling in query for web search 有权
标题翻译：在Web搜索查询中的Word复数处理
公开(公告)号：US07996410B2
公开(公告)日：2011-08-09
申请号：US11701736
申请日：2007-02-01
申请人： Fuchun Peng , Nawaaz Ahmed , Xin Li , Yumao Lu
发明人： Fuchun Peng , Nawaaz Ahmed , Xin Li , Yumao Lu
IPC分类号： G06F7/00
CPC分类号： G06F17/30864
摘要： Techniques for determining when and how to transform words in a query to its plural or non-plural form in order to provide the most relevant search results while minimizing computational overhead are provided. A dictionary is generated based upon the words used in a specified number of previous most frequent search queries and comprises lists of transformations from plural to singular and singular to plural. Unnecessary transformations are removed from the dictionary based upon language modeling. The word to transform is determined by finding the last non-stop re-writable word of the query. The context of the transformed word is confirmed in the search documents and a version of the query is executed using both the original form of the word and the transformation of the word.
摘要翻译：提供了用于确定何时以及如何将查询中的单词转换为多个或非复数形式的技术，以便在最小化计算开销的同时提供最相关的搜索结果。基于在指定数量的先前最频繁的搜索查询中使用的词来生成字典，并且包括从多个到单数和单数到多个的变换的列表。基于语言建模，从字典中删除不必要的转换。要转换的词是通过查找查询的最后一个不间断的可重写词来确定的。在搜索文档中确认转换词的上下文，并且使用单词的原始形式和单词的转换来执行查询的版本。

5. 发明授权

US07630978B2 Query rewriting with spell correction suggestions using a generated set of query features 有权
标题翻译：使用生成的查询功能集查询重写拼写修正建议
公开(公告)号：US07630978B2
公开(公告)日：2009-12-08
申请号：US11639492
申请日：2006-12-14
申请人： Xin Li , Nawaaz Ahmed , Fuchun Peng , Yumao Lu
发明人： Xin Li , Nawaaz Ahmed , Fuchun Peng , Yumao Lu
IPC分类号： G06F17/30
CPC分类号： G06F17/30672 , Y10S707/99933 , Y10S707/99935
摘要： Techniques for rewriting queries submitted to a query engine are provided. A query is submitted by a user and sent to a search mechanism. Based on the query, one or more query suggestions are generated. Features are generated based on the query and the query suggestions. Those features are input to a trained machine learning mechanism that generates a rewrite score. The rewrite score signifies a confidence score that indicates how confident the search mechanism is that the user intended to submit the original query. If the rewrite score is below a certain threshold, then the original query is rewritten to a second query. Results of executing the original query may be sent to the user along with a reference to the second query. Additionally or alternatively, results of executing the second query are sent to the user.
摘要翻译：提供了重写提交到查询引擎的查询的技术。查询由用户提交并发送到搜索机制。基于该查询，生成一个或多个查询建议。功能根据查询和查询建议生成。这些功能被输入到产生重写分数的训练有素的机器学习机制。重写分数表示置信度分数，表示用户希望提交原始查询的搜索机制的信心。如果重写分数低于某个阈值，则原始查询被重写为第二个查询。执行原始查询的结果可以与对第二个查询的引用一起发送给用户。另外或替代地，执行第二查询的结果被发送给用户。

6. 发明申请

US20080147637A1 Query rewriting with spell correction suggestions 有权
标题翻译：使用拼写修正建议查询重写
公开(公告)号：US20080147637A1
公开(公告)日：2008-06-19
申请号：US11639492
申请日：2006-12-14
申请人： Xin Li , Nawaaz Ahmed , Fuchun Peng , Yumao Lu
发明人： Xin Li , Nawaaz Ahmed , Fuchun Peng , Yumao Lu
IPC分类号： G06F17/30
CPC分类号： G06F17/30672 , Y10S707/99933 , Y10S707/99935
摘要： Techniques for rewriting queries submitted to a query engine are provided. A query is submitted by a user and sent to a search mechanism. Based on the query, one or more query suggestions are generated. Features are generated based on the query and the query suggestions. Those features are input to a trained machine learning mechanism that generates a rewrite score. The rewrite score signifies a confidence score that indicates how confident the search mechanism is that the user intended to submit the original query. If the rewrite score is below a certain threshold, then the original query is rewritten to a second query. Results of executing the original query may be sent to the user along with a reference to the second query. Additionally or alternatively, results of executing the second query are sent to the user.
摘要翻译：提供了重写提交到查询引擎的查询的技术。查询由用户提交并发送到搜索机制。基于该查询，生成一个或多个查询建议。功能根据查询和查询建议生成。这些功能被输入到产生重写分数的训练有素的机器学习机制。重写分数表示置信度分数，表示用户希望提交原始查询的搜索机制的信心。如果重写分数低于某个阈值，则原始查询被重写为第二个查询。执行原始查询的结果可以与对第二个查询的引用一起发送给用户。另外或替代地，执行第二查询的结果被发送给用户。

7. 发明申请

US20080059508A1 Techniques for navigational query identification 有权
标题翻译：导航查询识别技术
公开(公告)号：US20080059508A1
公开(公告)日：2008-03-06
申请号：US11514076
申请日：2006-08-30
申请人： Yumao Lu , Fuchun Peng , Xin Li , Nawaaz Ahmed
发明人： Yumao Lu , Fuchun Peng , Xin Li , Nawaaz Ahmed
IPC分类号： G06F17/00
CPC分类号： G06K9/623 , G06F17/30707 , G06F17/30864 , G06K9/6278
摘要： To accurately classify a query as navigational, thousands of available features are explored, extracted from major commercial search engine results, user Web search click data, query log, and the whole Web's relational content. To obtain the most useful features for navigational query identification, a three level system is used which integrates feature generation, feature integration, and feature selection in a pipeline. Because feature selection plays a key role in classification methodologies, the best feature selection method is coupled with the best classification approach to achieve the best performance for identifying navigational queries. According to one embodiment, linear Support Vector Machine (SVM) is used to rank features and the top ranked features are fed into a Stochastic Gradient Boosting Tree (SGBT) classification method for identifying whether or not a particular query is a navigational query.
摘要翻译：为了将查询精确地分类为导航，从主要商业搜索引擎结果，用户Web搜索点击数据，查询日志和整个Web的关系内容中提取出数千种可用功能。为了获得导航查询识别最有用的功能，使用了一个三级系统，将特征生成，特征集成和特征选择集成在一条流水线中。因为特征选择在分类方法中起着关键作用，因此最好的特征选择方法与最佳分类方法相结合，以实现识别导航查询的最佳性能。根据一个实施例，使用线性支持向量机（SVM）对特征进行排序，并且将顶级特征馈送到用于识别特定查询是否是导航查询的随机渐变增强树（SGBT）分类方法中。

8. 发明申请

US20100191758A1 SYSTEM AND METHOD FOR IMPROVED SEARCH RELEVANCE USING PROXIMITY BOOSTING 审中-公开
标题翻译：使用接近推进来改进搜索相关性的系统和方法
公开(公告)号：US20100191758A1
公开(公告)日：2010-07-29
申请号：US12360008
申请日：2009-01-26
申请人： Fuchun Peng , Xing Wei , Yumao Lu , Xin Li , Donald Metzler , Hang Cui , Benoit Dumoulin
发明人： Fuchun Peng , Xing Wei , Yumao Lu , Xin Li , Donald Metzler , Hang Cui , Benoit Dumoulin
IPC分类号： G06F17/30
CPC分类号： G06F16/951 , G06F16/353
摘要： A system and method for improved search relevance using proximity boosting. A query for a web search is received from a user, via a network, wherein the query comprises a plurality of query tokens. One or more concepts are identified in the query wherein each of concepts comprises at least two query tokens. A relative concept strength is determined for each of the identified concepts. The query is then rewritten for submission to a search engine wherein for each of the one or more concepts, a syntax rule associated with the respective relative concept strength of the concept is applied to the query tokens comprising the concept such that the rewritten query represents the one or more concepts whereby the proximity of the one or more concepts in a search result returned by the search engine to the user in response to the rewritten query is boosted.
摘要翻译：一种使用邻近度增强来提高搜索相关性的系统和方法。从用户经由网络接收到针对web搜索的查询，其中所述查询包括多个查询令牌。在查询中识别一个或多个概念，其中每个概念包括至少两个查询令牌。确定每个识别的概念的相对概念强度。然后，该查询被重写以提交给搜索引擎，其中对于一个或多个概念中的每一个，与概念的相应相对概念强度相关联的语法规则被应用于包括概念的查询令牌，使得重写的查询表示提高了一个或多个概念，由此响应于重写的查询，搜索引擎向用户返回的搜索结果中的一个或多个概念的接近度被提升。

9. 发明申请

US20150270751A1 ROTORS WITH SEGMENTED MAGNET CONFIGURATIONS AND RELATED DYNAMOELECTRIC MACHINES AND COMPRESSORS 有权
标题翻译：带有分段磁铁配置的转子和相关的动态电机和压缩机
公开(公告)号：US20150270751A1
公开(公告)日：2015-09-24
申请号：US14428296
申请日：2012-09-29
申请人： Pingshan CAO , Xin LI , Xin LI , EMERSON ELECTRIC CO.
发明人： Pingshan Cao , Xin Li , Xin Li
IPC分类号： H02K1/27 , F04D25/02 , F04D25/06 , H02K1/02
CPC分类号： H02K1/2773 , F04D25/026 , F04D25/06 , H02K1/02
摘要： A rotor for a dynamoelectric machine includes a rotor core having an outer periphery and at least a first set of magnets positioned within the outer periphery of the rotor core. The first set of magnets includes at least two block magnets and an arc magnet. The block magnets have a substantially parallel magnetization pattern and the arc magnet has a substantially radial magnetization pattern. The arc magnet has a concave surface facing the outer periphery of the rotor core. The first set of magnets defines a pole of the rotor. Rotors with other magnet configurations, and dynamoelectric machines and compressors incorporating such rotors, are also disclosed.
摘要翻译：一种用于电动机的转子包括具有外周边的转子芯和至少位于转子芯的外圆周内的第一组磁体。第一组磁体包括至少两个块磁体和电弧磁体。块状磁体具有基本平行的磁化模式，并且电弧磁体具有基本上径向的磁化模式。电弧磁体具有面向转子芯的外周的凹面。第一组磁体限定了转子的极点。还公开了具有其它磁体配置的转子，以及包含这种转子的电动机器和压缩机。

10. 发明申请

US20220211334A1 SCINTILLATION DETECTOR BASED SYSTEMS AND METHODS FOR USING THE SAME 有权
公开(公告)号：US20220211334A1
公开(公告)日：2022-07-07
申请号：US17700442
申请日：2022-03-21
申请人： Lars Furenlid , Xin Li
发明人： Lars Furenlid , Xin Li
IPC分类号： A61B6/03 , G01T1/202 , G01T1/20 , A61B6/00
摘要： A scintillation-crystal based gamma-ray detector with photon sensors disposed on edge surface(s) of the crystal to take advantage of total internal reflection of scintillation photons within the thin-slab detector substrate to improve spatial resolution of determination of a scintillation event (including depth-of-interaction resolution) while preserving energy resolution and detection efficiency. The proposed structure benefits from the reduced—as compared with related art—total number of readout channels elimination of need in complicated and repetitive cutting and polishing operations to form pixelated crystal arrays used in conventional PET detector modules. Detectors systems utilizing stacks of such detectors, and methods of operation of same.

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