公开(公告)号：US20070136457A1

公开(公告)日：2007-06-14

申请号：US11300748

申请日：2005-12-14

申请人： Honghua Dai ,  Lee Wang ,  Ying Li ,  Zaiqing Nie ,  Ji-Rong Wen ,  Lingzhi Zhao

发明人： Honghua Dai ,  Lee Wang ,  Ying Li ,  Zaiqing Nie ,  Ji-Rong Wen ,  Lingzhi Zhao

IPC分类号： G06F15/173

CPC分类号： G06Q30/02

摘要： Features extracted from network browser pages and/or network search queries are leveraged to facilitate in detecting a user's browsing and/or searching intent. Machine learning classifiers constructed from these features automatically detect a user's online commercial intention (OCI). A user's intention can be commercial or non-commercial, with commercial intentions being informational or transactional. In one instance, an OCI ranking mechanism is employed with a search engine to facilitate in providing search results that are ranked according to a user's intention. This also provides a means to match purchasing advertisements with potential customers who are more than likely ready to make a purchase (transactional stage). Additionally, informational advertisements can be matched to users who are researching a potential purchase (informational stage).

摘要翻译： 从网络浏览器页面和/或网络搜索查询中提取的特征被利用以便于检测用户的浏览和/或搜索意图。 从这些功能构建的机器学习分类器自动检测用户的在线商业意图（OCI）。 用户的意图可以是商业的或非商业的，商业意图是信息或交易的。 在一种情况下，使用OCI排名机制与搜索引擎，以便于提供根据用户意图进行排名的搜索结果。 这也提供了一种方法来将购买广告与潜在客户相匹配，潜在客户可能准备进行购买（交易阶段）。 此外，信息广告可以与正在研究潜在购买（信息阶段）的用户相匹配。

公开(公告)号：US07831685B2

公开(公告)日：2010-11-09

申请号：US11300748

申请日：2005-12-14

申请人： Honghua Dai ,  Lee Wang ,  Ying Li ,  Zaiqing Nie ,  Ji-Rong Wen ,  Lingzhi Zhao

发明人： Honghua Dai ,  Lee Wang ,  Ying Li ,  Zaiqing Nie ,  Ji-Rong Wen ,  Lingzhi Zhao

IPC分类号： G06F15/16 ,  G06Q30/00

CPC分类号： G06Q30/02

摘要： Features extracted from network browser pages and/or network search queries are leveraged to facilitate in detecting a user's browsing and/or searching intent. Machine learning classifiers constructed from these features automatically detect a user's online commercial intention (OCI). A user's intention can be commercial or non-commercial, with commercial intentions being informational or transactional. In one instance, an OCI ranking mechanism is employed with a search engine to facilitate in providing search results that are ranked according to a user's intention. This also provides a means to match purchasing advertisements with potential customers who are more than likely ready to make a purchase (transactional stage). Additionally, informational advertisements can be matched to users who are researching a potential purchase (informational stage).

摘要翻译： 从网络浏览器页面和/或网络搜索查询中提取的特征被利用以便于检测用户的浏览和/或搜索意图。 从这些功能构建的机器学习分类器自动检测用户的在线商业意图（OCI）。 用户的意图可以是商业的或非商业的，商业意图是信息或交易的。 在一种情况下，使用OCI排名机制与搜索引擎，以便于提供根据用户意图进行排名的搜索结果。 这也提供了一种方法来将购买广告与潜在客户相匹配，潜在客户可能准备进行购买（交易阶段）。 此外，信息广告可以与正在研究潜在购买（信息阶段）的用户匹配。

公开(公告)号：US20070208728A1

公开(公告)日：2007-09-06

申请号：US11366526

申请日：2006-03-03

申请人： Benyu Zhang ,  Honghua Dai ,  Hua-Jun Zeng ,  Li Qi ,  Tarek Najm ,  Teresa Mah ,  Vladimir Shipunov ,  Ying Li ,  Zheng Chen

发明人： Benyu Zhang ,  Honghua Dai ,  Hua-Jun Zeng ,  Li Qi ,  Tarek Najm ,  Teresa Mah ,  Vladimir Shipunov ,  Ying Li ,  Zheng Chen

IPC分类号： G06F17/30

CPC分类号： G06F16/337 ,  G06F16/951

摘要： This invention provides a system and method for predicting user demographic attributes for non-registered users and users with incomplete profiles. The invention uses demographic information from registered users and user search history logs to create a database of information that associates the users' search history habits with their demographic attributes. The invention creates a first database that associates users' search query history with their demographic attributes, and also creates a second database that associates web pages that users have visited frequently along with the users' demographic attributes. The invention can compare the searching and browsing habits of non-registered users and users with incomplete profiles to the searching and browsing habits of registered users. Through the comparison, the invention can use the corresponding demographic attributes of the registered users to predict the demographic attributes of the non-registered users and the registered users with incomplete profiles.

摘要翻译： 本发明提供一种用于预测非注册用户和具有不完整简档的用户的用户人口统计属性的系统和方法。 本发明使用来自注册用户和用户搜索历史日志的人口统计信息来创建将用户的搜索历史习惯与其人口统计属性相关联的信息数据库。 本发明创建了将用户的搜索查询历史与其人口统计属性相关联的第一数据库，并且还创建了将用户经常访问的网页与用户的人口统计属性一起关联的第二数据库。 本发明可以将注册用户和注册用户不完整的用户的搜索和浏览习惯与注册用户的搜索和浏览习惯进行比较。 通过比较，本发明可以使用注册用户的相应人口统计特性来预测非注册用户和具有不完整简档的注册用户的人口统计属性。

公开(公告)号：US20090248663A1

公开(公告)日：2009-10-01

申请号：US12059687

申请日：2008-03-31

申请人： OMPRAKASH MANIYAR ,  HONGHUA DAI ,  YING LI

发明人： OMPRAKASH MANIYAR ,  HONGHUA DAI ,  YING LI

IPC分类号： G06F17/30

CPC分类号： G06F16/9537

摘要： Documents are provided that are geographically relevant to a user or a request. Information describing the online activity of a user is received and location identifiers are obtained. The plurality of location identifiers provide geographic location information defining the geographic intent of the information describing the online activity of the user, the location of the computing device utilized by the user, or the user's registered geographic location. Sets of predefined rules are then applied to the received information and the plurality of location identifiers to select at least one geographic location. Documents are then returned to the user that are geographically relevant based on the selected geographic location. The received information may include search queries, and the documents may include search results and/or advertisements.

摘要翻译： 提供与用户或请求在地理上相关的文档。 收到描述用户在线活动的信息，并获得位置标识符。 多个位置标识符提供定义描述用户的在线活动的信息的地理意图，用户使用的计算设备的位置或用户的注册地理位置的地理位置信息。 然后将预定义规则的集合应用于所接收的信息和多个位置标识符以选择至少一个地理位置。 然后根据所选择的地理位置将文档返回给与地理位置相关的用户。 所接收的信息可以包括搜索查询，并且文档可以包括搜索结果和/或广告。