Accompanying type intelligent dialogue method and electronic equipment

The embodiment of the invention discloses an accompanying type intelligent dialogue method and electronic equipment. The method comprises the following steps: receiving user dialogue information; in the process or after the process of processing the user dialogue information by using a large language model to generate a response text, performing fragmentation processing on the response text according to a preset fragmentation strategy to obtain response text fragments; and carrying out speech synthesis based on the response text fragment and carrying out mouth shape driving processing on a base video containing a character image so as to output the generated fragment response content. Through the embodiment of the invention, the reply delay can be reduced, and the user experience is improved. 本申请实施例公开了陪伴式智能对话方法及电子设备，所述方法包括：接收用户对话信息；在利用大语言模型对所述用户对话信息进行处理以生成响应文本的过程中或者之后，按照预置的分片策略对所述响应文本进行分片处理，得到响应文本片段；基于所述响应文本片段进行语音合成以及对包含人物形象的基底视频进行口型驱动处理，以便对生成的分片响应内容进行输出。通过本申请实施例，能够降低回复延迟，提升用户体验。