利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

8 条记录 (耗时 0.014 秒)

    EFFICIENT PROCESSING OF MAPPED BOOLEAN QUERIES VIA GENERATIVE INDEXING
    1.
    发明申请
    EFFICIENT PROCESSING OF MAPPED BOOLEAN QUERIES VIA GENERATIVE INDEXING 审中-公开
    通过生成指标对映射布朗问题的有效处理

    公开(公告)号：US20090055358A1

    公开(公告)日：2009-02-26

    申请号：US12190894

    申请日：2008-08-13

    申请人： Anthony Tomasic

    发明人： Anthony Tomasic

    IPC分类号： G06F17/30

    CPC分类号： G06F16/31 ,  G06F16/3337 ,  G16B30/00 ,  G16B50/00

    摘要： A computer assisted method of searching at least one corpus of information based on at least one query. The method includes creating a generative index based on the corpus and a mapping of terms of the query to terms of the corpus. The method also includes searching the generative index and the corpus with the query to create a result comprising a portion of the corpus, wherein the result satisfies the query.

    摘要翻译： 一种基于至少一个查询来搜索至少一个信息语料库的计算机辅助方法。 该方法包括基于语料库创建生成索引，并将查询的术语映射到语料库的术语。 该方法还包括使用查询搜索生成索引和语料库以创建包含语料库的一部分的结果，其中结果满足查询。

    Systems and methods for implementing a machine-learning agent to retrieve information in response to a message
    4.
    发明授权
    Systems and methods for implementing a machine-learning agent to retrieve information in response to a message 有权
    用于实现机器学习代理以响应于消息来检索信息的系统和方法

    公开(公告)号：US08533132B2

    公开(公告)日：2013-09-10

    申请号：US12841714

    申请日：2010-07-22

    申请人： John Zimmerman ,  Anthony Tomasic ,  Ian Hargraves

    发明人： John Zimmerman ,  Anthony Tomasic ,  Ian Hargraves

    IPC分类号： G06F15/18

    CPC分类号： G06N99/005

    摘要： Mixed-initiative message-augmenting agent systems and methods that provide users with tools that allow them to respond to messages, such as email messages, containing requests for information or otherwise requiring responses that require information that needs to be retrieved from one or more data sources. The systems and methods allow users to train machine-learning agents how to retrieve and present information in responses to like messages so that the machine-learning agents can eventually automatedly generate responses with minimal involvement by the users. Embodiments of the systems and methods allow users to build message-augmenting forms containing the desired information for responding to messages and to demonstrate to the machine-learning agents where to retrieve pertinent information for populating the forms. Embodiments of the systems and methods allow users to modify and repair automatically generated forms to continually improve the knowledge of the machine-learning agents.

    摘要翻译： 混合主动消息增强代理系统和方法，为用户提供允许他们响应包含信息请求的消息（如电子邮件）或需要需要从一个或多个数据源检索到信息的响应的工具 。 系统和方法允许用户训练机器学习代理如何在类似消息的响应中检索和呈现信息，使得机器学习代理最终能够以最少的用户参与自动生成响应。 系统和方法的实施例允许用户构建包含用于响应消息的期望信息的消息增加表单，并向机器学习代理程序证明哪里可以检索用于填充表单的相关信息。 系统和方法的实施例允许用户修改和修复自动生成的表单，以不断地改进机器学习代理的知识。

    Intent-based information processing and updates in association with a service agent
    6.
    发明申请
    Intent-based information processing and updates in association with a service agent 有权
    与服务代理相关联的基于意图的信息处理和更新

    公开(公告)号：US20060235691A1

    公开(公告)日：2006-10-19

    申请号：US11405661

    申请日：2006-04-17

    申请人： Anthony Tomasic ,  John Zimmerman

    发明人： Anthony Tomasic ,  John Zimmerman

    IPC分类号： G10L15/00 ,  G06F3/00 ,  G06F13/00 ,  G10L15/18 ,  G10L15/16 ,  H04N5/445

    CPC分类号： G06F17/30401 ,  G06F3/0481 ,  G06Q10/10 ,  G10L15/18 ,  G10L2015/223

    摘要： In various embodiments, a method for processing a request made by a requester is provided. The method may include receiving at least one request from at least one requester, the request being in the form of natural language; analyzing the request with an agent; selecting at least one form based on analyzing the request; permitting a service agent to perform at least one step in association with the request; executing at least one update based on at least one form; and, forwarding information regarding processing of the request to a learning module operatively associated with the agent.

    摘要翻译： 在各种实施例中，提供了一种用于处理由请求者作出的请求的方法。 该方法可以包括从至少一个请求者接收至少一个请求，该请求以自然语言的形式; 用代理分析请求; 基于分析请求选择至少一个表单; 允许服务代理与请求相关联地执行至少一个步骤; 基于至少一个表单执行至少一个更新; 以及将关于所述请求的处理的信息转发到与所述代理可操作地相关联的学习模块。

    Systems and Methods for Implementing a Machine-Learning Agent to Retrieve Information in Response to a Message
    7.
    发明申请
    Systems and Methods for Implementing a Machine-Learning Agent to Retrieve Information in Response to a Message 有权
    用于实现机器学习代理以响应消息检索信息的系统和方法

    公开(公告)号：US20110022552A1

    公开(公告)日：2011-01-27

    申请号：US12841714

    申请日：2010-07-22

    申请人： John Zimmerman ,  Anthony Tomasic ,  Ian Hargraves

    发明人： John Zimmerman ,  Anthony Tomasic ,  Ian Hargraves

    IPC分类号： G06F15/18 ,  G06F17/00 ,  G06F15/16

    CPC分类号： G06N99/005

    摘要： Mixed-initiative message-augmenting agent systems and methods that provide users with tools that allow them to respond to messages, such as email messages, containing requests for information or otherwise requiring responses that require information that needs to be retrieved from one or more data sources. The systems and methods allow users to train machine-learning agents how to retrieve and present information in responses to like messages so that the machine-learning agents can eventually automatedly generate responses with minimal involvement by the users. Embodiments of the systems and methods allow users to build message-augmenting forms containing the desired information for responding to messages and to demonstrate to the machine-learning agents where to retrieve pertinent information for populating the forms. Embodiments of the systems and methods allow users to modify and repair automatically generated forms to continually improve the knowledge of the machine-learning agents.

    摘要翻译： 混合主动消息增强代理系统和方法，为用户提供允许他们响应包含信息请求的消息（例如电子邮件）或需要需要从一个或多个数据源检索到信息的响应的工具 。 系统和方法允许用户训练机器学习代理如何在类似消息的响应中检索和呈现信息，使得机器学习代理最终能够以最少的用户参与自动生成响应。 系统和方法的实施例允许用户构建包含用于响应消息的期望信息的消息增加表单，并向机器学习代理程序证明哪里可以检索用于填充表单的相关信息。 系统和方法的实施例允许用户修改和修复自动生成的表单，以不断地改进机器学习代理的知识。

    Method and apparatus for indexing document content and content comparison with World Wide Web search service
    8.
    发明授权
    Method and apparatus for indexing document content and content comparison with World Wide Web search service 有权
    使用万维网搜索服务索引文档内容和内容比较的方法和装置

    公开(公告)号：US06757675B2

    公开(公告)日：2004-06-29

    申请号：US10365839

    申请日：2003-02-12

    申请人： Alex Aiken ,  Saul Schleimer ,  Joel Auslander ,  Daniel Wilkerson ,  Anthony Tomasic ,  Steve Fink

    发明人： Alex Aiken ,  Saul Schleimer ,  Joel Auslander ,  Daniel Wilkerson ,  Anthony Tomasic ,  Steve Fink

    IPC分类号： G06F1730

    CPC分类号： G06F17/30628 ,  G06F17/30864 ,  Y10S707/99933 ,  Y10S707/99934

    摘要： Methods and related systems for indexing the contents of documents for comparison with the contents of other documents to identify matching content. A method for comparing the contents of a query document to the content on the World Wide Web is set forth. The contents of a query document are indexed and compared to content from the World Wide Web which is continuously retrieved and indexed. The method for indexing may comprise selecting substrings from the document, hashing the substrings to generate a plurality of hash values having a known range of values, selecting certain hash values to save from the generated hash values, and sorting the saved hash values. Methods for selecting certain hash values to save are set forth.

    摘要翻译： 用于索引文件内容的方法和相关系统与其他文件的内容进行比较，以识别匹配内容。 阐述了将查询文档的内容与万维网上的内容进行比较的方法。 查询文档的内容被索引并与来自万维网的内容进行比较，该内容被连续检索和索引。 用于索引的方法可以包括从文档中选择子串，将子串散列以产生具有已知值范围的多个哈希值，从所生成的散列值中选择某些哈希值以保存，以及对所保存的哈希值进行排序。 阐述了选择某些哈希值进行保存的方法。