Summary of the invention
Present invention solves the technical problem that it is when main control terminal carries out Voice command to controlled terminal, how to reduce controlledThe complexity of terminal and cost.
For solving above-mentioned technical problem, the embodiment of the present invention provides a kind of sound control method, including: main control terminal is by languageSound data are transmitted to Cloud Server by the way of network transmits；Described speech data is identified with life by described Cloud ServerBecoming control instruction, described control instruction is used for controlling controlled terminal；Described Cloud Server is by the most described for the transmission of described control instructionControlled terminal is to control described controlled terminal.
Alternatively, described speech data is after the described main control terminal primary voice data to collecting carries out semantics recognitionObtain.
Alternatively, described main control terminal is configured with default conventional voice entry, and described main control terminal is to described originalWhen speech data carries out semantics recognition, according to described conventional voice entry, described primary voice data is carried out fuzzy matching.
Alternatively, described network transmission mode include following any one: Wi-Fi, 3G, 4G, Ethernet.
Alternatively, described Cloud Server is P2P server；Described Cloud Server in the way of P2P by described control instructionTransmission extremely described controlled terminal is to control described controlled terminal.
Alternatively, in described main control terminal, the speech data collected is transmitted to cloud service by the way of network transmitsBefore device, also including: described main control terminal obtains the address code of described controlled terminal, described address code is for described in unique identificationControlled terminal.
Alternatively, the address code of described controlled terminal include following any one: the MAC Address of controlled terminal, IP addressOr Quick Response Code.
Alternatively, the address code of the described controlled terminal of described main control terminal acquisition includes: by user in dialog boxOperation is selected to determine described controlled terminal；Based on the controlled terminal selected, search the address code that described controlled terminal is corresponding.
For solving above-mentioned technical problem, the embodiment of the present invention also provides for a kind of speech control system, including: main control terminal,The mode by speech data transmits via network that is suitable to is transmitted to Cloud Server；Described Cloud Server, is suitable to described voice numberAccording to being identified generating control instruction, described control instruction is used for controlling controlled terminal, and described Cloud Server is further adapted for instituteState control instruction transmission to described controlled terminal to control described controlled terminal.
Alternatively, described speech data is after the described main control terminal primary voice data to collecting carries out semantics recognitionObtain.
Alternatively, described main control terminal is configured with default conventional voice entry, and described main control terminal is to described originalWhen speech data carries out semantics recognition, according to described conventional voice entry, described primary voice data is carried out fuzzy matching.
Alternatively, described network transmission mode include following any one: Wi-Fi, 3G, 4G, Ethernet.
Alternatively, described Cloud Server is P2P server；Described Cloud Server is suitable to described control in the way of P2PInstruction transmission extremely described controlled terminal is to control described controlled terminal.
Alternatively, described main control terminal is further adapted for obtaining the address code of described controlled terminal, and described address code is for uniqueIdentify described controlled terminal.
Alternatively, the address code of described controlled terminal include following any one: the MAC Address of controlled terminal, IP addressOr Quick Response Code.
Alternatively, described main control terminal is mobile phone.
Alternatively, described controlled terminal is intelligent television.
Compared with prior art, the technical scheme of the embodiment of the present invention has the advantages that
Embodiment of the present invention sound control method may include that main control terminal by speech data by the way of network transmitsTransmission is to Cloud Server；Described Cloud Server is identified generating control instruction, described control instruction to described speech dataFor controlling controlled terminal；Described control instruction is transmitted to described controlled terminal to control described controlled end by described Cloud ServerEnd.The present invention program uses described Cloud Server to be identified described speech data, and the control instruction of generation is directly passedTransport to described controlled terminal so that when main control terminal carries out Voice command to controlled terminal, it is not necessary to controlled terminal is configured with PangBig speech recognition system, greatly reduces the software and hardware requirement to controlled terminal, reduces complexity and the cost of controlled terminal.
Furthermore, speech data is transmitted to Cloud Server by the way of network transmits by described main control terminal, itsIn, described network transmission mode can include following any one: Wi-Fi, 3G, 4G, Ethernet so that voice control of the present inventionMethod processed can realize the main control terminal long-range control to controlled terminal.
Furthermore, described Cloud Server is P2P server, described Cloud Server in the way of P2P by described controlInstruction transmission is to described controlled terminal to control described controlled terminal, and P2P server is originally in high efficiency and peace of network transmissionFull property is so that sound control method of the present invention has high efficiency and safety.
Furthermore, described speech data is that the described main control terminal primary voice data to collecting carries out semantic knowledgeDo not obtain afterwards, namely before described speech data is sent to described Cloud Server, it is carried out pre-by described main control terminalProcess, the processing pressure of Cloud Server can be reduced.
Furthermore, described main control terminal is configured with default conventional voice entry, and described main control terminal is to describedWhen primary voice data carries out semantics recognition, according to described conventional voice entry, described primary voice data is carried out fuzzyJoin, the experience of user can be improved.
Detailed description of the invention
As described in the background section, controlled terminal needs to support that controlled terminal is provided with the highest by speech recognition systemTechnical threshold, the sound control method of prior art is faced with the problem higher to the soft and hardware system requirements of controlled terminal, leadsCause the complexity of controlled terminal and relatively costly.
For techniques discussed above problem, the embodiment of the present invention proposes a kind of sound control method, described Voice commandMethod can include below scheme: speech data is transmitted to Cloud Server by the way of network transmits by main control terminal；DescribedCloud Server is identified generating control instruction to described speech data, and described control instruction is used for controlling controlled terminal；InstituteState Cloud Server by described control instruction transmission extremely described controlled terminal to control described controlled terminal.The present invention program uses instituteState Cloud Server described speech data is identified, and the control instruction of generation is directly transferred to described controlled terminal, makeMust be when main control terminal carries out Voice command to controlled terminal, it is not necessary to controlled terminal is configured with huge speech recognition system, greatlyReduce greatly the technology requirement to controlled terminal.
Understandable for enabling the above-mentioned purpose of the present invention, feature and beneficial effect to become apparent from, below in conjunction with the accompanying drawings to thisThe specific embodiment of invention is described in detail.
Fig. 1 is the flow chart of a kind of sound control method of the embodiment of the present invention.
As it is shown in figure 1, embodiment of the present invention sound control method may comprise steps of:
Step S101, speech data is transmitted to Cloud Server by the way of network transmits by main control terminal.
Step S102, described Cloud Server is identified generating control instruction to described speech data, and described control refers toOrder is used for controlling controlled terminal.
Step S103, described control instruction is transmitted to described controlled terminal to control described controlled end by described Cloud ServerEnd.
In being embodied as, the present embodiment sound control method can perform described step S101 successively to step S103.In described step S101, it can be described that speech data is transmitted to Cloud Server by the way of network transmits by main control terminalDescribed speech data is directly transferred to described Cloud Server, described network transmission side by the way of network transmits by main control terminalFormula can include following any one: such as Wi-Fi, G mobile communication (3G), forth generation mobile communication technology(4G), Ethernet etc..
The control instruction that described in described step S102, Cloud Server is generated, can be identified by described controlled terminal,Described control instruction can be binary code, it is also possible to for other forms such as hexadecimal code, in actual applications, and canBeing adjusted in described Cloud Server with the particular type according to described controlled terminal and model, it is special that the present embodiment is not carried outLimit.
Furthermore, the sound control method of prior art typically uses in-plant wireless transmission method (such as blueTooth, ZIGBEE etc.) carry out voice transfer, controlled terminal carries out speech recognition, due to the restriction of communication protocol so that master controlWithin the physical distance of terminal and controlled terminal is limited in tens meters, distance may cause voice-operated failure when becoming.
By contrast, speech data is transmitted to cloud by the way of network transmits by the described main control terminal in the present embodimentServer so that sound control method of the present invention is not only restricted to the physical distance between main control terminal and controlled terminal, Ke YishiThe long-range control to controlled terminal of the existing main control terminal.Preferably, described Cloud Server can be associate with main control terminal presetCloud Server, such as can be pre-configured with the reference address of Cloud Server in main control terminal, when main control terminal starts voiceDuring control, speech data is directly transmitted by the way of network transmits the reference address to this Cloud Server, and without carrying outAddress lookup.
In being embodied as, described main control terminal 10 can be mobile phone；Described controlled terminal 30 can be intelligent television.NeedIt is noted that described main control terminal 10 can also be for intelligent remote controller or panel computer；Described controlled terminal 30 is all rightFor the intelligence terminal such as box or intelligent air condition, the embodiment of the present invention does not carry out special limit to main control terminal 10 and controlled terminal 30Fixed.
In being embodied as, described speech data can be that the described main control terminal primary voice data to collecting is carried outObtain after semantics recognition.Such as, described main control terminal is mobile phone, and user is by the raw tone of mobile phone typing " central authorities are a set of "Data, described primary voice data is carried out semantics recognition, namely described primary voice data is carried out pretreatment by described mobile phone,Being identified as word " central authorities are a set of ", described main control terminal is again by described word " central authorities are a set of " transmission extremely described Cloud Server, cloudServer has only to be converted into the speech data after semantics recognition the control instruction of correspondence, such as will " central authorities oneSet " word to be converted into channel switch be the control instruction of corresponding channel, such that it is able to reduce the processing pressure of Cloud Server.
In being embodied as, user uses Voice command in noisy environment for convenience, and described main control terminal also may be usedTo be configured with default conventional voice entry, such as: " start ", " shutdown " etc..Described main control terminal is to described raw toneWhen data carry out semantics recognition, according to described conventional voice entry, described primary voice data can be carried out fuzzy matching, withImprove the discrimination to conventional voice entry.Such as when not configuring described conventional voice entry, the raw tone of user's typingData at least need the matching degree of the speech data with standard to reach 90% the highest, and are configured with described conventional voice entryAfter, if user's typing is primary voice data reach the matching degree of the speech data more than 60% with standard i.e. can be describedMain control terminal is identified.This can help user to rapidly input, and is also avoided that noisy environment causes speech recognition failure, permissibleImprove the experience of user.
Fig. 2 is the flow chart of embodiment of the present invention another kind sound control method.
As in figure 2 it is shown, in being embodied as, described Cloud Server can be P2P server.The voice of the embodiment of the present inventionControl method can include that step S201 is to step S203.
Wherein, described step S201, speech data is transmitted by the way of network transmits to described P2P and takes by main control terminalBusiness device.
Described step S202, described P2P server is identified generating control instruction, described control to described speech dataInstruction processed is used for controlling controlled terminal.
Described step S203, described control instruction is transmitted to described controlled terminal in the way of P2P by described P2P serverTo control described controlled terminal.
Described step S201 to the relevant information of step S203 refer to above to described step S101 to step S103Associated description, here is omitted.
Specifically, P2P server is a kind of peer-to-peer network server, therefore, described Cloud Server can also include toA few P2P network node, described P2P server can transmit to institute via control instruction described in described P2P network nodeState controlled terminal.Due to P2P server, this has high efficiency and a safety in network transmits, therefore the embodiment of the present inventionSound control method has the high efficiency of transmission and the feature of safety.
In being embodied as, before described step S201, embodiment of the present invention sound control method can also include stepRapid S204, described main control terminal obtains the address code of described controlled terminal, and described address code identifies described controlled end for uniqueEnd.
Wherein, the address code of described controlled terminal can include following any one: the media interviews of described controlled terminalControl (Media Access Control, MAC) address, Internet protocol (Internet Protocol, IP) address or two dimensionCode.Specifically, described controlled terminal address code can be obtained by user's registration.
In being embodied as, user according to the MAC Address of described controlled terminal, or can have the IP address of uniquenessRegistration, thus obtain unique address code of a controlled terminal, it is also possible to obtained by the Quick Response Code of APP in scanning controlled terminalThe address code of described controlled terminal.
Fig. 3 is the flow chart of another sound control method of the embodiment of the present invention.
Shown in Fig. 2 and Fig. 3, described step S204 can include step S2041 and step S2042.
Described step S2041, determines described controlled terminal by user's selection operation in dialog box.
Described step S2042, based on the controlled terminal selected, searches the address code that described controlled terminal is corresponding.
In being embodied as, user can pass through to select terminal in the dialog box ejected in described main control terminal, according toHint image shown in APP interface, carries out phonetic order collection.After collection completes, utilize mobile phone terminal speech identifying function, languageSound instruction is processed as intelligent terminal's discernible instruction stream.Wherein, described dialog box can be the terminal name list of controlled terminal,Such as " television set 1 ", " television set 2 ", " air-conditioning 1 ", " air-conditioning 2 " etc., it is also possible to be address code list, such as " 0x1126 "," 0x1369 " etc..
The sound control method of the embodiment of the present invention can also carry out Voice command to the controlled terminal of different home, namelyA main control terminal can be used to control the controlled terminal of multiple families.Specifically, in the dialog box in described main control terminalCan there is multilevel menu, multilevel menu can be followed successively by family's name, the big class of controlled terminal according to order from top to bottomWith address code or the terminal name of controlled terminal, such as, top menu includes " family " and " company "；" family " and the submenu of " company "Include " TV ", " air-conditioning " and " air purifier " respectively；In the light of actual conditions, the submenu of " TV " can include respectively" TV 1 ", " TV 2 " ..., the submenu of " air-conditioning " can include " air-conditioning 1 ", " air-conditioning 2 " ..., " air cleaning respectivelyDevice " submenu can include " air purifier 1 ", " air purifier 2 " ... (only as a example by terminal name) respectively.
It should be noted that described main control terminal and controlled terminal can be configured with APP, described main control terminal can be passed throughAPP is through described voice data transmission to described Cloud Server, and described controlled terminal can receive described Cloud Server by APP and send outThe control instruction sent.Certainly, described main control terminal and controlled terminal can also be not configured with APP, but in the present embodiment, describedMain control terminal can be connected with described Cloud Server network, and can gather speech data, and meanwhile, described controlled terminal is permissibleIt is connected with described Cloud Server network to receive described control instruction.
Fig. 4 is the schematic block diagram of a kind of speech control system of the embodiment of the present invention.
As shown in Figure 4, the embodiment of the present invention is also disclosed a kind of speech control system 100, and described speech control system 100 canTo include main control terminal 10, Cloud Server 20 and controlled terminal 30.
Wherein, described main control terminal 10 is suitable to transmit to Cloud Server 20 speech data via the mode that network transmits.
Described Cloud Server 20 is suitable to be identified generating control instruction to described speech data, and described control instruction is usedIn controlling controlled terminal 30, described Cloud Server 20 is further adapted for described control instruction transmission to described controlled terminal 30 to controlDescribed controlled terminal 30.
In being embodied as, described main control terminal 10 can but be not limited to mobile phone.Described controlled terminal 30 can but notIt is defined to intelligent television.Such as, described main control terminal 10 can also be intelligent remote controller or panel computer；Described controlled terminal30 can also be the intelligence terminal unit such as box or intelligent air condition, and the embodiment of the present invention is to main control terminal 10 and controlled terminal 30Do not carry out particular determination.
In being embodied as, described speech data can be that the described main control terminal primary voice data to collecting is carried outObtain after semantics recognition.
In being embodied as, described main control terminal can be configured with default conventional voice entry, and described main control terminal existsWhen described primary voice data is carried out semantics recognition, according to described conventional voice entry, described primary voice data is carried out mouldStick with paste coupling.
In being embodied as, described network transmission mode can include following any one: Wi-Fi, 3G, 4G, etherNet.
In being embodied as, described Cloud Server can be P2P server；Described Cloud Server is suitable in the way of P2PBy the transmission of described control instruction to described controlled terminal to control described controlled terminal.
In being embodied as, described main control terminal can be adapted to obtain the address code of described controlled terminal, described addressCode identifies described controlled terminal for unique.
Wherein, the address code of described controlled terminal can include following any one: the MAC Address of controlled terminal, IP groundLocation or Quick Response Code.
The more information of described speech control system 100 refer to the phase in above example to described sound control methodClosing and describe, here is omitted.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is canCompleting instructing relevant hardware by program, this program can be stored in computer-readable recording medium, and storage is situated betweenMatter may include that ROM, RAM, disk or CD etc..
Although present disclosure is as above, but the present invention is not limited to this.Any those skilled in the art, without departing from thisIn the spirit and scope of invention, all can make various changes or modifications, therefore protection scope of the present invention should be with claim instituteLimit in the range of standard.