The invention discloses a voice interaction method, a server and a computer readable storage medium. The interaction method comprises the steps of receiving a current voice request forwarded by a vehicle, determining a first dialogue text according to the current voice request, and performing application program interface prediction and interface parameter filling on the first dialogue text according to the current voice request, the first dialogue text, a second dialogue text and a natural language understanding result of the second dialogue text, and sending an execution result of parameter filling to the vehicle to complete voice interaction. Therefore, processing of the dialogue text of the current dialogue round can be executed based on the current voice request, the first dialogue text of the current round, the second dialogue text of the previous dialogue round and the natural language understanding result of the second dialogue text, and voice interaction based on context and natural language processing based on multi-modal information are achieved. Therefore, the reliability and accuracy of application prediction and parameter filling can be guaranteed, and the user experience of the voice interaction function can be improved.

    本申请公开一种语音交互方法、服务器及计算机可读存储介质。交互方法包括:接收车辆转发的当前语音请求,根据当前语音请求确定第一对话文本,根据当前语音请求、第一对话文本、第二对话文本及第二对话文本的自然语言理解结果,对第一对话文本进行应用程序接口预测和接口参数填充,向车辆发送参数填充的执行结果以完成语音交互。如此,本申请使当前对话轮次的对话文本的处理可基于当前语音请求、当前轮次的第一对话文本、上一对话轮次的第二对话文本及第二对话文本的自然语言理解结果执行,实现基于上下文的语音交互和基于多模态信息的自然语言处理,因而可保障应用程序预测和参数填充的可靠与准确,可提升用户对于语音交互功能的使用体验。


    Access

    Download


    Export, share and cite



    Title :

    Voice interaction method, server and computer readable storage medium


    Additional title:

    语音交互方法、服务器及计算机可读存储介质


    Contributors:
    ZHU QIYU (author) / NING HONGKE (author) / FAN JUNFENG (author) / ZHAO QUN (author)

    Publication date :

    2024-10-22


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G10L Analyse oder Synthese von Sprache , SPEECH ANALYSIS OR SYNTHESIS / B60R Fahrzeuge, Fahrzeugausstattung oder Fahrzeugteile, soweit nicht anderweitig vorgesehen , VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR



    Voice interaction method, server and computer readable storage medium

    ZHU QIYU / FAN JUNFENG / ZHAO QUN | European Patent Office | 2024

    Free access

    Voice interaction method, server and computer readable storage medium

    FAN JUNFENG / ZHAO QUN / DING PENGJIE et al. | European Patent Office | 2024

    Free access

    Voice interaction method, server and computer readable storage medium

    FAN JUNFENG / DING PENGJIE / ZHAO QUN et al. | European Patent Office | 2023

    Free access

    Voice interaction method, server and computer readable storage medium

    DING PENGJIE / ZHAO QUN / NING HONGKE et al. | European Patent Office | 2024

    Free access

    Voice interaction method, server and computer readable storage medium

    WANG YI | European Patent Office | 2024

    Free access