The invention discloses a vehicle voice interaction method, and the method comprises the steps: generating target training data according to a pre-trained large language model, training a preset model according to the target training data, obtaining a voice interaction module, and deploying the voice interaction model to a vehicle, and enabling the vehicle to complete voice interaction according to the deployed voice interaction model and the obtained current voice request. Thus, in the application, the server can generate the target training data and the voice interaction model through the large language model, so that the vehicle can complete voice interaction with the user through the voice interaction model in combination with the current voice request, thus voice interaction in an offline state can be completed, and the use scene of the vehicle voice interaction function is widened. According to the method, target training is generated through the large language model, so that the condition that both sample generation and sample labeling need to be completed manually is improved, and the training difficulty and training cost of the voice interaction model are reduced to a certain extent.

    本申请公开一种车辆语音交互方法,所述方法包括:根据预先训练完成的大语言模型,生成目标训练数据,根据目标训练数据对预设模型进行训练,得到语音交互模块,部署语音交互模型至车辆,以使得车辆根据部署的语音交互模型和获取到的当前语音请求,完成语音交互。如此,在本申请中,服务器可通过大语言模型生成目标训练数据及语音交互模型,以使车辆可通过语音交互模型,结合当前语音请求以完成与用户的语音交互,从而能完成离线状态下的语音交互,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目标训练,使得样本生成和样本标注均需由人工完成的情况得以改善,语音交互模型的训练难度和训练成本在一定程度上得以降低。


    Access

    Download


    Export, share and cite



    Title :

    Vehicle voice interaction method, server and computer readable storage medium


    Additional title:

    车辆语音交互方法、服务器及计算机可读存储介质


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

    Publication date :

    2024-01-12


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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. | European Patent Office | 2024

    Free access

    Vehicle voice interaction method, server and computer readable storage medium

    FAN JUNFENG / ZHAO QUN / NING HONGKE et al. | European Patent Office | 2024

    Free access

    Voice interaction method, server and computer readable storage medium

    FAN JUNFENG / ZHAO QUN / JIAN TAOWEN et al. | European Patent Office | 2024

    Free access

    Voice interaction method, server and computer readable storage medium

    HU JING | 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 | 2022

    Free access