Method, device and system for executing task corresponding to natural language command

Abstract

The objective of the invention lies in providing a method, device and system for executing a task corresponding to a natural language command. Specifically, the method comprises the steps: obtaining the natural language command inputted by a user currently; carrying out the analysis of the natural language command, so as to obtain the task corresponding to the natural language command; dividing the task into at least two subtasks which have the execution sequential relation; and transmitting each of the subtasks to the device for executing the corresponding subtask, so as to enable the task to be executed. Compared with the prior art, the method achieves a purpose that the user can operate a plurality of intelligent devices to cooperate to meet the demands, expressed by the natural language demand, of the user through the natural language demand, and there is no need of interaction with each intelligent device, so the operation is convenient. The method reduces the interaction time of the user, improves the interaction efficiency, and also improves the interaction experience of the intelligent devices of the user.

Description

technical field [0001] The present invention relates to the technical field of voice interaction, in particular to a technology for performing tasks corresponding to natural language commands. Background technique [0002] With the popularization of computer technology, people's life today has gradually entered the era of intelligence. Not only computers, mobile phones, PADs, but all aspects of people's clothing, food, housing and transportation have also begun to incorporate smart technologies, such as smart TVs, smart cars, smart homes, etc.; at the same time, the application of smart voice interaction technology to smart devices also greatly facilitates smart devices. usage of. [0003] However, the existing voice-based interaction between users and smart devices is usually limited to the fact that the user can only interact with one smart device at the same time through natural language, even if the user can operate multiple smart devices (for example, the user has more...

AI Technical Summary

Problems solved by technology

[0003] However, the existing voice-based interaction between users and smart devices is usually limited to the fact that the user can only interact with one smart device at the same time through natural language, even if the user can operate multiple smart devices (for example, the user has more than one smart device), especially when When multiple smart devices need to cooperate to fulfill the user's needs, they can only interact with each smart device separately

For example, if a user owns smart glasses and a smartphone at the same time, when the user wants the smart glasses to take photos or videos and set them as the background of the smartphone or share such photos or videos through social applications on the smartphone, the user needs to separately Smart glasses and smartphones cannot be operated through a simple voice command such as "take a photo and set it as the background of the phone" to complete the entire process, which not only increases user interaction time and reduces interaction efficiency, but also seriously affects User experience with smart devices

Images