The invention discloses a voice interaction method, and the method comprises the steps: obtaining a current voice request, recognizing a target application scene type corresponding to the current voice request, and carrying out the recognition of the target application scene type based on a predetermined corresponding relation between the application scene type and a prompt information template, and in combination with a plurality of pre-configured prompt information templates. And determining target prompt information corresponding to the target application scene category, determining a target vehicle control instruction corresponding to the current voice request according to the target prompt information and the large language model, and completing voice interaction. Thus, the server determines the target prompt information according to the target application scene category corresponding to the current voice request and the pre-configured prompt information template, and the large language model determines the target vehicle control instruction according to the target prompt information. Therefore, the large language model can determine the vehicle control instruction according to the prompt information corresponding to the voice request, the condition that model reasoning is difficult to reliably guide by fixed prompt is improved, and the reasoning precision is guaranteed.

    本申请公开一种语音交互方法,所述方法包括:获取当前语音请求,识别当前语音请求对应的目标应用场景类别,基于预先确定的应用场景类别与提示信息模板的对应关系,及结合预先配置的多种提示信息模板,确定与目标应用场景类别相对应的目标提示信息,根据目标提示信息和大语言模型,确定当前语音请求所对应的目标车辆控制指令,完成语音交互。如此,本申请的服务器根据当前语音请求对应的目标应用场景类别,及预先配置的提示信息模板确定目标提示信息,大语言模型根据目标提示信息,确定目标车辆控制指令,使得大语言模型可根据语音请求对应的提示信息确定车辆控制指令,改善固定提示难以可靠地引导模型推理的情况,推理精度得以保障。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Voice interaction method, server and computer readable storage medium


    Weitere Titelangaben:

    语音交互方法、服务器及计算机可读存储介质


    Beteiligte:
    HU JING (Autor:in)

    Erscheinungsdatum :

    2024-02-13


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    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

    FAN JUNFENG / ZHAO QUN / JIAN TAOWEN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Voice interaction method, server and computer readable storage medium

    FAN JUNFENG / DING PENGJIE / ZHAO QUN et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Voice interaction method, server and computer readable storage medium

    WANG YI | Europäisches Patentamt | 2024

    Freier Zugriff

    VOICE INTERACTION METHOD, SERVER, AND COMPUTER-READABLE STORAGE MEDIUM

    ZHANG XIKANG / ZHAO YAO / WANG TIANYI | Europäisches Patentamt | 2024

    Freier Zugriff

    Voice interaction method, server and computer readable storage medium

    FAN JUNFENG / NING HONGKE / ZHAO QUN | Europäisches Patentamt | 2022

    Freier Zugriff