The invention discloses a voice interaction method, a server and a computer readable storage medium, and the method comprises the steps: receiving a current voice request forwarded by a vehicle, and under the condition that a corresponding vehicle control instruction is not determined according to the current voice request, according to a large language model and the current voice request, carrying out the voice interaction according to the large language model and the current voice request; and determining target guide information for guiding the user to adjust the current voice request, and feeding back the target guide information to guide the user to complete voice interaction. Thus, the server can feed back the target guiding information, the user adjusts the current voice request based on the target guiding information, the target guiding information is made to be related to the current voice request, the reliability of the target guiding information is guaranteed, the target guiding information is determined through the large language model, the target guiding information is credible, and the user experience is improved. And updating of each training round of the large language model can be carried out according to prediction results of the previous training round and the current training round, so that the model training effect is guaranteed.

    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,所述方法包括:接收车辆转发的当前语音请求,在根据当前语音请求未能确定出对应的车辆控制指令的情况下,根据大语言模型和当前语音请求,确定用于引导用户对所述当前语音请求进行调整的目标引导信息,反馈目标引导信息以引导用户完成语音交互。如此,本申请的服务器可将目标引导信息反馈,用户基于目标引导信息进行当前语音请求的调整,及使目标引导信息与当前语音请求相关,目标引导信息的可靠性得到保障,及通过大语言模型确定目标引导信息,目标引导信息可信,及使得大语言模型每一训练轮次的更新可前一训练轮次和当前训练轮次的预测结果进行,模型训练效果得到保障。


    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:
    FAN JUNFENG (Autor:in) / NING HONGKE (Autor:in) / DING PENGJIE (Autor:in) / ZHU QIYU (Autor:in) / ZHAO QUN (Autor:in) / GUO YALIN (Autor:in)

    Erscheinungsdatum :

    04.06.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

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



    Voice interaction method, server and computer readable storage medium

    ZHANG LIAO / YU XIAOJIE | 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

    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

    HU JING | 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