Processing voice information with a terminal device and a cloud server to control an operation

Patent metadata

Field	Value
Publication number	US-11967320-B2
Application number	US-201917413150-A
Country	US
Kind code	B2
Filing date	Nov 26, 2019
Priority date	Dec 11, 2018
Publication date	Apr 23, 2024
Grant date	Apr 23, 2024

Abstract

A process of a voice control method with a cloud server and a terminal device. The voice control method includes: a terminal device receiving voice information; the terminal device querying a control instruction corresponding to the voice information from a local voice database; when the control instruction corresponding to the voice information is not queried in the local voice database, the terminal device uploading the voice information to a cloud server; the cloud server parsing the control instruction corresponding to the voice information; when the control instruction corresponding to the voice information is parsed, the cloud server sending the control instruction to the terminal device; and the terminal device receiving the control instruction, and performing a corresponding operation on the basis of control instruction.

First claim

What is claimed is:

1. A voice control method, comprising:
receiving voice information by a terminal device;
querying a control instruction corresponding to the voice information from a local voice library by the terminal device;
uploading the voice information to a cloud server by the terminal device when the control instruction corresponding to the voice information is not found by querying in the local voice library, wherein a cloud voice library is stored in the cloud server, and the cloud voice library stores mapping relationships between voice information and control instructions;
parsing the control instruction corresponding to the uploaded voice information by the cloud server;
finding, by the cloud server, whether there is a mapping relationship same as the mapping relationship between the uploaded voice information and the control instruction which is parsed out, by querying in the cloud voice library;
recording, by the cloud server, the mapping relationship between the uploaded voice information and the control instruction which is parsed out in the cloud voice library, when the cloud server does not find the same mapping relationship by querying in the cloud voice library;
sending the control instruction corresponding to the voice information to the terminal device by the cloud server, when the control instruction corresponding to the voice information is parsed out; and
receiving the control instruction by the terminal device, and performing a corresponding operation by the terminal device based on the control instruction,
wherein after parsing the control instruction corresponding to the uploaded voice information by the cloud server, the method further comprises:
determining, by the cloud server, the number of times the mapping relationship between the voice information and the control instruction has been recorded in the cloud voice library, when the control instruction corresponding to the voice information is parsed out;
comparing, by the cloud server, the number of times of recording with a preset number of times, if the number of times of recording is not equal to zero;
sending, by the cloud server, the mapping relationship to the terminal device if the number of times of recording is larger than the preset number of times; and
receiving the mapping relationship by the terminal device, and storing the mapping relationship in the local voice library by the terminal device.

2. A voice control method, comprising:
receiving, by a cloud server, voice information uploaded by a terminal device, wherein a cloud voice library is stored in the cloud server, and the cloud voice library stores mapping relationships between voice information and control instructions;
parsing a control instruction corresponding to the uploaded voice information by the cloud server;
finding, by the cloud server, whether there is a mapping relationship same as the mapping relationship between the uploaded voice information and the control instruction which is parsed out, by querying in the cloud voice library;
recording, by the cloud server, the mapping relationship between the uploaded voice information and the control instruction which is parsed out in the cloud voice library, when the cloud server does not find the same mapping relationship by querying in the cloud voice library;
sending the control instruction corresponding to the voice information to the terminal device by the cloud server when the control instruction corresponding to the voice information is parsed out, so that the terminal device performs a corresponding operation based on the control instruction;
after parsing the control instruction corresponding to the uploaded voice information by the cloud server, the method further comprises:
determining, by the cloud server, the number of times a mapping relationship between the voice information and the control instruction has been recorded in a cloud voice library, when the control instruction corresponding to the voice information is parsed out;
comparing, by the cloud server, the number of times of recording with a preset number of times, if the number of times of recording is not equal to zero; and
sending, by the cloud server, the mapping relationship to the terminal device if the number of times of recording is larger than the preset number of times, so that the terminal device stores the mapping relationship in a local voice library,
wherein the terminal device uploads the voice information when the control instruction corresponding to the voice information cannot be found by querying in the local voice library.

3. A voice control method, comprising:
receiving voice information by a terminal device;
querying a control instruction corresponding to the voice information from a local voice library by the terminal device;
uploading the voice information to a cloud server by the terminal device, when the control instruction corresponding to the voice information is not found by querying in the local voice library, so that the cloud server parses the control instruction corresponding to the voice information;
receiving the parsed-out control instruction corresponding to the voice information from the cloud server by the terminal device, and performing a corresponding operation by the terminal device based on the control instruction;
after the uploading of the voice information to the cloud server by the terminal device, the method further comprises:
receiving a mapping relationship between the voice information and the control instruction from the cloud server by the terminal device, and storing the mapping relationship in the local voice library by the terminal device;
wherein when the cloud server has parsed out the control instruction corresponding to the uploaded voice information, the cloud server is configured to
find whether there is a mapping relationship same as the mapping relationship between the uploaded voice information and the control instruction which is parsed out, by querying in a cloud voice library;
determine the number of times the mapping relationship between the voice information and the control instruction has been recorded in a cloud voice library;
compare the number of times of recording with a preset number of times, if the number of times of recording is not equal to zero; and
send the mapping relationship to the terminal device if the number of times of recording is larger than the preset number of times, so that the terminal device stores the mapping relationship in the local voice library.

Assignees

• Qingdao Haier Washing Mach Co
• Haier Smart Home Co Ltd

Inventors

• Huang Zhenxing
• Xu Sheng
• Yin Junming
• Shu Hai

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/1822

  Parsing for meaning understanding · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L15/26 Primary

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• H04L67/10 Primary

  in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title