Generating user information for use in targeted advertising
    1.
    发明授权
    Generating user information for use in targeted advertising 有权
    生成用于定向广告的用户信息

    公开(公告)号:US09235849B2

    公开(公告)日:2016-01-12

    申请号:US10750363

    申请日:2003-12-31

    IPC分类号: G06Q30/02 G06Q30/00 G06Q10/00

    摘要: User profile information for a user may be determined by (a) determining initial user profile information for the user, (b) inferring user profile information for the user, and (c) determining the user profile information for the user using both the initial user profile information and the inferred user profile information. Initial user profile information for the user may be determined using past search queries submitted by the user, and/or past document selections by the user. User profile information for the user may be inferred by (a) defining a node for each of a number of documents and the user, (b) adding edges between nodes if there is an association between the nodes to define a graph, and (c) inferring user profile information for the user using a topology of the graph and user profile information of other documents. Similarly, user profile information for a document may be determined by (a) determining initial user profile information for the document, (b) inferring user profile information for the document, and (c) determining the user profile information for the document using both the initial user profile information and the inferred user profile information. The initial user profile information for the document may be determined using content information from the document, and/or document meta information. User profile information for the document may be inferred by (a) defining a node for each of a number of documents and for each of a number of users, (b) adding edges between nodes if there is an association between the nodes to define a graph, and (c) inferring user profile information for the document using a topology of the graph and user profile information of users and of other documents. Document, user, and/or ad user profile information may be used when serving ads.

    摘要翻译: 可以通过以下方式确定用户的用户简档信息:(a)确定用户的初始用户简档信息,(b)推断用户的用户简档信息,以及(c)使用初始用户 配置文件信息和推断的用户配置文件信息。 可以使用用户提交的过去搜索查询和/或用户的过去文档选择来确定用户的初始用户简档信息。 可以通过(a)为多个文档和用户中的每一个定义一个节点来推断用户的用户简档信息,(b)如果节点之间存在关联以定义图形,则(b)在节点之间添加边,并且(c )使用图的拓扑和其他文档的用户简档信息来推断用户的用户简档信息。 类似地,文档的用户简档信息可以通过以下方式来确定:(a)确定文档的初始用户简档信息,(b)推断文档的用户简档信息,以及(c)使用两者 初始用户配置文件信息和推断的用户配置文件信息。 可以使用来自文档的内容信息和/或文档元信息来确定文档的初始用户简档信息。 可以通过以下方式来推断用于文档的用户简档信息:(a)为多个文档中的每一个为多个用户定义一个节点,以及为每个用户定义一个节点;(b)如果节点之间存在关联以定义一个 图形和(c)使用图形的拓扑和用户和其他文档的用户简档信息来推断文档的用户简档信息。 在投放广告时可以使用文档,用户和/或广告用户个人资料信息。

    Generating user information for use in targeted advertising
    2.
    发明申请
    Generating user information for use in targeted advertising 有权
    生成用于定向广告的用户信息

    公开(公告)号:US20050131762A1

    公开(公告)日:2005-06-16

    申请号:US10750363

    申请日:2003-12-31

    IPC分类号: G06Q10/00 G06F17/60

    摘要: User profile information for a user may be determined by (a) determining initial user profile information for the user, (b) inferring user profile information for the user, and (c) determining the user profile information for the user using both the initial user profile information and the inferred user profile information. Initial user profile information for the user may be determined using past search queries submitted by the user, and/or past document selections by the user. User profile information for the user may be inferred by (a) defining a node for each of a number of documents and the user, (b) adding edges between nodes if there is an association between the nodes to define a graph, and (c) inferring user profile information for the user using a topology of the graph and user profile information of other documents. Similarly, user profile information for a document may be determined by (a) determining initial user profile information for the document, (b) inferring user profile information for the document, and (c) determining the user profile information for the document using both the initial user profile information and the inferred user profile information. The initial user profile information for the document may be determined using content information from the document, and/or document meta information. User profile information for the document may be inferred by (a) defining a node for each of a number of documents and for each of a number of users, (b) adding edges between nodes if there is an association between the nodes to define a graph, and (c) inferring user profile information for the document using a topology of the graph and user profile information of users and of other documents. Document, user, and/or ad user profile information may be used when serving ads.

    摘要翻译: 可以通过以下方式确定用户的用户简档信息:(a)确定用户的初始用户简档信息,(b)推断用户的用户简档信息,以及(c)使用初始用户 配置文件信息和推断的用户配置文件信息。 可以使用用户提交的过去搜索查询和/或用户的过去文档选择来确定用户的初始用户简档信息。 可以通过(a)为多个文档和用户中的每一个定义一个节点来推断用户的用户简档信息,(b)如果节点之间存在关联以定义图形,则(b)在节点之间添加边,并且(c )使用图的拓扑和其他文档的用户简档信息来推断用户的用户简档信息。 类似地,文档的用户简档信息可以通过以下方式来确定:(a)确定文档的初始用户简档信息,(b)推断文档的用户简档信息,以及(c)使用两者 初始用户配置文件信息和推断的用户配置文件信息。 可以使用来自文档的内容信息和/或文档元信息来确定文档的初始用户简档信息。 可以通过以下方式来推断用于文档的用户简档信息:(a)为多个文档中的每一个为多个用户定义一个节点,以及为每个用户定义一个节点;(b)如果节点之间存在关联以定义一个 图形和(c)使用图形的拓扑和用户和其他文档的用户简档信息来推断文档的用户简档信息。 在投放广告时可以使用文档,用户和/或广告用户个人资料信息。

    Personalized network searching
    4.
    发明授权
    Personalized network searching 有权
    个性化网络搜索

    公开(公告)号:US08015170B2

    公开(公告)日:2011-09-06

    申请号:US12099583

    申请日:2008-04-08

    IPC分类号: G06F17/30

    摘要: Personalized network searching, in which a search query is received from a user, and a request is received to personalize a search result. Responsive to the search query and the request to personalize the search result, a personalized search result is generated by searching a personalized search object. Responsive to the search query, a general search result is generated by searching the general search object. The personalized search result and the general search result are provided to a client device, an advertisement is selected based at least in part upon the personalized search object, and the advertisement, the personalized search result, and the general search result are displayed.

    摘要翻译: 个性化网络搜索,其中从用户接收到搜索查询,并且接收到请求以个性化搜索结果。 响应于搜索查询和个性化搜索结果的请求,通过搜索个性化搜索对象来生成个性化搜索结果。 响应于搜索查询,通过搜索一般搜索对象来生成一般搜索结果。 将个性化搜索结果和一般搜索结果提供给客户端设备,至少部分地基于个性化搜索对象选择广告,并且显示广告,个性化搜索结果和一般搜索结果。

    DISTRIBUTED VOICE RECOGNITION SYSTEM AND METHOD
    5.
    发明申请
    DISTRIBUTED VOICE RECOGNITION SYSTEM AND METHOD 有权
    分布式语音识别系统和方法

    公开(公告)号:US20070011010A1

    公开(公告)日:2007-01-11

    申请号:US11427029

    申请日:2006-06-28

    IPC分类号: G10L21/00

    CPC分类号: G10L15/30

    摘要: A distributed voice recognition system (500) and method employs principles of bottom-up (i.e., raw input) and top-down (i.e., prediction based on past experience) processing to perform client-side and server-side processing by (i) at the client-side, replacing application data by a phonotactic table (504); (ii) at the server-side, tracking separate confidence scores for matches against an acoustic model and comparison to a grammar; and (iii) at the server-side using a contention resolver (514) to weight the client-side and server-side results to establish a single output which represents the collaboration between client-side processing and server-side processing.

    摘要翻译: 分布式语音识别系统(500)和方法采用自下而上(即原始输入)和自顶向下(即,基于过去经验的预测)处理来执行客户端和服务器端处理的原理(i) 在客户端,通过语音表替换应用数据(504); (ii)在服务器端,跟踪与声学模型匹配的单独置信度分数,并与语法进行比较; 和(iii)在服务器端使用竞争解决器(514)来加权客户端和服务器端的结果,以建立表示客户端处理和服务器端处理之间的协作的单个输出。

    Systems and Methods for Associating a Keyword With a User Interface Area
    6.
    发明申请
    Systems and Methods for Associating a Keyword With a User Interface Area 有权
    将关键字与用户界面区域相关联的系统和方法

    公开(公告)号:US20070271262A1

    公开(公告)日:2007-11-22

    申请号:US11834497

    申请日:2007-08-06

    IPC分类号: G06F17/30

    摘要: Systems and methods for associating a keyword with a window are described. In one described system, a computer program, such as an indexer, captures processor, or query system, associates a keyword with a first user interface area. The query system or other computer program receives a signal that the first user interface is inactive and that a second user interface area is active and, in response, generates an implicit search query that includes the keyword associated with the first user interface area.

    摘要翻译: 描述用于将关键字与窗口相关联的系统和方法。 在一个描述的系统中,计算机程序(诸如索引器,捕获处理器或查询系统)将关键字与第一用户界面区域相关联。 查询系统或其他计算机程序接收第一用户界面不活动并且第二用户界面区域是活动的信号,并且作为响应,生成包括与第一用户界面区域相关联的关键字的隐含搜索查询。

    Multiple client search method and system
    7.
    发明申请
    Multiple client search method and system 审中-公开
    多客户端搜索方法和系统

    公开(公告)号:US20070174246A1

    公开(公告)日:2007-07-26

    申请号:US11339301

    申请日:2006-01-25

    IPC分类号: G06F17/30

    CPC分类号: G06F16/1787

    摘要: A method includes receiving an event indicating an action associated with a first file has been performed by a user using a first client. The action is unrelated to transmitting the first file to another client. The method also includes automatically extracting content from the first file in response to the event using the first client and generating metadata to associate with the content, and transmitting, using the first client, the content and the metadata to a peer client if the peer client and the first client are currently operating and visible to each other on a network. The timing of the transmission is determined automatically after the event is received.

    摘要翻译: 一种方法包括接收指示与第一文件相关联的动作的事件已由用户使用第一客户端执行。 该操作与将第一个文件传输到另一个客户端无关。 该方法还包括响应于使用第一客户端的事件自动提取来自第一文件的内容并生成与内容相关联的元数据,并且如果对等客户端将对第一客户端的内容和元数据发送到对等客户端 并且第一客户端当前在网络上彼此操作和可见。 在接收到事件之后,自动确定发送的定时。

    Profile based capture component
    8.
    发明申请
    Profile based capture component 有权
    基于配置文件的捕获组件

    公开(公告)号:US20050246588A1

    公开(公告)日:2005-11-03

    申请号:US11051317

    申请日:2005-02-04

    IPC分类号: G06F11/30 G06F17/30 G06F11/00

    摘要: An indexing system in a computer system may include applications, a capture processor, a queue, a search engine, and a display processor. The indexing system captures events of user interactions with the applications. Events are queued and if indexable, indexed and stored for user access through the search engine. Capture components in the capture processor can include a keyboard capture component that processes user keystrokes to determine events. A display capture component captures event data from windows associated with the applications. Display event data can be captured on a polling schedule or based on state changes of window elements. To determine target applications and window applications of interest application profiles and window profiles can be used.

    摘要翻译: 计算机系统中的索引系统可以包括应用程序,捕获处理器,队列,搜索引擎和显示处理器。 索引系统捕获用户与应用程序交互的事件。 事件排队,如果可索引,索引和存储,以供用户通过搜索引擎访问。 捕获处理器中的捕获组件可以包括处理用户按键以确定事件的键盘捕获组件。 显示捕获组件从与应用程序相关的窗口捕获事件数据。 可以在轮询时间表上或基于窗口元素的状态变化来捕获显示事件数据。 可以使用感兴趣的应用程序配置文件和窗口配置文件来确定目标应用程序和窗口应用程序。

    Methods and systems for information capture and retrieval
    9.
    发明申请
    Methods and systems for information capture and retrieval 有权
    用于信息捕获和检索的方法和系统

    公开(公告)号:US20050234848A1

    公开(公告)日:2005-10-20

    申请号:US10881584

    申请日:2004-06-30

    IPC分类号: G06F7/00 G06F17/30

    CPC分类号: G06F17/30864

    摘要: Systems and methods that identify and extract information from articles are described. In one embodiment, a search engine implements a method comprising capturing an event in real time upon the occurrence of the event, wherein the event comprises a user interaction with an article on a client device, wherein the article is capable of being associated with at least one of a plurality of client applications, determining if the event should be indexed, and if the event should be indexed, indexing the event and storing the event and at least a portion of content associated with the article.

    摘要翻译: 描述了从文章中识别和提取信息的系统和方法。 在一个实施例中,搜索引擎实现一种方法,包括在事件发生时实时捕获事件,其中事件包括与客户端设备上的物品的用户交互,其中该物品能够至少与 多个客户应用程序之一,确定事件是否应被索引,以及如果事件应被索引,索引事件并存储事件以及与该文章相关联的内容的至少一部分。

    Systems and methods for weighting a search query result
    10.
    发明申请
    Systems and methods for weighting a search query result 有权
    用于加权搜索查询结果的系统和方法

    公开(公告)号:US20050222981A1

    公开(公告)日:2005-10-06

    申请号:US10815074

    申请日:2004-03-31

    IPC分类号: G06F7/00 G06F17/30

    CPC分类号: G06F17/30864

    摘要: Systems and methods for weighting a search query result are described. In one described system, a program, such as a query system, determines a first article identifier associated with a source and receives an input signal indicating an interest in the first article identifier. The query system then determines a second article identifier associated with the source and determines a score associated with the second article identifier based at least in part on the input signal.

    摘要翻译: 描述用于加权搜索查询结果的系统和方法。 在一个描述的系统中,诸如查询系统的程序确定与源相关联的第一文章标识符,并且接收指示对第一文章标识符感兴趣的输入信号。 查询系统然后确定与源相关联的第二物品标识符,并且至少部分地基于输入信号确定与第二物品标识符相关联的得分。