Generation of domain-specific models in networked system

The present disclosure is generally directed to the generation of domain-specific, voice-activated systems in interconnected networks. The system can receive input signals that are detected at a client device. The input signals can be voice-based input signals, text-based input signals, image-based input signals, or other type of input signals. Based on the input signals, the system can select domain-specific knowledge graphs and generate responses based on the selected knowledge graph. 本公开通常涉及互连网络中特定于域的、语音激活的系统的生成。系统可以接收在客户端设备上检测到的输入信号。输入信号可以是基于语音的输入信号、基于文本的输入信号、基于图像的输入信号或其他类型的输入信号。基于输入信号，系统可以选择特定于域的知识图并基于所选择的知识图来生成响应。