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

US08499008B2 Mixing knowledge sources with auto learning for improved entity extraction 有权
标题翻译：将知识来源与自动学习相结合，改进实体提取
公开(公告)号：US08499008B2
公开(公告)日：2013-07-30
申请号：US12509310
申请日：2009-07-24
申请人： Marco Pennacchiotti , Patrick Pantel
发明人： Marco Pennacchiotti , Patrick Pantel
IPC分类号： G06F17/30
CPC分类号： G06N99/005
摘要： The disclosed embodiments of computer systems and techniques utilize an ensemble semantics framework to combine knowledge acquisition systems that yield significantly higher quality resources than each system in isolation. Gains in entity extraction are achieved by combining state-of-the-art distributional and pattern-based systems with a large set of features from, for example, a webcrawl, query logs, and wisdom of the crowd sources. This results in improved query interpretation and greater relevancy in providing search results and advertising, for example.
摘要翻译：所公开的计算机系统和技术的实施例利用集合语义框架来组合知识获取系统，其产生比每个系统孤立地显着更高质量的资源。实体提取的收益通过将最先进的分布式和基于模式的系统与来自例如webcrawl，查询日志和人群智慧的大量功能组合来实现。例如，这可以提高查询解释和提供搜索结果和广告的相关性。

2. 发明授权

US09466071B2 Social media user recommendation system and method 有权
标题翻译：社交媒体用户推荐系统和方法
公开(公告)号：US09466071B2
公开(公告)日：2016-10-11
申请号：US13297988
申请日：2011-11-16
申请人： Marco Pennacchiotti , Siva Gurumurthy
发明人： Marco Pennacchiotti , Siva Gurumurthy
IPC分类号： G06F15/18 , G06Q30/02 , G06N99/00 , G06Q50/00
CPC分类号： G06F17/3097 , G06F17/30867 , G06N99/005 , G06Q30/0255 , G06Q50/01
摘要： Each user is represented by a mixture of topics, e.g., one or more topics, and a probability of interest in each topic in the mixture, and given the target user, one or more other users can be recommended, each user that is recommended to the target user is determined to have a topical interest similarity with the target user, e.g., the target user's interest in one or more topics of the mixtures of topics is determined to be similar to a recommended interest in the one or more topics of the mixture of topics. The target user and the one or more recommended users can be said to have similar topical interests. The target user can use the user recommendation to establish an interactive dialogue, for example, with one or more users identified in the user recommendation.
摘要翻译：每个用户通过主题的混合来表示，例如一个或多个主题，以及混合中每个主题的兴趣概率，并且给予目标用户，可以推荐一个或多个其他用户，推荐使用每个用户目标用户被确定为与目标用户具有主题兴趣相似性，例如，目标用户对主题混合物的一个或多个主题的兴趣被确定为与混合物的一个或多个主题中的推荐兴趣相似的主题。目标用户和一个或多个推荐用户可以说具有类似的主题兴趣。目标用户可以使用用户建议来建立例如与用户推荐中标识的一个或多个用户的交互对话。

3. 发明申请

US20110022550A1 MIXING KNOWLEDGE SOURCES WITH AUTO LEARNING FOR IMPROVED ENTITY EXTRACTION 有权
标题翻译：混合知识来源与自动学习改进实体提取
公开(公告)号：US20110022550A1
公开(公告)日：2011-01-27
申请号：US12509310
申请日：2009-07-24
申请人： Marco Pennacchiotti , Patrick Pantel
发明人： Marco Pennacchiotti , Patrick Pantel
IPC分类号： G06F15/18
CPC分类号： G06N99/005
摘要： The disclosed embodiments of computer systems and techniques utilize an ensemble semantics framework to combine knowledge acquisition systems that yield significantly higher quality resources than each system in isolation. Gains in entity extraction are achieved by combining state-of-the-art distributional and pattern-based systems with a large set of features from, for example, a webcrawl, query logs, and wisdom of the crowd sources. This results in improved query interpretation and greater relevancy in providing search results and advertising, for example.
摘要翻译：所公开的计算机系统和技术的实施例利用集合语义框架来组合知识获取系统，其产生比每个系统孤立地显着更高质量的资源。实体提取的收益通过将最先进的分布式和基于模式的系统与来自例如webcrawl，查询日志和人群智慧的大量功能组合来实现。例如，这可以提高查询解释和提供搜索结果和广告的相关性。

4. 发明申请

US20160092791A1 MINING TEXTUAL FEEDBACK 审中-公开
标题翻译：采矿文字反馈
公开(公告)号：US20160092791A1
公开(公告)日：2016-03-31
申请号：US14586789
申请日：2014-12-30
申请人： Samaneh Abbasi Moghaddam , Marco Pennacchiotti , Thomas Normile
发明人： Samaneh Abbasi Moghaddam , Marco Pennacchiotti , Thomas Normile
IPC分类号： G06N99/00 , G06Q30/02
CPC分类号： G06N99/005 , G06F17/2785 , G06F17/30707 , G06F17/30719 , G06Q30/0282
摘要： Methods, systems, and apparatus for mining feedback are described. A set of one or more lexical patterns associated with one or more of a suggestion and a defect report are determined and the set of one or more lexical patterns are matched against a plurality of feedback items to generate a distance learning training set. A distance learning technique is applied to the distance learning training set to generate a distance learning model and the distance learning model is used to identify one or more candidate feedback items of the plurality of feedback items, each of which is one or more of a candidate suggestion and a candidate defect report.
摘要翻译：描述了采矿反馈的方法，系统和装置。确定与建议和缺陷报告中的一个或多个相关联的一个或多个词汇模式的集合，并且将一个或多个词汇模式的集合与多个反馈项目进行匹配以生成远程学习训练集合。远程学习技术被应用于距离学习训练集合以产生距离学习模型，并且使用距离学习模型来识别多个反馈项目中的一个或多个候选反馈项目，每个候选反馈项目是候选者中的一个或多个建议和候选缺陷报告。

5. 发明申请

US20130124437A1 SOCIAL MEDIA USER RECOMMENDATION SYSTEM AND METHOD 有权
标题翻译：社会媒体用户建议系统及方法
公开(公告)号：US20130124437A1
公开(公告)日：2013-05-16
申请号：US13297988
申请日：2011-11-16
申请人： MARCO PENNACCHIOTTI , SIVA GURUMURTHY
发明人： MARCO PENNACCHIOTTI , SIVA GURUMURTHY
IPC分类号： G06F15/18
CPC分类号： G06F17/3097 , G06F17/30867 , G06N99/005 , G06Q30/0255 , G06Q50/01
摘要： Each user is represented by a mixture of topics, e.g., one or more topics, and a probability of interest in each topic in the mixture, and given the target user, one or more other users can be recommended, each user that is recommended to the target user is determined to have a topical interest similarity with the target user, e.g., the target user's interest in one or more topics of the mixtures of topics is determined to be similar to a recommended interest in the one or more topics of the mixture of topics. The target user and the one or more recommended users can be said to have similar topical interests. The target user can use the user recommendation to establish an interactive dialogue, for example, with one or more users identified in the user recommendation.
摘要翻译：每个用户通过主题的混合来表示，例如一个或多个主题，以及混合中每个主题的兴趣概率，并且给予目标用户，可以推荐一个或多个其他用户，推荐使用每个用户目标用户被确定为与目标用户具有主题兴趣相似性，例如，目标用户对主题混合物的一个或多个主题的兴趣被确定为与混合物的一个或多个主题中的推荐兴趣相似的主题。目标用户和一个或多个推荐用户可以说具有相似的主题兴趣。目标用户可以使用用户建议来建立例如与用户推荐中标识的一个或多个用户的交互对话。

6. 发明授权

US10127522B2 Automatic profiling of social media users 有权
公开(公告)号：US10127522B2
公开(公告)日：2018-11-13
申请号：US13183260
申请日：2011-07-14
申请人： Marco Pennacchiotti , Ana-Maria Popescu
发明人： Marco Pennacchiotti , Ana-Maria Popescu
IPC分类号： G06Q10/10 , G06Q30/02 , G06Q50/00
摘要： Disclosed are methods and apparatus for classifying users. In accordance with one embodiment, a plurality of messages posted by a user via a microblogging service may be obtained. A set of feature values associated with the user may be obtained, each of the set of feature values corresponding to a different one of a set of one or more features. One or more of the set of feature values may be obtained based, at least in part, on content of the plurality of messages posted by the user, messaging behavior of the user via the microblogging service, and/or social connections of the user established via the microblogging service. The user may be classified based upon the set of feature values associated with the user.

7. 发明授权

US09105008B2 Detecting controversial events 有权
标题翻译：检测有争议的事件
公开(公告)号：US09105008B2
公开(公告)日：2015-08-11
申请号：US12955007
申请日：2010-11-29
申请人： Ana-Maria Popescu , Marco Pennacchiotti
发明人： Ana-Maria Popescu , Marco Pennacchiotti
IPC分类号： G06F15/173 , G06Q10/10 , G06Q50/00
CPC分类号： G06Q10/10 , G06Q50/01
摘要： A method, device, and computer-readable storage medium storing instructions are provided for detecting controversial events that are reflected in user-generated content items. In a single-step approach, user-generated content items are received and analyzed by a controversial event detection module, which determines the likelihood that sets of content items reflect controversial events. In one example, public posts by users of a social networking service are grouped into snapshots of posts that are associated with an entity and were generated during a window of time. An event detection module may determine the likelihood that snapshots reflect events. In a two-step approach, event snapshots are provided to a controversy detection module, which determines the likelihood that event snapshots are controversial. In a blended approach, snapshots are provided to a controversy detection module, which determines the likelihood that snapshots are controversial events based in part on the event score.
摘要翻译：提供了存储指令的方法，设备和计算机可读存储介质，用于检测反映在用户生成的内容项中的有争议的事件。在单步方法中，由有争议的事件检测模块接收和分析用户生成的内容项目，该模块确定内容项集合反映有争议的事件的可能性。在一个示例中，社交网络服务的用户的公共帖子被分组为与实体相关联并且在时间窗口期间生成的帖子的快照。事件检测模块可以确定快照反映事件的可能性。以两步法，事件快照被提供给一个争议检测模块，这决定了事件快照有争议的可能性。在混合方法中，将快照提供给争议检测模块，该模块确定快照是部分基于事件分数的有争议事件的可能性。

8. 发明申请

US20140244361A1 SYSTEM AND METHOD OF PREDICTING PURCHASE BEHAVIORS FROM SOCIAL MEDIA 审中-公开
标题翻译：从社会媒体预测购买行为的系统和方法
公开(公告)号：US20140244361A1
公开(公告)日：2014-08-28
申请号：US14103062
申请日：2013-12-11
申请人： Yongzheng Zhang , Marco Pennacchiotti
发明人： Yongzheng Zhang , Marco Pennacchiotti
IPC分类号： G06Q30/02
CPC分类号： G06Q30/0204
摘要： In an example embodiment, a first social media profile is retrieved. Express interests in the first social media profile are extracted, and social media categories corresponding to the express interests are identified. Demographic information is also extracted from the first social media profile. Then, the identified social media categories and demographic information are correlated with ecommerce categories of purchases. Using results from the correlating, a machine learning process is configured, the machine learning process accepting a second social media profile as input and returning a prediction of an ecommerce category as output.
摘要翻译：在示例实施例中，检索第一社交媒体简档。提取对第一个社交媒体简介的兴趣，确定与特定兴趣相对应的社交媒体类别。人口信息也从第一个社交媒体简介中提取出来。然后，所识别的社交媒体类别和人口信息与购买的电子商务类别相关联。使用相关的结果，配置机器学习过程，机器学习过程接受第二社交媒体简档作为输入并返回电子商务类别的预测作为输出。

9. 发明申请

US20130018968A1 AUTOMATIC PROFILING OF SOCIAL MEDIA USERS 审中-公开
标题翻译：社会媒体用户的自动分类
公开(公告)号：US20130018968A1
公开(公告)日：2013-01-17
申请号：US13183260
申请日：2011-07-14
申请人： Marco Pennacchiotti , Ana-Maria Popescu
发明人： Marco Pennacchiotti , Ana-Maria Popescu
IPC分类号： G06F15/16
CPC分类号： G06Q30/0201 , G06Q10/10 , G06Q50/01
摘要： Disclosed are methods and apparatus for classifying users. In accordance with one embodiment, a plurality of messages posted by a user via a microblogging service may be obtained. A set of feature values associated with the user may be obtained, each of the set of feature values corresponding to a different one of a set of one or more features. One or more of the set of feature values may be obtained based, at least in part, on content of the plurality of messages posted by the user, messaging behavior of the user via the microblogging service, and/or social connections of the user established via the microblogging service. The user may be classified based upon the set of feature values associated with the user.
摘要翻译：公开了用于对用户进行分类的方法和装置。根据一个实施例，可以获得由用户通过微博服务发布的多个消息。可以获得与用户相关联的一组特征值，所述一组特征值中的每一个对应于一组或多个特征中的不同的一个。可以至少部分地基于用户发布的多个消息的内容，经由微博服务的用户的消息行为和/或建立的用户的社交连接来获得该组特征值中的一个或多个通过微博服务。可以基于与用户相关联的一组特征值对用户进行分类。

10. 发明申请

US20120136985A1 DETECTING CONTROVERSIAL EVENTS 有权
标题翻译：检测对比事件
公开(公告)号：US20120136985A1
公开(公告)日：2012-05-31
申请号：US12955007
申请日：2010-11-29
申请人： Ana-Maria Popescu , Marco Pennacchiotti
发明人： Ana-Maria Popescu , Marco Pennacchiotti
IPC分类号： G06F15/16
CPC分类号： G06Q10/10 , G06Q50/01
摘要： A method, device, and computer-readable storage medium storing instructions are provided for detecting controversial events that are reflected in user-generated content items. In a single-step approach, user-generated content items are received and analyzed by a controversial event detection module, which determines the likelihood that sets of content items reflect controversial events. In one example, public posts by users of a social networking service are grouped into snapshots of posts that are associated with an entity and were generated during a window of time. An event detection module may determine the likelihood that snapshots reflect events. In a two-step approach, event snapshots are provided to a controversy detection module, which determines the likelihood that event snapshots are controversial. In a blended approach, snapshots are provided to a controversy detection module, which determines the likelihood that snapshots are controversial events based in part on the event score.
摘要翻译：提供了存储指令的方法，设备和计算机可读存储介质，用于检测反映在用户生成的内容项中的有争议的事件。在单步方法中，由有争议的事件检测模块接收和分析用户生成的内容项，该模块确定内容项集合反映有争议的事件的可能性。在一个示例中，社交网络服务的用户的公共帖子被分组为与实体相关联并且在时间窗口期间生成的帖子的快照。事件检测模块可以确定快照反映事件的可能性。以两步法，事件快照被提供给一个争议检测模块，这决定了事件快照有争议的可能性。在混合方法中，将快照提供给争议检测模块，该模块确定快照是部分基于事件分数的有争议事件的可能性。

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