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

US09411886B2 Ranking advertisements with pseudo-relevance feedback and translation models 有权
标题翻译：排序广告与伪相关反馈和翻译模型
公开(公告)号：US09411886B2
公开(公告)日：2016-08-09
申请号：US12059098
申请日：2008-03-31
申请人： Vanessa Murdock
发明人： Vanessa Murdock
IPC分类号： G06F7/00 , G06F17/30 , G06Q30/02
CPC分类号： G06Q30/0244 , G06F17/3053 , G06F17/30864 , G06N7/005 , G06Q30/02 , G06Q30/0277
摘要： Methods, computer products, and systems for selecting advertisements in response to an internet query are provided. The method provides for receiving an internet query having query terms, and retrieving and ranking a first set of advertisements using a query likelihood model. Sampling words are selected using pseudo-relevance feedback and translation models, the internet query, and the first set of ad materials. Sampling words are chosen from the words in the first set, and the pseudo-relevance feedback model is used to select word w in the distribution of words based on a probability that w generates query term q(p(q|w)). The translation model calculates p(q|w) based on a translation probability that w translates into q(t(q|w)). A second set of ad materials are retrieved and ranked using an expanded query which adds the selected sampling words to the original query. The second set of ad materials is presented to the user.
摘要翻译：提供了用于响应于互联网查询来选择广告的方法，计算机产品和系统。该方法提供接收具有查询词语的因特网查询，以及使用查询似然模型来检索和排列第一组广告。使用伪相关反馈和翻译模型，互联网查询和第一组广告材料来选择抽样单词。从第一组中的单词中选择抽样单词，并且使用伪相关反馈模型基于w生成查询项q（p（q | w））的概率来选择单词的分布中的单词w。翻译模型基于转换为q（t（q | w））的翻译概率来计算p（q | w）。使用扩展查询来检索和排名第二组广告资料，该查询将选定的抽样单词添加到原始查询中。向用户呈现第二组广告资料。

2. 发明授权

US08918328B2 Ranking using word overlap and correlation features 有权
标题翻译：使用单词重叠和相关特征排列
公开(公告)号：US08918328B2
公开(公告)日：2014-12-23
申请号：US12106230
申请日：2008-04-18
申请人： Vassilis Plachouras , Vanessa Murdock , Massimiliano Ciaramita
发明人： Vassilis Plachouras , Vanessa Murdock , Massimiliano Ciaramita
IPC分类号： G06Q30/02
CPC分类号： G06Q30/02 , G06Q30/0256
摘要： A system for and method for ranking results. The system includes a server configured to receive a query and an advertisement engine configured to receive the query from the server. The advertisement engine ranks advertisements based on various features, including at least one word overlap feature and a correlation feature.
摘要翻译：用于评估结果的系统和方法。该系统包括被配置为接收查询的服务器和被配置为从服务器接收查询的广告引擎。广告引擎基于各种特征来排列广告，包括至少一个单词重叠特征和相关特征。

3. 发明授权

US08868551B2 Method for storing bookmarks for search results from previously submitted search queries by a user and storing links to selected documents by the user 有权
标题翻译：用于存储由用户先前提交的搜索查询的搜索结果的书签并由用户存储到所选文档的链接的方法
公开(公告)号：US08868551B2
公开(公告)日：2014-10-21
申请号：US13619443
申请日：2012-09-14
申请人： Vanessa Murdock , Lluis Garcia , Barbara Poblete , Vassilis Plachouras
发明人： Vanessa Murdock , Lluis Garcia , Barbara Poblete , Vassilis Plachouras
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30876
摘要： In one embodiment, a search query is received. Information identifying a bookmark representing the search query is automatically stored in association with a set of bookmarks. Search results corresponding to the search query are automatically obtained and provided, where the search results identify one or more documents. When one of the documents is selected, a link to the selected one of the documents is automatically stored in association with the bookmark.
摘要翻译：在一个实施例中，接收到搜索查询。识别表示搜索查询的书签的信息与一组书签相关联地自动存储。自动获取和提供与搜索查询相对应的搜索结果，其中搜索结果标识一个或多个文档。当选择其中一个文档时，与书签相关联地自动存储到所选文档之一的链接。

4. 发明授权

US08171043B2 Methods for improving the diversity of image search results 有权
标题翻译：提高图像搜索结果多样性的方法
公开(公告)号：US08171043B2
公开(公告)日：2012-05-01
申请号：US12257991
申请日：2008-10-24
申请人： Vanessa Murdock , Roelof Van Zwol , Lluis Garcia Pueyo , Georgina Ramirez Camps
发明人： Vanessa Murdock , Roelof Van Zwol , Lluis Garcia Pueyo , Georgina Ramirez Camps
IPC分类号： G06F17/30
CPC分类号： G06F17/30265
摘要： Techniques are described to increase the diversity or focus of image search results. A user submits an original query to search for images. A server generates a first results set by executing the original query using metadata associated with each image. The server selects, from the first results set, a specified number of results ranked highest and generates a list of terms from the metadata of each of the results selected. The terms may be only the tags of the results. The server generates an updated query using terms in the list that may be weighted based on the frequency of the term in the list or include only a specified number of the highest occurring terms in the list. The server generates a second results set by executing the updated query using metadata associated with each image. The second results set is then stored and displayed to the user.
摘要翻译：描述技术来增加图像搜索结果的多样性或重点。用户提交原始查询以搜索图像。服务器通过使用与每个图像相关联的元数据执行原始查询来生成第一个结果集。服务器从第一个结果集中选择指定数量的结果排名最高，并从所选结果的每个结果的元数据中生成术语列表。术语可能只是结果的标签。服务器使用列表中的术语来生成更新的查询，该列可以根据列表中的术语的频率进行加权，或者仅包括指定数量的列表中最高出现的术语。服务器通过使用与每个图像相关联的元数据执行更新的查询来生成第二个结果集。然后将第二个结果集存储并显示给用户。

5. 发明申请

US20120084226A1 MEASURING OR ESTIMATING USER CREDIBILITY 审中-公开
标题翻译：测量或估计用户可信度
公开(公告)号：US20120084226A1
公开(公告)日：2012-04-05
申请号：US12898644
申请日：2010-10-05
申请人： Vanessa Murdock , Roelof van Zwol , Emmanouil Papangelis
发明人： Vanessa Murdock , Roelof van Zwol , Emmanouil Papangelis
IPC分类号： G06F15/16 , G06F3/01 , G06Q99/00
CPC分类号： G06Q10/10 , G06Q30/0282
摘要： A method or system for measuring or estimating user credibility is described.
摘要翻译：描述了用于测量或估计用户可信度的方法或系统。

6. 发明授权

US08145649B2 Method for selecting electronic advertisements using machine translation techniques 有权
标题翻译：使用机器翻译技术选择电子广告的方法
公开(公告)号：US08145649B2
公开(公告)日：2012-03-27
申请号：US12970757
申请日：2010-12-16
申请人： Vanessa Murdock , Massimiliano Ciaramita , Vassilis Plachouras
发明人： Vanessa Murdock , Massimiliano Ciaramita , Vassilis Plachouras
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06Q30/02
摘要： A system for selecting electronic advertisements from an advertisement pool to match the surrounding content is disclosed. To select advertisements, the system takes an approach to content match that takes advantage of machine translation technologies. The system of the present invention implements this goal by means of simple and efficient machine translation features that are extracted from the surrounding context to match with the pool of potential advertisements. Machine translation features used as features for training a machine learning model. In one embodiment, a ranking SVM (Support Vector Machines) trained to identify advertisements relevant to a particular context. The trained machine learning model can then be used to rank advertisements for a particular context by supplying the machine learning model with the machine translation features measures for the advertisements and the surrounding context.
摘要翻译：公开了一种用于从广告池中选择电子广告以匹配周围内容的系统。为了选择广告，系统采取利用机器翻译技术的内容匹配的方法。本发明的系统通过简单有效的机器翻译功能来实现这一目标，这些机器翻译功能是从周围环境中提取的，以与潜在的广告池相匹配。机器翻译功能用作训练机器学习模型的特征。在一个实施例中，经训练以识别与特定上下文相关的广告的排名SVM（支持向量机）。训练后的机器学习模型然后可以用于通过向机器学习模型提供用于广告和周围环境的机器翻译特征措施来对特定上下文的广告进行排名。

7. 发明授权

US08073803B2 Method for matching electronic advertisements to surrounding context based on their advertisement content 有权
标题翻译：基于其广告内容将电子广告与周围环境进行匹配的方法
公开(公告)号：US08073803B2
公开(公告)日：2011-12-06
申请号：US11778540
申请日：2007-07-16
申请人： Vanessa Murdock , Vassilis Plachouras , Massimiliano Ciaramita
发明人： Vanessa Murdock , Vassilis Plachouras , Massimiliano Ciaramita
IPC分类号： G06F17/00 , G06N5/02
CPC分类号： G06Q30/02 , G06Q30/0276
摘要： A system for selecting electronic advertisements from an advertisement pool to match the surrounding content is disclosed. To select advertisements, the system takes an approach to content match that focuses on capturing subtler linguistic associations between the surrounding content and the content of the advertisement. The system of the present invention implements this goal by means of simple and efficient semantic association measures dealing with lexical collocations such as conventional multi-word expressions like “big brother” or “strong tea”. The semantic association measures are used as features for training a machine learning model. In one embodiment, a ranking SVM (Support Vector Machines) trained to identify advertisements relevant to a particular context. The trained machine learning model can then be used to rank advertisements for a particular context by supplying the machine learning model with the semantic association measures for the advertisements and the surrounding context.
摘要翻译：公开了一种用于从广告池中选择电子广告以匹配周围内容的系统。为了选择广告，系统采取内容匹配的方法，重点是捕获周围内容和广告内容之间的细微的语言关联。本发明的系统通过简单而有效的语义关联度量来实现这一目标，这些措施涉及诸如“大哥”或“强茶”等常规多字表达的词汇搭配。语义关联度量被用作训练机器学习模型的特征。在一个实施例中，经训练以识别与特定上下文相关的广告的排名SVM（支持向量机）。训练后的机器学习模型然后可以用于通过向机器学习模型提供广告和周围环境的语义关联度量来对特定上下文的广告进行排名。

8. 发明申请

US20110173572A1 METHOD AND INTERFACE FOR DISPLAYING LOCATIONS ASSOCIATED WITH ANNOTATIONS 有权
标题翻译：用于显示与注释相关的位置的方法和界面
公开(公告)号：US20110173572A1
公开(公告)日：2011-07-14
申请号：US12686677
申请日：2010-01-13
申请人： Roelof van Zwol , Vanessa Murdock , Lluis Garcia Pueyo
发明人： Roelof van Zwol , Vanessa Murdock , Lluis Garcia Pueyo
IPC分类号： G06N5/02 , G06F3/048 , G09G5/00
CPC分类号： G06N7/005 , G06F17/241 , G06F17/30241 , G06F17/30268
摘要： Methods, systems and computer program products for displaying geographical locations with the one or more annotations. In a particular embodiment, a language model is used to obtain the probability distribution of the locations over one or more annotations. Further, the system and the method utilizes the probability data obtained from the language model to determine a probability score for each location over the one or more annotations. Subsequently, one or more geographical locations are displayed on a world map, based on the probability score of the geographical locations over the one or more annotations. In one embodiment, geographical locations may be highlighted using a color code on a heat map overlaid on the world map. The color code may represent the ranking of the geographical locations based on the calculated probability score for each identified geographical location. Further, when the user provides one or more additional annotations, the world map may be dynamically updated to display the relevant geographical locations associated with the updated annotations.
摘要翻译：用于显示具有一个或多个注释的地理位置的方法，系统和计算机程序产品。在特定实施例中，使用语言模型来获得位置在一个或多个注释上的概率分布。此外，系统和方法利用从语言模型获得的概率数据来确定一个或多个注释上的每个位置的概率分数。随后，基于一个或多个注释上的地理位置的概率分数，在世界地图上显示一个或多个地理位置。在一个实施例中，可以使用覆盖在世界地图上的热图上的颜色代码突出显示地理位置。颜色代码可以基于针对每个确定的地理位置的计算的概率分数来表示地理位置的排名。此外，当用户提供一个或多个附加注释时，可以动态地更新世界地图以显示与更新的注释相关联的相关地理位置。

9. 发明申请

US20110173150A1 METHODS AND SYSTEM FOR ASSOCIATING LOCATIONS WITH ANNOTATIONS 审中-公开
标题翻译：方法和系统用于与位置相关联的位置
公开(公告)号：US20110173150A1
公开(公告)日：2011-07-14
申请号：US12686883
申请日：2010-01-13
申请人： Roelof van Zwol , Vanessa Murdock , Pavel Serdyukov
发明人： Roelof van Zwol , Vanessa Murdock , Pavel Serdyukov
IPC分类号： G06N5/02
CPC分类号： G06N7/005
摘要： Methods, systems and computer program products for associating geographical locations with annotations corresponding to content. In one method, a language model is developed. The language model is developed from the location information and the one or more annotations associated with content uploaded by users. The language model is based on the probabilistic distribution of locations over one or more annotations. Further, when a user provides one or more annotations, the system and the method may use the language model to identify one or more locations associated with the one or more annotations provided by the user. The language model predicts one or more geographical locations based on the probabilistic distribution of locations over the annotations.
摘要翻译：用于将地理位置与与内容相对应的注释关联的方法，系统和计算机程序产品。在一种方法中，开发了语言模型。语言模型是从位置信息和与用户上传的内容相关联的一个或多个注释开发的。语言模型基于一个或多个注释上位置的概率分布。此外，当用户提供一个或多个注释时，系统和方法可以使用语言模型来识别与由用户提供的一个或多个注释相关联的一个或多个位置。语言模型基于注释上的位置的概率分布来预测一个或多个地理位置。

10. 发明申请

US20110087680A1 Method for Selecting Electronic Advertisements Using Machine Translation Techniques 有权
标题翻译：使用机器翻译技术选择电子广告的方法
公开(公告)号：US20110087680A1
公开(公告)日：2011-04-14
申请号：US12970757
申请日：2010-12-16
申请人： Vanessa Murdock , Massimiliano Ciaramita , Vassilis Plachouras
发明人： Vanessa Murdock , Massimiliano Ciaramita , Vassilis Plachouras
IPC分类号： G06F7/00 , G06F17/30 , G06F17/28
CPC分类号： G06Q30/02
摘要： A system for selecting electronic advertisements from an advertisement pool to match the surrounding content is disclosed. To select advertisements, the system takes an approach to content match that takes advantage of machine translation technologies. The system of the present invention implements this goal by means of simple and efficient machine translation features that are extracted from the surrounding context to match with the pool of potential advertisements. Machine translation features used as features for training a machine learning model. In one embodiment, a ranking SVM (Support Vector Machines) trained to identify advertisements relevant to a particular context. The trained machine learning model can then be used to rank advertisements for a particular context by supplying the machine learning model with the machine translation features measures for the advertisements and the surrounding context.
摘要翻译：公开了一种用于从广告池中选择电子广告以匹配周围内容的系统。为了选择广告，系统采取利用机器翻译技术的内容匹配的方法。本发明的系统通过简单有效的机器翻译功能来实现这一目标，这些机器翻译功能是从周围环境中提取的，以与潜在的广告池相匹配。机器翻译功能用作训练机器学习模型的特征。在一个实施例中，经训练以识别与特定上下文相关的广告的排名SVM（支持向量机）。训练后的机器学习模型然后可以用于通过向机器学习模型提供用于广告和周围环境的机器翻译特征措施来对特定上下文的广告进行排名。

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