MULTI-COMMAND SINGLE UTTERANCE INPUT METHOD

摘要

Systems and processes are disclosed for handling a multi-part voice command for a virtual assistant. Speech input can be received from a user that includes multiple actionable commands within a single utterance. A text string can be generated from the speech input using a speech transcription process. The text string can be parsed into multiple candidate substrings based on domain keywords, imperative verbs, predetermined substring lengths, or the like. For each candidate substring, a probability can be determined indicating whether the candidate substring corresponds to an actionable command. Such probabilities can be determined based on semantic coherence, similarity to user request templates, querying services to determine manageability, or the like. If the probabilities exceed a threshold, the user intent of each substring can be determined, processes associated with the user intents can be executed, and an acknowledgment can be provided to the user.

主权项

1. A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:
receive speech input from a user, wherein the speech input comprises a single utterance having one or more actionable commands; generate a text string based on the speech input using a speech transcription process; parse the text string into at least a first candidate substring and a second candidate substring; determine a first probability that the first candidate substring corresponds to a first actionable command and a second probability that the second candidate substring corresponds to a second actionable command; in response to the first probability and the second probability exceeding a threshold, determine a first intent associated with the first candidate substring and a second intent associated with the second candidate substring; execute a first process associated with the first intent and a second process associated with the second intent; and provide to the user an acknowledgment associated with the first intent and the second intent.