US Patent 10991371 Voice function control method and apparatus

A first recognition result of an input voice is generated, where the input voice is input by a user of a terminal, and the first recognition result is generated by a voice assistant of the terminal. An application of the terminal is determined based on the first recognition result, where the application provides a service, and the application is different from the voice assistant. The input voice is passed to the application, where the application performs voice recognition on the input voice to generate a second recognition result. The service is provided to the user based on the second recognition result.