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

US08954357B2 Multi-task machine learning using features bagging and local relatedness in the instance space 有权
标题翻译：多任务机器学习使用功能包装和局部相关性在实例空间
公开(公告)号：US08954357B2
公开(公告)日：2015-02-10
申请号：US13106105
申请日：2011-05-12
申请人： Jean-Baptiste Faddoul , Boris Chidlovskii
发明人： Jean-Baptiste Faddoul , Boris Chidlovskii
IPC分类号： G06F15/18 , G06N99/00
CPC分类号： G06N99/005
摘要： A multi-task machine learning component learns a set of tasks comprising two or more different tasks based on a set of examples. The examples are represented by features of a set of features. The multi-task machine learning component comprises a digital processing device configured to learn an ensemble of base rules wherein each base rule is learned for a sub-set of the set of features and comprises a multi-task decision tree (MT-DT) having nodes comprising decision rules for tasks of the set of tasks. An inference component comprises a digital processing device configured to predict a result for at least one task of the set of tasks for an input item represented by features of the set of features using the learned ensemble of base rules.
摘要翻译：多任务机器学习组件基于一组示例学习包括两个或多个不同任务的一组任务。这些例子由一组特征的特征表示。多任务机器学习部件包括被配置为学习基本规则的集合的数字处理设备，其中为该特征集合的子集学习每个基本规则，并且包括具有多任务决策树（MT-DT）的多任务决策树（MT-DT），其具有节点包括用于该组任务的任务的决策规则。推理组件包括数字处理设备，该数字处理设备被配置为使用所学习的基本规则的集合来预测由所述特征集合的特征所表示的输入项目的所述任务集合中的至少一个任务的结果。

2. 发明申请

US20140012637A1 TRAFFIC DELAY DETECTION BY MINING TICKET VALIDATION TRANSACTIONS 审中-公开
标题翻译：通过采购门票验证交易进行交通延迟检测
公开(公告)号：US20140012637A1
公开(公告)日：2014-01-09
申请号：US13553614
申请日：2012-07-19
申请人： Boris Chidlovskii , Eduardo Cárdenas Sánchez
发明人： Boris Chidlovskii , Eduardo Cárdenas Sánchez
IPC分类号： G06Q50/30
CPC分类号： G08G1/0112 , G07B15/02 , G08G1/0116 , G08G1/0133 , G08G1/0141 , G08G1/123
摘要： A method, system and processor-readable medium for detecting traffic delays A transfer time sample can be analyzed from ticketing data (e.g., ticket validation timestamps) that includes data indicative of a plurality of stops. An optimal set of stop pairs can be selected from among the plurality of stops based on a plurality of factors including a coverage, a volume and a distance between at least two stops among the plurality of stops. A structural outlier associated with the transfer time sample can be then detected in order to detect traffic delays determined from the optimal set of stop pairs selected from among the plurality of stops. Note that such a structural outlier can comprise an outlier in a spatio-temporal series collected from the transfer time sample.
摘要翻译：用于检测交通延迟的方法，系统和处理器可读介质可以从包括指示多个停靠点的数据的票据数据（例如，票证验证时间戳）来分析传送时间样本。可以基于包括多个停靠点中的至少两个停止点之间的覆盖范围，音量和距离的多个因素从多个停止中选择最佳的一组停止对。然后可以检测与传送时间样本相关联的结构异常值，以便检测从从多个停止点中选择的最佳停止对集合确定的业务延迟。注意，这种结构异常值可以包括从传送时间样本收集的时空序列中的异常值。

3. 发明授权

US08417708B2 Average case analysis for efficient spatial data structures 有权
标题翻译：高效空间数据结构的平均案例分析
公开(公告)号：US08417708B2
公开(公告)日：2013-04-09
申请号：US12367638
申请日：2009-02-09
申请人： Boris Chidlovskii
发明人： Boris Chidlovskii
IPC分类号： G06F7/00
CPC分类号： G06F17/30241
摘要： A computer performed method models a spatial index having n spatial regions defined in a multidimensional space using a tree-based model representing an infinite number of arrangements of n spatial regions in the multidimensional space allowable by the spatial index using a finite number of tree representations, computes an average retrieval complexity measure for content retrieval using the spatial index based on the tree based model, and provides a spatial index recommendation based on the average retrieval complexity measure. In some embodiments a spatial index selection module selects the spatial index based on average retrieval complexity measures for candidate spatial indices that are functionally dependent upon a number of spatial regions to be defined by the spatial index.
摘要翻译：计算机执行的方法使用基于树的模型对具有在多维空间中定义的n个空间区域的空间索引进行建模，该模型表示使用有限数量的树表示在空间索引允许的多维空间中的n个空间区域的无限数量的排列，使用基于树的模型，使用空间索引计算内容检索的平均检索复杂度度量，并提供基于平均检索复杂度度量的空间索引推荐。在一些实施例中，空间索引选择模块基于功能上取决于要由空间索引定义的空间区域的数量的候选空间索引的平均检索复杂度度量来选择空间索引。

4. 发明申请

US20120226651A1 SYSTEM AND METHOD FOR RECOMMENDING ITEMS IN MULTI-RELATIONAL ENVIRONMENTS 有权
标题翻译：在多个环境中建议项目的系统和方法
公开(公告)号：US20120226651A1
公开(公告)日：2012-09-06
申请号：US13040005
申请日：2011-03-03
申请人： Boris Chidlovskii
发明人： Boris Chidlovskii
IPC分类号： G06N5/02
CPC分类号： G06Q10/10
摘要： A system, method, and computer program product for making a recommendation to a user of a social network to associate an existing tag with a social media entity instance are provided. The method includes generating a random walk model that includes the social media entity instance for at least a portion of the social network, determining weighted values for the random walk model, generating a weighted random walk model based on the random walk model and the weighted values, performing a random walk on the weighted random walk model starting at the social media entity instance, and recommending an existing tag to the user based on the random walk.
摘要翻译：提供了一种用于向社交网络的用户推荐将现有标签与社交媒体实体实例相关联的系统，方法和计算机程序产品。该方法包括生成随机游走模型，其包括用于社交网络的至少一部分的社交媒体实体实例，确定随机游走模型的加权值，基于随机游走模型生成加权随机游走模型和加权值在社交媒体实体开始的加权随机游走模型上执行随机游走，并且基于随机游走向用户推荐现有标签。

5. 发明申请

US20090271338A1 SCALABLE FEATURE SELECTION FOR MULTI-CLASS PROBLEMS 有权
标题翻译：多级问题的可选特征选择
公开(公告)号：US20090271338A1
公开(公告)日：2009-10-29
申请号：US12107875
申请日：2008-04-23
申请人： Boris Chidlovskii , Loic Lecerf
发明人： Boris Chidlovskii , Loic Lecerf
IPC分类号： G06F15/18
CPC分类号： G06N99/005
摘要： In a feature filtering approach, a set of relevant features and a set of training objects classified respective to a set of classes are provided. A candidate feature and a second feature are selected from the set of relevant features. An approximate Markov blanket criterion is computed that is indicative of whether the candidate feature is redundant in view of the second feature. The approximate Markov blanket criterion includes at least one dependency on less than the entire set of classes. An optimized set of relevant features is defined, consisting of a sub-set of the set of relevant features from which features indicated as redundant by the selecting and computing are removed.
摘要翻译：在特征过滤方法中，提供了一组相关特征和一组分类为一类的训练对象。从相关特征集中选择候选特征和第二特征。计算一个近似的马尔科夫毯标准，其指示考虑到第二特征的候选特征是否是冗余的。马尔可夫近似值标准包括至少一个依赖于小于整个类的整体。定义了一组优化的相关特征，其中包括一组相关特征的子集，通过选择和计算表示为冗余的特征被去除。

6. 发明申请

US20090157572A1 STACKED GENERALIZATION LEARNING FOR DOCUMENT ANNOTATION 失效
标题翻译：用于文件说明的堆叠式通用学习
公开(公告)号：US20090157572A1
公开(公告)日：2009-06-18
申请号：US11954484
申请日：2007-12-12
申请人： Boris Chidlovskii
发明人： Boris Chidlovskii
IPC分类号： G06F15/18 , G06N7/00
CPC分类号： G06N99/005
摘要： A document annotation method includes modeling data elements of an input document and dependencies between the data elements as a dependency network. Static features of at least some of the data elements are defined, each expressing a relationship between a characteristic of the data element and its label. Dynamic features are defined which define links between an element and labels of the element and of a second element. Parameters of a collective probabilistic model for the document are learned, each expressing a conditional probability that a first data element should be labeled with information derived from a label of a neighbor data element linked to the first data element by a dynamic feature. The learning includes decomposing a globally trained model into a set of local learning models. The local learning models each employ static features to generate estimations of the neighbor element labels for at least one of the data elements.
摘要翻译：文档注释方法包括建模输入文档的数据元素和作为依赖网络的数据元素之间的依赖关系。定义至少一些数据元素的静态特征，每个数据元素表示数据元素的特征与其标签之间的关系。定义了动态特征，其定义元素和元素和第二元素的标签之间的链接。学习用于文档的集体概率模型的参数，每个表示一个条件概率，其中第一数据元素应该被通过动态特征从与第一数据元素链接的邻居数据元素的标签导出的信息标记。学习包括将全球训练的模型分解为一组本地学习模型。本地学习模型每个采用静态特征来生成至少一个数据元素的相邻元素标签的估计。

7. 发明申请

US20060101058A1 System and method for transforming legacy documents into XML documents 有权
标题翻译：将遗留文档转换为XML文档的系统和方法
公开(公告)号：US20060101058A1
公开(公告)日：2006-05-11
申请号：US10986490
申请日：2004-11-10
申请人： Boris Chidlovskii
发明人： Boris Chidlovskii
IPC分类号： G06F17/00 , G06F7/00
CPC分类号： G06F17/3092 , G06F17/2247 , G06F17/227 , Y10S707/99943
摘要： A method for converting a legacy document into an XML document, includes decomposing the conversion process into a plurality of individual conversion tasks. A legacy document is decomposed into a plurality of document portions. A target XML schema including a plurality of schema components is provided. Local schema are generated from the target XML schema, wherein each local schema includes at least one of the schema components in the target XML schema. A plurality of conversion tasks is generated by associating a local schema and an applicable document portion, wherein each conversion task associates data from the applicable document portion with the applicable schema component in the local schema. For each conversion task, a conversion method is selected and the conversion method is performed on the applicable document portion and local schema. Finally, the results of all the individual conversion tasks are assembled into a target XML document.
摘要翻译：将遗留文档转换为XML文档的方法包括将转换处理分解为多个单独的转换任务。遗留文档被分解成多个文档部分。提供了包括多个模式组件的目标XML模式。本地模式是从目标XML模式生成的，其中每个本地模式都包含目标XML模式中的至少一个模式组件。通过将本地模式和可应用文档部分相关联来生成多个转换任务，其中每个转换任务将来自可应用文档部分的数据与本地模式中的可应用模式组件相关联。对于每个转换任务，选择转换方法，并对适用的文档部分和本地模式执行转换方法。最后，将所有单个转换任务的结果汇总到目标XML文档中。

8. 发明授权

US07007017B2 Method for automatic discovery of query language features of web sites 失效
标题翻译：自动发现网站查询语言功能的方法
公开(公告)号：US07007017B2
公开(公告)日：2006-02-28
申请号：US10361955
申请日：2003-02-10
申请人： Andre Bergholz , Boris Chidlovskii
发明人： Andre Bergholz , Boris Chidlovskii
IPC分类号： G06F17/30
CPC分类号： G06F17/30864 , Y10S707/99934 , Y10S707/99935
摘要： A method for automatically determining query language operators of a Web information source, includes providing a set of known query operators, each known query operator in the set operating according to at least one syntax, wherein for a test query comprising a query operator and a test key word, each syntax of the operator produces a different number of document matches for the test query at a known Web information source; performing the test query on the Web information source, wherein the test query produces a number of document matches on the Web information source; comparing the number of document matches produced by the Web information source with the number of document matches produced by the known operator's different syntaxes; and using an established criteria for determining if comparing results indicate the Web information source supports the known query operator according its matching syntax.
摘要翻译：一种用于自动确定Web信息源的查询语言运算符的方法，包括提供一组已知的查询运算符，所述集合中的每个已知查询运算符根据至少一种语法操作，其中对于包括查询运算符和测试的测试查询关键字，操作员的每个语法在已知的Web信息源处产生用于测试查询的不同数量的文档匹配; 在Web信息源上执行测试查询，其中测试查询在Web信息源上产生多个文档匹配; 将由Web信息源生成的文档匹配的数量与由已知运算符的不同语法产生的文档匹配的数量进行比较; 并且使用建立的标准来确定比较结果是否表明Web信息源根据其匹配语法来支持已知的查询运算符。

9. 发明申请

US20050154979A1 Systems and methods for converting legacy and proprietary documents into extended mark-up language format 失效
标题翻译：将传统和专有文档转换为扩展标记语言格式的系统和方法
公开(公告)号：US20050154979A1
公开(公告)日：2005-07-14
申请号：US10756313
申请日：2004-01-14
申请人： Boris Chidlovskii , Herve Dejean
发明人： Boris Chidlovskii , Herve Dejean
IPC分类号： G06F17/22 , G06F17/30 , G06F17/24 , G06F17/21
CPC分类号： G06F17/30914 , G06F17/227
摘要： A system and method that converts legacy and proprietary documents into extended mark-up language format which treats the conversion as transforming ordered trees of one schema and/or model into ordered trees of another schema and/or model. In embodiments, the tree transformers are coded using a learning method that decomposes the converting task into three components which include path re-labeling, structural composition and input tree traversal, each of which involves learning approaches. The transformation of an input tree into an output tree may involve labeling components in the input tree with valid labels or paths from a particular output schema, composing the labeled elements into the output tree with a valid structure, and finding such a traversal of the input tree that achieves the correct composition of the output tree and applies structural rules.
摘要翻译：将传统和专有文档转换为扩展标记语言格式的系统和方法，该格式将转换视为将一个模式和/或模型的有序树转换为另一模式和/或模型的有序树。在实施例中，使用将转换任务分解为包括路径重新标记，结构组合和输入树遍历的三个组件的学习方法对树型变换器进行编码，每个组件涉及学习方法。将输入树转换为输出树可能涉及使用来自特定输出模式的有效标签或路径来标注输入树中的组件，使用有效结构将标记的元素组合成输出树，并且找到输入的遍历树，实现输出树的正确组合并应用结构规则。

10. 发明授权

US06327590B1 System and method for collaborative ranking of search results employing user and group profiles derived from document collection content analysis 有权
标题翻译：使用从文件收集内容分析导出的用户和组配置文件对搜索结果进行协同排序的系统和方法
公开(公告)号：US06327590B1
公开(公告)日：2001-12-04
申请号：US09305435
申请日：1999-05-05
申请人： Boris Chidlovskii , Natalie S. Glance , Antonietta Grasso
发明人： Boris Chidlovskii , Natalie S. Glance , Antonietta Grasso
IPC分类号： G06F1730
CPC分类号： G06F17/30867 , Y10S707/99935
摘要： A system for ranking search results obtained from an information retrieval system includes a search pre-processor, a search engine and a search post-processor. The search preprocessor determines the context of the search query by comparing the terms in the search query with a predetermined user context profile. Preferably, the context profile is a user profile or a community profile, which includes a set of terms which have been rated by the user, community, or a recommender system. The search engine generates a search result comprising at least one item obtained from the information retrieval system. The search post-processor ranks each item returned in the search result in accordance with the context of the search query.
摘要翻译：用于对从信息检索系统获得的搜索结果进行排名的系统包括搜索预处理器，搜索引擎和搜索后处理器。搜索预处理器通过将搜索查询中的术语与预定的用户上下文简档进行比较来确定搜索查询的上下文。优选地，上下文简档是用户简档或社区简档，其包括由用户，社区或推荐系统评估的一组术语。搜索引擎生成包括从信息检索系统获得的至少一个项目的搜索结果。搜索后处理器根据搜索查询的上下文排列搜索结果中返回的每个项目。

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