The invention discloses a voice interaction method, and the method comprises the steps: obtaining target word information, inferring a large language model of corresponding category information through pre-training according to the word information, determining the target category information of the target word information, and determining a voice interaction model according to the target word information and the target category information, and completing voice interaction according to the voice interaction model. Thus, the server can infer the category of the target word information according to the large language model to determine the target category information of the target word information, so that understanding and classification of the target word information can be executed by the large language model, and the classification efficiency of the target word information is guaranteed. According to the invention, the voice interaction model can be trained according to the target word information and the target category information of the target word information, so that the voice interaction model can learn the semantics or category of the target word information, and the credibility of the voice interaction model is guaranteed.

    本申请公开一种的语音交互方法,所述方法包括:获取目标字词信息,通过预先训练完成,且能根据字词信息推理出对应的类别信息的大语言模型,确定目标字词信息的目标类别信息,根据目标字词信息和目标类别信息,确定语音交互模型,进而根据语音交互模型完成语音交互。如此,本申请的服务器可根据大语言模型,推理目标字词信息的类别以确定目标字词信息的目标类别信息,使得目标字词信息的理解和分类均可由大语言模型执行,目标字词信息的分类效率得以保障。本申请可根据目标字词信息及目标字词信息的目标类别信息,训练语音交互模型,以使得语音交互模型能学习到目标字词信息的语义或类别,语音交互模型的可信度得到保障。


    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:
    NIU HAIBO (author)

    Publication date :

    2024-03-05


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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 | European Patent Office | 2024

    Free access

    Voice interaction method, server and computer readable storage medium

    FAN JUNFENG / NING HONGKE / DING PENGJIE et al. | European Patent Office | 2024

    Free access

    Voice interaction method, server and computer readable storage medium

    FAN JUNFENG / NING HONGKE / ZHAO QUN | European Patent Office | 2022

    Free access

    Voice interaction method, server and computer readable storage medium

    FU JUNQIANG | European Patent Office | 2024

    Free access

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

    ZHANG XIKANG / ZHAO YAO / WANG TIANYI | European Patent Office | 2024

    Free access