Conversation processing method and device

One or more embodiments of the invention provide a dialogue processing method and device, and the method comprises the steps: carrying out the intention recognition of user input information, and determining a first task scene of a current dialogue, and calling a target function module corresponding to the first task scene from a pre-established function set based on the user intention to create a first dialogue task, executing the first dialogue task, and generating and displaying an output result. In the embodiment of the invention, the function modules required by different task scenes are packaged in advance based on the atomic power of the bottom layer of the system, and in the dialogue recognition process, the corresponding task construction is completed by recognizing the user intention, autonomously learning and calling the required function modules, so that various scene requirements of the user are met. 本说明书一个或多个实施方式提供一种对话处理方法及装置，对话处理方法包括对用户输入信息进行意图识别确定当前对话的第一任务场景，基于用户意图从预先建立的功能集中调用与第一任务场景对应的目标功能模块创