-
公开(公告)号：US20120254188A1
公开(公告)日：2012-10-04
申请号：US13434600
申请日：2012-03-29
申请人： Krzysztof Koperski , Satish Bhatti , Jisheng Liang , Adrian Klein
发明人： Krzysztof Koperski , Satish Bhatti , Jisheng Liang , Adrian Klein
IPC分类号： G06F17/30
CPC分类号： G06F17/30598 , G06F17/30663 , G06F17/30699 , G06F17/30705 , G06F17/30707 , G06F17/3071 , G06F17/30722 , G06F17/30867
摘要： Methods, systems, and techniques for cluster-based content recommendation are described. Some embodiments provide a content recommendation system (“CRS”) configured to recommend news stories about events or occurrences. In some embodiments, a news story about an event includes multiple related content items that each include an account of the event and that each reference one or more entities or categories that are represented by the CRS. In one embodiment, the CRS identifies news stories by generating clusters of related content items. Then, in response to a received query that indicates a keyterm, entity, or category, the CRS determines and provides indications of one or more news stories that are relevant to the received query. In some embodiments, at least some of these techniques are employed to implement a news story recommendation facility in an online news service.
摘要翻译： 描述了基于群集的内容推荐的方法，系统和技术。 一些实施例提供了被配置为推荐关于事件或事件的新闻故事的内容推荐系统（CRS）。 在一些实施例中，关于事件的新闻故事包括多个相关内容项，每个内容项包括事件的帐户，并且每个引用由CRS表示的一个或多个实体或类别。 在一个实施例中，CRS通过生成相关内容项目的集群来识别新闻故事。 然后，响应于接收到的指示关键字，实体或类别的查询，CRS确定并提供与所接收的查询相关的一个或多个新闻故事的指示。 在一些实施例中，使用这些技术中的至少一些来实现在线新闻服务中的新闻故事推荐设施。
-
公开(公告)号：US09405848B2
公开(公告)日：2016-08-02
申请号：US13233879
申请日：2011-09-15
申请人： Jisheng Liang , Will Hunsinger , Satish Bhatti
发明人： Jisheng Liang , Will Hunsinger , Satish Bhatti
CPC分类号： G06F17/30321 , G06F17/30867 , G06F17/30899
摘要： Techniques for recommending mobile device activities, such as accessing mobile applications and/or mobile Web pages, are described. Some embodiments provide an Activity Recommendation System (“ARS”) configured to recommend relevant activities for a user to perform with a mobile device, based on context of the mobile device. In one embodiment, the ARS recommends mobile applications based content items (e.g., Web pages, images, videos) that are being currently accessed via the mobile device. The ARS may process information about mobile applications and content items to determine semantic information, such as entities and/or categories referenced or associated therewith. The ARS may then use the semantic information to determine mobile applications that have semantic information that is at least similar to that of a content item accessed via a mobile device.
摘要翻译： 描述了用于推荐移动设备活动的技术，例如访问移动应用和/或移动网页。 一些实施例提供了一种活动推荐系统（“ARS”），其被配置为基于移动设备的上下文来推荐用户使用移动设备执行的相关活动。 在一个实施例中，ARS推荐基于当前通过移动设备访问的基于移动应用的内容项目（例如，网页，图像，视频）。 ARS可以处理关于移动应用和内容项的信息以确定语义信息，例如被引用或相关联的实体和/或类别。 然后，ARS可以使用语义信息来确定具有至少类似于经由移动设备访问的内容项的语义信息的移动应用。
-
公开(公告)号：US09116995B2
公开(公告)日：2015-08-25
申请号：US13434600
申请日：2012-03-29
申请人： Krzysztof Koperski , Satish Bhatti , Jisheng Liang , Adrian Klein
发明人： Krzysztof Koperski , Satish Bhatti , Jisheng Liang , Adrian Klein
CPC分类号： G06F17/30598 , G06F17/30663 , G06F17/30699 , G06F17/30705 , G06F17/30707 , G06F17/3071 , G06F17/30722 , G06F17/30867
摘要： Methods, systems, and techniques for cluster-based content recommendation are described. Some embodiments provide a content recommendation system (“CRS”) configured to recommend news stories about events or occurrences. In some embodiments, a news story about an event includes multiple related content items that each include an account of the event and that each reference one or more entities or categories that are represented by the CRS. In one embodiment, the CRS identifies news stories by generating clusters of related content items. Then, in response to a received query that indicates a keyterm, entity, or category, the CRS determines and provides indications of one or more news stories that are relevant to the received query. In some embodiments, at least some of these techniques are employed to implement a news story recommendation facility in an online news service.
摘要翻译： 描述了基于群集的内容推荐的方法，系统和技术。 一些实施例提供了被配置为推荐关于事件或事件的新闻故事的内容推荐系统（“CRS”）。 在一些实施例中，关于事件的新闻故事包括多个相关内容项，每个内容项包括事件的帐户，并且每个引用由CRS表示的一个或多个实体或类别。 在一个实施例中，CRS通过生成相关内容项目的集群来识别新闻故事。 然后，响应于接收到的指示关键字，实体或类别的查询，CRS确定并提供与所接收的查询相关的一个或多个新闻故事的指示。 在一些实施例中，使用这些技术中的至少一些来实现在线新闻服务中的新闻故事推荐设施。
-
公开(公告)号：US08594996B2
公开(公告)日：2013-11-26
申请号：US12288158
申请日：2008-10-15
IPC分类号： G06F17/27
CPC分类号： G06F17/21 , G06F17/278
摘要： Methods and systems for entity recognition and disambiguation using natural language processing techniques are provided. Example embodiments provide an entity recognition and disambiguation system (ERDS) and process that, based upon input of a text segment, automatically determines which entities are being referred to by the text using both natural language processing techniques and analysis of information gleaned from contextual data in the surrounding text. In at least some embodiments, supplemental or related information that can be used to assist in the recognition and/or disambiguation process can be retrieved from knowledge repositories such as an ontology knowledge base. In one embodiment, the ERDS comprises a linguistic analysis engine, a knowledge analysis engine, and a disambiguation engine that cooperate to identify candidate entities from a knowledge repository and determine which of the candidates best matches the one or more detected entities in a text segment using context information.
-
公开(公告)号：US20120084292A1
公开(公告)日：2012-04-05
申请号：US13233879
申请日：2011-09-15
申请人： Jisheng Liang , Will Hunsinger , Satish Bhatti
发明人： Jisheng Liang , Will Hunsinger , Satish Bhatti
CPC分类号： G06F17/30321 , G06F17/30867 , G06F17/30899
摘要： Techniques for recommending mobile device activities, such as accessing mobile applications and/or mobile Web pages, are described. Some embodiments provide an Activity Recommendation System (“ARS”) configured to recommend relevant activities for a user to perform with a mobile device, based on context of the mobile device. In one embodiment, the ARS recommends mobile applications based content items (e.g., Web pages, images, videos) that are being currently accessed via the mobile device. The ARS may process information about mobile applications and content items to determine semantic information, such as entities and/or categories referenced or associated therewith. The ARS may then use the semantic information to determine mobile applications that have semantic information that is at least similar to that of a content item accessed via a mobile device.
摘要翻译： 描述了用于推荐移动设备活动的技术，例如访问移动应用和/或移动网页。 一些实施例提供了一种活动推荐系统（“ARS”），其被配置为基于移动设备的上下文来推荐用户使用移动设备执行的相关活动。 在一个实施例中，ARS推荐基于当前通过移动设备访问的基于移动应用的内容项目（例如，网页，图像，视频）。 ARS可以处理关于移动应用和内容项的信息以确定语义信息，例如被引用或相关联的实体和/或类别。 然后，ARS可以使用语义信息来确定具有至少类似于经由移动设备访问的内容项的语义信息的移动应用。
-
公开(公告)号：US20090144609A1
公开(公告)日：2009-06-04
申请号：US12288158
申请日：2008-10-15
CPC分类号： G06F17/21 , G06F17/278
摘要： Methods and systems for entity recognition and disambiguation using natural language processing techniques are provided. Example embodiments provide an entity recognition and disambiguation system (ERDS) and process that, based upon input of a text segment, automatically determines which entities are being referred to by the text using both natural language processing techniques and analysis of information gleaned from contextual data in the surrounding text. In at least some embodiments, supplemental or related information that can be used to assist in the recognition and/or disambiguation process can be retrieved from knowledge repositories such as an ontology knowledge base. In one embodiment, the ERDS comprises a linguistic analysis engine, a knowledge analysis engine, and a disambiguation engine that cooperate to identify candidate entities from a knowledge repository and determine which of the candidates best matches the one or more detected entities in a text segment using context information.
摘要翻译： 提供了使用自然语言处理技术进行实体识别和消歧的方法和系统。 示例性实施例提供了一种实体识别和消歧系统（ERDS）和过程，其基于文本段的输入，使用自然语言处理技术自动确定文本正在引用哪些实体以及从上下文数据中收集的信息的分析 周围的文字。 在至少一些实施例中，可以用于帮助识别和/或消歧过程的补充或相关信息可以从诸如本体知识库的知识库中检索。 在一个实施例中，ERDS包括语言分析引擎，知识分析引擎和消歧引擎，其协作以从知识库识别候选实体，并且使用以下方式确定哪个候选最符合文本段中的一个或多个检测到的实体 上下文信息。
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.015 秒)
