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

US08635172B1 Dynamic techniques for evaluating quality of clustering or classification system aimed to minimize the number of manual reviews based on Bayesian inference and Markov Chain Monte Carlo (MCMC) techniques 有权
标题翻译：用于评估聚类或分类系统质量的动态技术旨在最大限度地减少基于贝叶斯推理和马尔可夫链蒙特卡罗（MCMC）技术的手动评论数量
公开(公告)号：US08635172B1
公开(公告)日：2014-01-21
申请号：US13267937
申请日：2011-10-07
申请人： Kirill Buryak , Steven Lee Scott , Steven Doubilet
发明人： Kirill Buryak , Steven Lee Scott , Steven Doubilet
IPC分类号： G06F15/18
CPC分类号： G06K9/6262
摘要： Performance of the machine learning technique is assessed using Bayesian analysis where previously grouped documents belonging to a machine-assigned class or cluster are presented to a human rater and the rater's assessment is fed to the Bayesian analysis processor that updates a Beta bionomial model with each document. The model represents the precision probability associated with the class or cluster under test. Monitoring the precision probability, the technique enforces a set of stopping rules corresponding to an acceptance/rejection assessment of the machine learning apparatus. A Markov Chain Monte Carlo process operates on the model to infuse the processing of each subsequent class or cluster with knowledge from those previously processed.
摘要翻译：使用贝叶斯分析评估机器学习技术的性能，其中属于机器分配类别或集群的先前分组的文档被呈现给人类评估者，并且评估者的评估被馈送到贝叶斯分析处理器，其使用每个文档更新Beta仿生模型。该模型表示与被测试的类或集群相关联的精度概率。监控精度概率，该技术执行与机器学习装置的接受/拒绝评估相对应的一组停止规则。马尔可夫链蒙特卡洛过程在模型上运行，以便将以前处理过的知识从每个后续类或集群中进行处理。

2. 发明授权

US09613029B2 Techniques for transliterating input text from a first character set to a second character set 有权
公开(公告)号：US09613029B2
公开(公告)日：2017-04-04
申请号：US14381395
申请日：2012-02-28
申请人： Fan Yang , Kirill Buryak , Feng Yuan , Baohua Liao
发明人： Fan Yang , Kirill Buryak , Feng Yuan , Baohua Liao
IPC分类号： G06F17/28 , G06F17/21
CPC分类号： G06F17/289 , G06F17/21 , G06F17/2863
摘要： Computer implemented techniques for performing transliteration of input text in a first character set to a second character set are disclosed. The techniques include receiving input text and determining a set of possible transliterations of the input text based on a plurality of mapping standards. Each mapping standard defines a mapping of characters in the first character set to characters in the second character set. The techniques further include determining a set of candidate words in the target language based on the possible transliterations and a text corpus. The techniques also include determining a likelihood score for each one of the candidate words based on a language model in the target language previously received words. The techniques also include providing one or more candidate words based on the likelihood scores and receiving a user selection indicating one of the candidate words.

3. 发明授权

US09262398B2 Language set disambiguator 有权
标题翻译：语言设定歧义
公开(公告)号：US09262398B2
公开(公告)日：2016-02-16
申请号：US13278605
申请日：2011-10-21
申请人： Andrew Swerdlow , Clément Roux , Cibu Johny , Kirill Buryak
发明人： Andrew Swerdlow , Clément Roux , Cibu Johny , Kirill Buryak
IPC分类号： G06F17/27 , G06F9/44 , G06F3/0482 , G06F17/28
CPC分类号： G06F17/275 , G06F3/0482 , G06F9/454 , G06F17/2288 , G06F17/289
摘要： A set of language tags in a backend application can be passed to a frontend application in the form of a language selection tool. The disclosure creates a mapping between the frontend and backend application of at least one non-default language descriptor string onto a language tag of the backend application. The frontend language selection tool then displays to the user the non-default language descriptor string. The use of non-default language descriptor strings clarifies to the user otherwise ambiguous language identifiers.
摘要翻译：后端应用程序中的一组语言标签可以以语言选择工具的形式传递给前端应用程序。本公开在至少一个非默认语言描述符字符串的前端和后端应用之间创建到后端应用的语言标签上的映射。然后，前端语言选择工具向用户显示非默认语言描述符字符串。使用非默认语言描述符字符串向用户说明了其他模糊的语言标识符。

4. 发明申请

US20150161104A1 Language Detection Based Upon a Social Graph 有权
标题翻译：基于社会图表的语言检测
公开(公告)号：US20150161104A1
公开(公告)日：2015-06-11
申请号：US13173581
申请日：2011-06-30
申请人： Kirill Buryak , Andrew Swerdlow , Clément Roux , Luke Hiro Swartz , Cibu Johny
发明人： Kirill Buryak , Andrew Swerdlow , Clément Roux , Luke Hiro Swartz , Cibu Johny
IPC分类号： G06F17/28 , G06F17/20
CPC分类号： G06F17/275 , G06F9/454 , G06F17/289 , G06Q50/01
摘要： Techniques for determining one or more preferred languages for a user are provided. The preferred languages may be determined based upon a set of language indicators. The language indicators are analyzed using, for example, rules-based techniques, clustering, language classifiers, and the like, or combinations thereof. Language indicators can include or be derived from information about the user's behavior, location, preferences, social connections, or other data related to the user.
摘要翻译：提供了用于确定用户的一种或多种优选语言的技术。可以基于一组语言指示符来确定优选语言。使用例如基于规则的技术，聚类，语言分类器等或其组合来分析语言指示符。语言指标可以包括或从关于用户的行为，位置，偏好，社交连接或与用户相关的其他数据的信息中得出。

5. 发明授权

US08671389B1 Web application resource manager on the web and localizable components 有权
标题翻译：网络上的Web应用程序资源管理器和本地化组件
公开(公告)号：US08671389B1
公开(公告)日：2014-03-11
申请号：US13246288
申请日：2011-09-27
申请人： Kirill Buryak , Jeremy Aron-Dine , Luke Hiro Swartz
发明人： Kirill Buryak , Jeremy Aron-Dine , Luke Hiro Swartz
IPC分类号： G06F9/44
CPC分类号： G06F9/454
摘要： Applications can be localized by a localization expert to allow them to be used by a broader customer base. The localization can be conducted by a localization expert who is provided with a resource file containing localizable components. The resource file can be generated by providing a developer with one or more text strings based on the development code of the application and receiving the localizable components which are selected from with the text strings based on the development code.
摘要翻译：应用程序可以由本地化专家进行本地化，以使其能够被更广泛的客户群使用。本地化可由本地化专家进行，该专家被提供有包含可本地化组件的资源文件。资源文件可以通过向开发者提供基于应用程序的开发代码的一个或多个文本字符串并基于开发代码接收从文本串中选择的可本地化组件来生成资源文件。

6. 发明授权

US08200661B1 Dynamic recommendations based on user actions 有权
标题翻译：基于用户操作的动态建议
公开(公告)号：US08200661B1
公开(公告)日：2012-06-12
申请号：US12338847
申请日：2008-12-18
申请人： Cail Pearce , Peter Dolan , Owen Carlsen , Kirill Buryak , Rob Christy
发明人： Cail Pearce , Peter Dolan , Owen Carlsen , Kirill Buryak , Rob Christy
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30867
摘要： Embodiments of a system (such as a computer system), a method, and a computer-program product (e.g., software) for use with the computer system are described. These embodiments may be used to provide one or more recommendations to a user based at least in part on monitored user actions while the user interacts with a support document (e.g., a website or a web page) that includes content for multiple support topics, such as help instructions associated with an application or a service. In particular, one or more support topics are associated with the monitored user actions using a supervised-learning model, and these support topics are recommended to the user. This supervised-learning model may be trained on portions of the content accessed by multiple users during multiple sessions. Moreover, in the supervised-learning model, content accessed by one of the users during a given session may be more relevant than content accessed by this user during the multiple sessions.
摘要翻译：描述与计算机系统一起使用的系统（诸如计算机系统），方法和计算机程序产品（例如，软件）的实施例。这些实施例可以用于至少部分地基于受监控的用户动作来向用户提供一个或多个推荐，同时用户与包括多个支持主题的内容的支持文档（例如，网站或网页）进行交互，例如，作为与应用程序或服务相关联的帮助说明。特别地，一个或多个支持主题使用监督学习模型与被监视的用户动作相关联，并且这些支持主题被推荐给用户。该监督学习模型可以在多个会话期间由多个用户访问的内容的一部分进行训练。此外，在监督学习模型中，在给定会话期间由用户之一访问的内容可能比在多个会话期间由该用户访问的内容更相关。

7. 发明授权

US09436766B1 Clustering of documents for providing content 有权
标题翻译：提供内容的文档的聚类
公开(公告)号：US09436766B1
公开(公告)日：2016-09-06
申请号：US13679732
申请日：2012-11-16
申请人： Kirill Buryak
发明人： Kirill Buryak
IPC分类号： G06F17/30
CPC分类号： G06F17/30867 , G06F17/30705
摘要： Systems and methods for providing relevant content may include applying a clustering algorithm to posts associated with a device identifier and labeled documents to cluster the unlabeled posts with the labeled documents to determine interests. Content related to the interests may be selected and provided to an electronic device associated with the device identifier.
摘要翻译：用于提供相关内容的系统和方法可以包括将聚类算法应用于与设备标识符相关联的帖子和标记的文档，以将未标记的帖子与标记的文档聚类以确定兴趣。可以选择与兴趣相关的内容并将其提供给与设备标识符相关联的电子设备。

8. 发明授权

US09111218B1 Method and system for remediating topic drift in near-real-time classification of customer feedback 有权
标题翻译：用于补救客户反馈近实时分类中主题漂移的方法和系统
公开(公告)号：US09111218B1
公开(公告)日：2015-08-18
申请号：US13530667
申请日：2012-06-22
申请人： Glenn M. Lewis , Kirill Buryak , Aner Ben-Artzi , Jun Peng , Nadav Benbarak
发明人： Glenn M. Lewis , Kirill Buryak , Aner Ben-Artzi , Jun Peng , Nadav Benbarak
IPC分类号： G06F15/18 , G06F7/00 , G06F17/30 , G06N5/04
CPC分类号： G06N5/04 , G06F17/30705 , G06Q30/01
摘要： A method and system of classifying documents is provided. The method includes receiving a stream of documents from at least one user wherein each document includes a topic of information relating to a customer support issue or sentiment. The method includes classifying each of the received documents using a plurality of trained classifiers, the classification based on a voting by the trained classifiers, each document labeled according to a similar topic. A drift of the topic of one or more of the classifications is determined wherein the drift is related to the received documents that include information relating to an unclassified customer support issue or sentiment. If the determined drift exceeds a predetermined threshold range, rebuilding the plurality of classifiers to include a second set of classifiers trained to recognize the unclassified customer support issue or sentiment.
摘要翻译：提供了一种分类文件的方法和系统。该方法包括从至少一个用户接收文档流，其中每个文档包括与客户支持问题或情绪相关的信息的主题。该方法包括使用多个经过训练的分类器对接收到的文档进行分类，基于训练分类器的投票的分类，每个文献根据相似的主题标记。确定一个或多个分类的主题的漂移，其中漂移与包括与未分类的客户支持问题或情绪相关的信息的接收到的文档相关。如果所确定的漂移超过预定的阈值范围，则重建多个分类器以包括被训练以识别未分类的客户支持问题或情绪的第二组分类器。

9. 发明授权

US09110984B1 Methods and systems for constructing a taxonomy based on hierarchical clustering 有权
标题翻译：基于层次聚类构建分类法的方法和系统
公开(公告)号：US09110984B1
公开(公告)日：2015-08-18
申请号：US13531147
申请日：2012-06-22
申请人： Glenn M. Lewis , Kirill Buryak , Nadav Benbarak , Aner Ben-Artzi , Jun Peng
发明人： Glenn M. Lewis , Kirill Buryak , Nadav Benbarak , Aner Ben-Artzi , Jun Peng
IPC分类号： G06F17/30
CPC分类号： G06F17/3071 , G06F17/30598 , G06F17/30731
摘要： Methods and systems for constructing a taxonomy based on hierarchical clustering are provided. The taxonomy is generated by first constructing a hierarchy of clusters using a clustering algorithm. A first level of the hierarchy of clusters is generated by providing a plurality of content files to a clustering algorithm. Subsequent levels of the hierarchy are generated by providing the clusters of the preceding levels to the clustering algorithm. Labels that characterize each cluster within the hierarchy are assigned to corresponding clusters. Labels and clusters are combined to form the taxonomy.
摘要翻译：提供了基于分层聚类构建分类法的方法和系统。通过使用聚类算法首先构建聚类的层次来生成分类法。通过向聚类算法提供多个内容文件来生成集群层级的第一级。通过向聚类算法提供前述层次的聚类来生成层次结构的后续层级。表征层次结构中每个集群的标签被分配给相应的集群。标签和集群组合形成分类。

10. 发明申请

US20150154182A1 DATA LOCALIZATION SERVICE MADE AVAILABLE BY A WEB BROWSER 有权
标题翻译：数据本地化服务由网络浏览器提供
公开(公告)号：US20150154182A1
公开(公告)日：2015-06-04
申请号：US13313157
申请日：2011-12-07
申请人： Sudhakar Chandrasekharan , Kirill Buryak , Shanjian Li , Vladimir Weinstein , Robert S. Jung , Jungshik Shin , Nebojsa Ciric
发明人： Sudhakar Chandrasekharan , Kirill Buryak , Shanjian Li , Vladimir Weinstein , Robert S. Jung , Jungshik Shin , Nebojsa Ciric
IPC分类号： G06F17/28 , G06F17/00
CPC分类号： G06F17/289 , G06F9/454
摘要： A data localization service is provided for a web browser residing on a computing device. Depending upon the availability of the network connection as well as the level of native support in the browser, the data localization service will support different levels of service/performance to optimize the user experience. To do so, the data localization service includes a priority handler configured to receive a request to localize data from a requesting client application and provide in response thereto a localized representation of the data to the requesting client application. The data localization service may also include a native data localizer configured to receive a request to localize data from the priority handler and localize the data in accordance with a localization preference parameter indicative of a locale. The native data localizer may be a function integrated into the script interpreter of the web browser.
摘要翻译：为驻留在计算设备上的Web浏览器提供数据定位服务。根据网络连接的可用性以及浏览器本机支持的级别，数据本地化服务将支持不同级别的服务/性能，以优化用户体验。为此，数据定位服务包括优先处理器，其被配置为接收来自请求客户端应用的本地化数据的请求，并响应于此向所述请求客户端应用提供数据的局部化表示。数据定位服务还可以包括本地数据定位器，其被配置为接收来自优先处理器的本地化数据的请求，并且根据指示区域设置的定位偏好参数来定位数据。本地数据定位器可以是集成到web浏览器的脚本解释器中的功能。

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