US Patent No. 9,236,048

METHOD AND DEVICE FOR VOICE CONTROLLING


Patent No. 9,236,048
Issue Date January 12, 2016 
Title Method And Device For Voice Controlling
Inventorship Manhai Li, Shenzhen (CN)
Kaili Xiao, Shenzhen (CN)
Jingping Wang, Shenzhen (CN)
Xin Liao, Shenzhen (CN)
Assignee ZTE Corporation, Shenzhen, Guangdong Province (CN)

Claim of US Patent No. 9,236,048

1. A method for voice control, comprising the following steps:
classifying stored recognition information used for voice recognition to obtain a plurality of syntax packets, wherein each
syntax packet corresponds to one type of recognition information;

receiving an inputted voice signal, and performing a voice recognition processing repeatedly on the received voice signal
by using each of the plurality of syntax packets in turn to obtain a plurality of voice data portions, each of which is recognized
from the corresponding syntax packet, of the voice signal as a plurality of voice recognition results, wherein the plurality
of voice recognition results include some voice data portions recognized successfully and/or voice recognition failure;

wherein, the step of performing a voice recognition processing repeatedly on the received voice signal by using each of the
plurality of syntax packets comprises:

when at least one piece of recognition information in one of the syntax packets can be recognized from the received voice
signal, selecting an identifier corresponding to the recognized piece of the recognition information from pre-designated identifiers
corresponding to various pieces of the recognition information in the syntax packet as the voice recognition result of the
syntax packet on the voice signal;

otherwise, determining that voice recognition fails this time, and selecting an identifier corresponding to a reason for voice
recognition processing failure of this time from pre-designated identifiers corresponding to various reasons for voice recognition
processing failure as the voice recognition result of the syntax packet on the voice signal; and

performing a corresponding control processing based on a combination of the plurality of voice recognition results as follows:
combining the voice recognition results of various syntax packets on the voice signal in a predetermined combining order,
and sending a combination result to an external equipment;

receiving a query request sent from the external equipment, wherein the query request contains a splitting result obtained
after the external equipment splits the combination result in a splitting order corresponding to the predetermined combining
order;

selecting recognition information corresponding to the splitting result contained in the query request from a pre-designated
corresponding relationship between the recognition information and the identifiers; and

providing the recognition information corresponding to the splitting result to the external equipment, so that the external
equipment performs the control processing according to the recognition information corresponding to the splitting result.