中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

25 records (took 0.017 seconds)

    METHOD AND SYSTEM FOR NON-INTRUSIVE SPEAKER VERIFICATION USING BEHAVIOR MODELS
    3.
    发明申请
    METHOD AND SYSTEM FOR NON-INTRUSIVE SPEAKER VERIFICATION USING BEHAVIOR MODELS 审中-公开
    使用行为模型进行非侵入式语音识别的方法和系统

    公开(公告)号：WO03050799A1

    公开(公告)日：2003-06-19

    申请号：PCT/US0147910

    申请日：2001-12-12

    Applicant: IBM

    Inventor： RAMASWAMY GANESH N ,  CHAUDHARI UPENDRA V

    IPC: G06F17/27 ,  G06F17/28 ,  G06F21/00 ,  G10L15/18 ,  H04Q1/00 ,  G10L15/00 ,  G06F17/20

    CPC classification number: G06F17/2881 ,  G06F21/32 ,  G10L15/18 ,  G10L17/02 ,  G10L17/22

    Abstract: A system and method for verifying user identity, in accordance with the present invention, includes a conversational system (114) for receiving inputs from a user (110) and transforming the inputs into formal commands. A behavior verifier (118) is coupled to the conversational system (114) for extracting features from the inputs. The features include behavior patterns of the user. The behavior verifier (118) is adapted to compare the input behavior to a behavior model (214) to determine if the user is authorized to interact with the system.

    Abstract translation: 根据本发明的用于验证用户身份的系统和方法包括用于从用户（110）接收输入并将输入转换为正式命令的对话系统（114）。 行为验证器（118）耦合到对话系统（114），用于从输入中提取特征。 功能包括用户的行为模式。 行为验证器（118）适于将输入行为与行为模型（214）进行比较，以确定用户是否被授权与系统交互。

    INTELLIGENT CACHING AND NETWORK MANAGEMENT BASED ON LOCATION AND RESOURCE ANTICIPATION
    4.
    发明申请
    INTELLIGENT CACHING AND NETWORK MANAGEMENT BASED ON LOCATION AND RESOURCE ANTICIPATION 审中-公开
    基于位置和资源预测的智能高速缓存和网络管理

    公开(公告)号：WO03001327A3

    公开(公告)日：2003-02-27

    申请号：PCT/US0219658

    申请日：2002-06-20

    Applicant: IBM

    Inventor： GOPALAKRISHNAN PONANI ,  MAES STEPHANE H ,  RAMASWAMY GANESH N

    IPC: G06F17/30 ,  H04L12/24 ,  H04L29/06 ,  H04L29/08 ,  G06F13/00

    CPC classification number: G06F17/30902 ,  H04L29/06 ,  H04L41/0879 ,  H04L41/0886 ,  H04L41/0896 ,  H04L41/12 ,  H04L41/147 ,  H04L41/5067 ,  H04L67/18 ,  H04L67/2847 ,  H04L67/306 ,  H04L67/325 ,  H04L69/329

    Abstract: A system (100) for intelligent caching and network management. The system (100) includes event and time information (102) representing a user's schedule, a location database (106) including information about destination devices (110) and capabilities of the destination devices (110), a predictor (104) which receives the event and time information (102) and the information and capabilities of the destination devices to predict a location of the user and/or resources needed at the location, such that the resources are transferred to the user at a location when and where the resources are needed. User preference profiles (108), which include user preference information, are further employed by the predictor (104) to predict a location of the user and/or resources needed at the location.

    Abstract translation: 一种用于智能缓存和网络管理的系统（100）。 系统（100）包括表示用户调度的事件和时间信息（102），包括关于目的地设备（110）的信息和目的地设备（110）的能力的位置数据库（106），接收 事件和时间信息（102）以及目的地设备的信息和能力来预测在该位置处所需的用户和/或资源的位置，使得资源被传送到用户在资源是何处何地的位置 需要。 预测器（104）进一步使用包括用户偏好信息的用户偏好简档（108）来预测在该位置处所需的用户和/或资源的位置。

    METHODS AND APPARATUS FOR DYNAMIC USER AUTHENTICATION
    5.
    发明申请
    METHODS AND APPARATUS FOR DYNAMIC USER AUTHENTICATION 审中-公开
    动态用户认证的方法和设备

    公开(公告)号：WO2004042540A3

    公开(公告)日：2004-07-22

    申请号：PCT/US0322686

    申请日：2003-07-21

    Applicant: IBM

    Inventor： RAMASWAMY GANESH N ,  ZILCA RAN ,  ALECKSANDROVICH OLEG

    IPC: G06F1/00

    CPC classification number: H04L63/08 ,  G06F21/31 ,  G06F21/32 ,  H04L63/0861

    Abstract: An authentication framework is provided which enables dynamic user authentication that combines multiple authentication objects using a shared context and that permits customizable interaction design to suit varying user preferences and transaction/application requirements. Such a framework provides a high degree of flexibility, accuracy, convenience and robustness. In one illustrative aspect of the invention, an automated technique for user authentication comprises the following steps/operations. First, user input is obtained. At least a portion of the user input is associated with two or more verification objects. Then, the user is verified based on the two or more verification objects in accordance with at least one verification policy operating on a context shared across the two or more verification objects. The user authentication technique of the invention may preferably be implemented in a flexible, distributed architecture comprising at least one client device coupled to at least one verification server. The client device and the verification server may operate together to perform the user authentication techniques of the invention.

    Abstract translation: 提供了一种认证框架，其使得能够使用共享上下文组合多个认证对象的动态用户认证，并且允许可定制的交互设计以适应不同的用户偏好和交易/应用需求。 这样的框架提供了高度的灵活性，准确性，便利性和鲁棒性。 在本发明的一个说明性方面，用于用户认证的自动化技术包括以下步骤/操作。 首先，获得用户输入。 至少一部分用户输入与两个或更多个验证对象相关联。 然后，根据在跨两个或多个验证对象共享的上下文操作的至少一个验证策略，基于两个或多个验证对象来验证用户。 本发明的用户认证技术可以优选地以灵活的分布式架构来实现，其包括耦合到至少一个验证服务器的至少一个客户端设备。 客户端设备和验证服务器可以一起操作以执行本发明的用户认证技术。

    Method, system and program for sequential authentication using one or more error rates, which characterize each security challenge
    6.
    发明专利
    Method, system and program for sequential authentication using one or more error rates, which characterize each security challenge 有权
    使用一个或多个错误率进行顺序认证的方法，系统和程序，其特征在于每个安全挑战

    公开(公告)号：JP2007004796A

    公开(公告)日：2007-01-11

    申请号：JP2006169543

    申请日：2006-06-20

    Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

    Inventor： RAN ZILCA ,  JIRI NAVRATIL W ,  PELECANOS JASON W ,  RAMASWAMY GANESH N ,  RYAN L OSBORN

    IPC: G06F21/20 ,  H04L9/32

    CPC classification number: H04L63/0861 ,  G06F21/31 ,  G06F2221/2103 ,  H04L63/104

    Abstract: PROBLEM TO BE SOLVED: To provide a method and an apparatus for sequential user authentication using one or more error rates, which characterize each security challenge. SOLUTION: To acquire a intermediate authentication result, at least one knowledge challenge is attempted for a user, and the user challenge is continued until accumulated authentication results satisfy one or more criteria. The intermediate authentication result is based on one or more probabilities of errors for mis-acceptance and mis-rejection for every knowledge challenge. The probability of errors for mis-acceptance indicates a probability that the response is made by another user who has correctly answered for knowledge challenges, and the probability of errors for mis-rejection indicates a probability that the response is made by an authentic user who does not correctly answer for knowledge challenges. The probabilities of errors for mis-acceptance and mis-rejection can be adjusted based on known information on field data or specified challenges. COPYRIGHT: (C)2007,JPO&INPIT

    Abstract translation: 要解决的问题：提供一种用于使用一个或多个错误率进行顺序用户认证的方法和装置，其表征每个安全挑战。 解决方案：为了获得中间认证结果，尝试对用户进行至少一个知识挑战，并持续用户质询直到累积认证结果满足一个或多个标准。 中间认证结果基于每个知识挑战的错误接受和错误拒绝的一个或多个概率。 错误接受错误的概率表示响应是由正确应答知识挑战的另一用户做出的概率，错误拒绝的概率表示响应是由可靠的用户进行的响应的概率 不正确地回答知识面临的挑战。 可以根据现场数据或具体挑战的已知信息来调整错误接受和错误拒收的可能性。 版权所有（C）2007，JPO＆INPIT

    COMMAND BOUNDARY DISCRIMINATING DEVICE, METHOD AND PROGRAM MEMORY DEVICE
    7.
    发明专利
    COMMAND BOUNDARY DISCRIMINATING DEVICE, METHOD AND PROGRAM MEMORY DEVICE 失效

    公开(公告)号：JP2000132186A

    公开(公告)日：2000-05-12

    申请号：JP23021799

    申请日：1999-08-17

    Applicant: IBM

    Inventor： RAMASWAMY GANESH N ,  KLEINDIENST JAN

    IPC: G10L15/28 ,  G06F3/16 ,  G10L15/00 ,  G10L15/04 ,  G10L15/08 ,  G10L15/10 ,  G10L15/18 ,  G10L15/22 ,  G10L15/26

    Abstract: PROBLEM TO BE SOLVED: To provide a device for automatically discriminating a command boundary in a conversation type natural language system. SOLUTION: This device comprises a voice recognizing device 20 for converting an input signal into a recognized text 30 and a boundary discriminating device 40 connected to the voice recognizing device 20 to receive the recognized text 30 and determine whether a command is present in the recognized text 30 or not. The boundary discriminating device 40 outputs the command when the command is present in the recognized text 30. The method for discriminating a command boundary in a conversation type natural language system is also included.

    8.
    发明专利
    未知

    公开(公告)号：DE60037164T2

    公开(公告)日：2008-09-25

    申请号：DE60037164

    申请日：2000-08-11

    Applicant: IBM

    Inventor： COFFMAN DANIEL F ,  GOPALAKRISHNAN POPANI ,  RAMASWAMY GANESH N ,  KLEINDIENST JAN ,  CHALAPATHY NETI V

    IPC: G06F9/44 ,  G06F3/00 ,  G06F3/16 ,  G10L15/22

    Abstract: In accordance with the invention, a method and system for accessing a dialog system 101 employing a plurality of different clients 100, includes providing a first client device for accessing a conversational system 300 and presenting a command to the conversational system 300 by converting the command to a form understandable to the conversational system. The command is interpreted by employing a mediator 302, a dialog manager 303 and a multi-modal history 304 to determine the intent of the command based on a context of the command. A second client device is determined based on a predetermined device preference stored in the conversational system. An application is abstracted (400) to perform the command, and the results of the performance of the command are sent to the second client device.

    Natural language understanding system for command execution
    9.
    发明专利
    Natural language understanding system for command execution 未知

    公开(公告)号：GB2358499A

    公开(公告)日：2001-07-25

    申请号：GB0021378

    申请日：2000-09-01

    Applicant: IBM

    Inventor： RAMASWAMY GANESH N ,  JAMIESON KYLE A ,  KLEINDIENST JAN

    IPC: G10L15/18 ,  G10L15/22 ,  G10L15/26 ,  G10L15/00 ,  G06F3/00

    Abstract: A method and system, which may be implemented by employing a program, perform method steps of a natural language understanding (NLU) system which include tagging, 200, recognized words of a command input to the NLU system to associate the command with a context, and translating, 300, the command to at least one formal command based on the tagged words. A top ranked formal command is determined, 400, based on scoring of the tagged recognized words and scoring translations of the at least one formal command. Whether the top ranked formal command is accepted is determined by comparing a feature vector of the top ranked formal command to representations of feature vectors stored in an accept model. The top ranked formal command is executed, 500, if accepted and incorrect commands are prevented from execution.

Patent Agency Ranking