Dynamic Mixed-Initiative Dialog Generation in Speech Recognition
    2.
    发明申请
    Dynamic Mixed-Initiative Dialog Generation in Speech Recognition 审中-公开
    语音识别中的动态混合主动对话生成

    公开(公告)号:US20090055163A1

    公开(公告)日:2009-02-26

    申请号:US11841147

    申请日:2007-08-20

    CPC classification number: G10L15/22 G06F17/2881 G10L15/1822

    Abstract: Disclosed are a method (500), apparatus (100) and computer program product for generating a mixed-initiative dialog to obtain information for dialog slots. A composite grammar dependent upon a set of unfilled slots is constructed (501). A prompt, dependent upon the a set of unfilled slots, is presented (309) to a user. An utterance is received (301) from the user in response to said prompt. Relevant information is determined based upon the further utterance. One or more said unfilled slots are filled (302) with said relevant information.

    Abstract translation: 公开了一种用于产生混合主动对话以获得对话槽的信息的方法(500),装置(100)和计算机程序产品。 构建依赖于一组未填充槽的复合语法(501)。 取决于一组未填充插槽的提示(309)被呈现给用户。 响应于所述提示,从用户接收(301)发声。 相关信息是基于进一步的话语来确定的。 一个或多个所述未填充的插槽用所述相关信息填充(302)。

    Execution of server-side dynamic pages
    3.
    发明授权
    Execution of server-side dynamic pages 有权
    执行服务器端动态页面

    公开(公告)号:US08010595B2

    公开(公告)日:2011-08-30

    申请号:US11289147

    申请日:2005-11-29

    CPC classification number: G06F9/54 H04L67/02

    Abstract: A system (30) and method are provided for single-pass execution of dynamic pages across multiple request-response cycles. The system (30) comprises a client (32) and server (34) in communication with one another. A container (35) resides on the server and handles requests made for the result of a dynamic page (36). The container controls the processing of the dynamic page. If the dynamic page requires additional information to continue processing, an intermediate request (44) is transmitted to the client, which responds with an intermediate response (46) containing the additional information. A notifier servlet (38) receives the intermediate response and passes the information to the dynamic page so that execution can resume without interruption.

    Abstract translation: 提供了一种用于在多个请求 - 响应周期内单次执行动态页面的系统(30)和方法。 系统(30)包括彼此通信的客户机(32)和服务器(34)。 容器(35)驻留在服务器上并处理为动态页面(36)产生的请求。 容器控制动态页面的处理。 如果动态页面需要附加信息以继续处理,则中间请求(44)被发送到客户端,客户端用包含附加信息的中间响应(46)进行响应。 通知器servlet(38)接收中间响应并将该信息传递给动态页面,以便执行可以不中断地恢复。

    Dynamic mixed-initiative dialog generation in speech recognition
    4.
    发明授权
    Dynamic mixed-initiative dialog generation in speech recognition 有权
    语音识别中的动态混合主动对话生成

    公开(公告)号:US07941312B2

    公开(公告)日:2011-05-10

    申请号:US12061748

    申请日:2008-04-03

    CPC classification number: G10L15/22 G06F17/2881 G10L15/1822

    Abstract: Disclosed are a method (500), apparatus (100) and computer program product for generating a mixed-initiative dialog to obtain information for dialog slots. A composite grammar dependent upon a set of unfilled slots is constructed (501). A prompt, dependent upon the a set of unfilled slots, is presented (309) to a user. An utterance is received (301) from the user in response to said prompt. Relevant information is determined based upon the further utterance. One or more said unfilled slots are filled (302) with said relevant information.

    Abstract translation: 公开了一种用于产生混合主动对话以获得对话槽的信息的方法(500),装置(100)和计算机程序产品。 构建依赖于一组未填充槽的复合语法(501)。 取决于一组未填充插槽的提示(309)被呈现给用户。 响应于所述提示,从用户接收(301)发声。 相关信息是基于进一步的话语来确定的。 一个或多个所述未填充的插槽用所述相关信息填充(302)。

    DYNAMIC MIXED-INITIATIVE DIALOG GENERATION IN SPEECH RECOGNITION
    6.
    发明申请
    DYNAMIC MIXED-INITIATIVE DIALOG GENERATION IN SPEECH RECOGNITION 有权
    语音识别中的动态混合对话对话生成

    公开(公告)号:US20090055165A1

    公开(公告)日:2009-02-26

    申请号:US12061748

    申请日:2008-04-03

    CPC classification number: G10L15/22 G06F17/2881 G10L15/1822

    Abstract: Disclosed are a method (500), apparatus (100) and computer program product for generating a mixed-initiative dialog to obtain information for dialog slots. A composite grammar dependent upon a set of unfilled slots is constructed (501). A prompt, dependent upon the a set of unfilled slots, is presented (309) to a user. An utterance is received (301) from the user in response to said prompt. Relevant information is determined based upon the further utterance. One or more said unfilled slots are filled (302) with said relevant information.

    Abstract translation: 公开了一种用于产生混合主动对话以获得对话槽的信息的方法(500),装置(100)和计算机程序产品。 构建依赖于一组未填充槽的复合语法(501)。 取决于一组未填充插槽的提示(309)被呈现给用户。 响应于所述提示,从用户接收(301)发声。 相关信息是基于进一步的话语来确定的。 一个或多个所述未填充的插槽用所述相关信息填充(302)。

    Execution of server-side dynamic pages
    7.
    发明申请
    Execution of server-side dynamic pages 有权
    执行服务器端动态页面

    公开(公告)号:US20070124479A1

    公开(公告)日:2007-05-31

    申请号:US11289147

    申请日:2005-11-29

    CPC classification number: G06F9/54 H04L67/02

    Abstract: A system (30) and method are provided for single-pass execution of dynamic pages across multiple request-response cycles. The system (30) comprises a client (32) and server (34) in communication with one another. A container (35) resides on the server and handles requests made for the result of a dynamic page (36). The container controls the processing of the dynamic page. If the dynamic page requires additional information to continue processing, an intermediate request (44) is transmitted to the client, which responds with an intermediate response (46) containing the additional information. A notifier servlet (38) receives the intermediate response and passes the information to the dynamic page so that execution can resume without interruption.

    Abstract translation: 提供了一种用于在多个请求 - 响应周期内单次执行动态页面的系统(30)和方法。 系统(30)包括彼此通信的客户机(32)和服务器(34)。 容器(35)驻留在服务器上并处理为动态页面(36)产生的请求。 容器控制动态页面的处理。 如果动态页面需要附加信息以继续处理,则中间请求(44)被发送到客户端,客户端用包含附加信息的中间响应(46)进行响应。 通知器servlet(38)接收中间响应并将该信息传递给动态页面,以便执行可以不中断地恢复。

Patent Agency Ranking