公开(公告)号：US06512922B1

公开(公告)日：2003-01-28

申请号：US09489641

申请日：2000-01-25

申请人： Bernard Burg ,  Ronnie Taib ,  Alan Schmitt

发明人： Bernard Burg ,  Ronnie Taib ,  Alan Schmitt

IPC分类号： H04Q720

CPC分类号： H04W4/02 ,  H04L67/34 ,  H04W4/20 ,  H04W8/18 ,  H04W80/04

摘要： A radio telecommunications network for providing information services to a mobile subscriber (22) includes a distributed arrangement of Agent Transceiver Systems (13, 14, 15), each associated with a base station (17, 18, 19) serving a respective geographical area, and each acting as a host platform for local information services. This distributed arrangement keeps the transmission loads due to accessed information which is added to the radio communications system to a minimum. A further feature of the invention allows mobility of a subscriber's personalised details to be moved around from platform to platform as he moves from one location to another, without interfering with the usual operation of the telecommunications system. Links (20, 21, 23) to a global services platform also provide access to Internet-type services.

摘要翻译： 用于向移动用户（22）提供信息服务的无线电电信网络包括代理收发器系统（13,14,15）的分布式布置，每个相关联的服务于相应地理区域的基站（17,18,19） 并且每个作为本地信息服务的主机平台。 这种分布式布置使得由于被添加到无线电通信系统的访问信息的传输负载降至最低。 本发明的另一特征允许用户的个性化细节的移动性在从一个位置移动到另一个位置时从平台移动到平台，而不会干扰电信系统的通常操作。 向全球服务平台（20,21,23）的链接也提供了对互联网类型服务的访问。

公开(公告)号：US20050004788A1

公开(公告)日：2005-01-06

申请号：US10613790

申请日：2003-07-03

申请人： Hang Shun Lee ,  Ronnie Taib

发明人： Hang Shun Lee ,  Ronnie Taib

IPC分类号： G06F20060101 ,  G06F9/45

CPC分类号： G06F3/038 ,  G10L13/00 ,  G10L15/26

摘要： A method and system (102) is provided for a multi-modal task-oriented dialog management implemented on a computer-based system. The system (102) maximizes the probability of successful task completion after a task is requested (302). Every task is associated with a task model comprising recipes, acts, parameters and modalities. Confidence measures are calculated at various levels for each task. The confidence measures represent the probability of success of the action depending on the user preferences. The most suitable recipe, act, parameter and modality are selected at runtime using the provided confidence measures (304) to maximize the probability of task completion. After each act, confidence measures are modified (312) depending on the user response, and the next suitable act is accordingly selected. Optionally, a post evaluation module (PEM) is provided for monitoring the user response and modifying the formulation for the confidence measures calculation.

摘要翻译： 提供了一种用于在基于计算机的系统上实现的多模式面向任务的对话管理的方法和系统（102）。 在请求任务之后，系统（102）最大化成功完成任务的可能性（302）。 每个任务与包括配方，动作，参数和模态的任务模型相关联。 对于每个任务，对各个层次的信心度量进行计算。 置信度度表示取决于用户偏好的动作成功的概率。 在运行时使用提供的置信度（304）选择最合适的配方，动作，参数和模态，以最大化任务完成的概率。 在每个动作之后，取决于用户的响应修改（312）置信度量度，因此选择下一个合适的动作。 可选地，提供后评估模块（PEM）用于监视用户响应并修改置信度测量计算的公式。