The invention discloses a vehicle voice interaction method, and the method comprises the steps: updating original training data generated by a second large language model according to a first large language model, and obtaining target training data. And training a preset model according to the target training data to obtain a voice interaction model. And deploying the voice interaction model to the vehicle, so that the vehicle can complete voice interaction according to the voice interaction model and the obtained current voice request. Therefore, according to the method and the device, the original training data can be updated through the second large language model, the noise data in the original training data is eliminated, and the reliability of the voice interaction model is guaranteed. The vehicle can complete voice interaction in an offline state according to the deployed voice interaction model, and the use scene of the vehicle voice interaction function is widened. The training data are generated through the large language model, the situation that the training data are obtained manually is improved to a certain degree, the training data obtaining difficulty is lowered, and the training difficulty of the voice interaction model is lowered.

    本申请公开一种车辆语音交互方法,所述方法包括:根据第一大语言模型,更新第二大语言模型生成的原始训练数据,得到目标训练数据。根据目标训练数据训练预设模型得到语音交互模型。部署语音交互模型至车辆,使得车辆能根据语音交互模型,及获取到的当前语音请求完成语音交互。如此,在本申请中,可通过第二大语言模型更新原始训练数据,消除原始训练数据中的噪声数据,语音交互模型的可靠性得以保障。车辆可根据部署的语音交互模型,在离线状态下完成语音交互,车辆语音交互功能的使用场景拓宽。本申请通过大语言模型生成训练数据,在一定程度上改善训练数据由人工得到的情况出现,训练数据的获取难度降低,语音交互模型的训练难度降低。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Vehicle voice interaction method, server and computer readable storage medium


    Weitere Titelangaben:

    车辆语音交互方法、服务器及计算机可读存储介质


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

    Erscheinungsdatum :

    2024-01-19


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G10L Analyse oder Synthese von Sprache , SPEECH ANALYSIS OR SYNTHESIS / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G01C Messen von Entfernungen, Höhen, Neigungen oder Richtungen , MEASURING DISTANCES, LEVELS OR BEARINGS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung



    Vehicle voice interaction method, server and computer readable storage medium

    FAN JUNFENG / ZHAO QUN / NING HONGKE et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Vehicle voice interaction method, server and computer readable storage medium

    FAN JUNFENG / ZHAO QUN / NING HONGKE et al. | Europäisches Patentamt | 2024

    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