CN107145329A - Apparatus control method, device and smart machine - Google Patents

Apparatus control method, device and smart machine Download PDF

Info

Publication number
CN107145329A
CN107145329A CN201710229949.2A CN201710229949A CN107145329A CN 107145329 A CN107145329 A CN 107145329A CN 201710229949 A CN201710229949 A CN 201710229949A CN 107145329 A CN107145329 A CN 107145329A
Authority
CN
China
Prior art keywords
user speech
speech information
smart machine
interactive instruction
audio section
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710229949.2A
Other languages
Chinese (zh)
Inventor
李福祥
陈君宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Orion Star Technology Co Ltd
Original Assignee
Beijing Orion Star Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Orion Star Technology Co Ltd filed Critical Beijing Orion Star Technology Co Ltd
Priority to CN201710229949.2A priority Critical patent/CN107145329A/en
Publication of CN107145329A publication Critical patent/CN107145329A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16Sound input; Sound output
    • G06F3/167Audio in a user interface, e.g. using voice commands for navigating, audio feedback
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/334Query execution
    • G06F16/3343Query execution using phonetics
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16Sound input; Sound output
    • G06F3/165Management of the audio stream, e.g. setting of volume, audio stream path

Abstract

The embodiments of the invention provide a kind of apparatus control method, device and smart machine.This method is applied to smart machine, and methods described includes:Respond after the corresponding interactive instruction of the first user speech information, it is continuously in working condition, and judge whether very first time interval is less than or equal to target time interval threshold value, if yes, detect when receiving user speech information again, target interactive instruction is responded, wherein, the target interactive instruction is:The corresponding interactive instruction of user speech information received again;If it has not, switching to holding state by working condition.Equipment control is carried out by scheme provided in an embodiment of the present invention, from can realizing at the time of the corresponding interactive instruction of the first user speech information has been responded, in target time interval threshold value, smart machine is continuously in working condition, user need not wake up smart machine again and just can again be interacted with smart machine, process is simple, and Consumer's Experience is more preferable.

Description

Apparatus control method, device and smart machine
Technical field
The present invention relates to equipment control technology field, more particularly to a kind of apparatus control method, a kind of equipment control dress Put and a kind of smart machine.
Background technology
With the fast development of science and technology, smart machine is gradually applied to all trades and professions.In the prior art, user is each , it is necessary to wake up smart machine by the default wake-up word of smart machine before being interacted with smart machine, that is to say, that Yong Huxu Smart machine is switched to by working condition from holding state by the default word that wakes up, then smart machine could be responded and received again The corresponding interactive instruction of user speech information arrived, and enter holding state after above-mentioned interactive instruction has been responded, if user needs To be interacted again with smart machine, said process need to be repeated, smart machine is waken up again through default wake-up word.
For example, smart machine is named as " Xiao Ming ", then above-mentioned default wake-up word can be " Xiao Ming ", then user opens Smart machine, and smart machine be in holding state when, user wants to interact with smart machine, and process is as follows:
User says " Xiao Ming ";
Smart machine is collected into the voice messaging that user sends, and identifies comprising word " Xiao Ming " is waken up, is cut from holding state Shift to working condition;
User sends voice messaging again, and the recognition result of smart machine is:" today, how is weather”;
Smart machine is collected into after the voice messaging that user sends again, responds the voice messaging being collected into again corresponding Interactive instruction, such as:The Weather information of today is searched for, and the Weather information searched is played to user;
After response is completed, holding state is switched to by working condition.
At this moment, if user needs to continue to interact with smart machine, need to repeat said process, i.e., called out again by wake-up word Wake up smart machine, and then complete again to interact with smart machine.
It can be seen that, user is realized with smart machine when interacting using aforesaid way, user need to hand over smart machine every time Smart machine is first waken up before mutually, process is cumbersome, poor user experience.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of apparatus control method, device and smart machine, to simplify user With the interaction of smart machine, Consumer's Experience is improved.Concrete technical scheme is as follows:
In a first aspect, the embodiments of the invention provide a kind of apparatus control method, applied to smart machine, methods described bag Include:
Respond after the corresponding interactive instruction of the first user speech information, be continuously in working condition, and when judging first Between be spaced whether be less than or equal to target time interval threshold value, wherein, the first user speech information is:From holding state switching The last user speech information receive, not comprising standby audio section after to working condition, the standby audio section is: Voice identification result include preset standby word audio section, the very first time at intervals of:Believe from the first user speech has been responded The time interval of user speech information is not received from the time of ceasing corresponding interactive instruction;
If it is, detecting when receiving user speech information again, target interactive instruction is responded, wherein, the target Interactive instruction is:The corresponding interactive instruction of user speech information received again;
If it has not, switching to holding state by working condition.
Optionally, it is described to detect when receiving user speech information again, the step of response target interactive instruction, bag Include:
Detect when receiving user speech information again, judge whether included in the user speech information received again The standby audio section;
If comprising switching to holding state by working condition.
Optionally, methods described also includes:
When the smart machine is in holding state, whether judge in the user speech information received comprising wake-up audio Section, wherein, the wake-up audio section is:The default audio section for waking up word is included in voice identification result;
If comprising, working condition is switched to by holding state, and determination includes the user speech letter of the wake-up audio section The intended recipient direction of breath;
The first user speech information is:Switched to from holding state the last receiving, next after working condition User speech information from the intended recipient direction, not comprising standby audio section;
The user speech information that receives again is:User receiving again, from the intended recipient direction Voice messaging.
Optionally, the step of response target interactive instruction, including:
Speech recognition is carried out to the user speech information received again, recognition result is obtained;
The interaction scenarios for the user speech information for determining to receive again according to the recognition result;
Target interactive instruction is responded according to the interaction scenarios.
Optionally, the step of response target interactive instruction according to the interaction scenarios, including:
Whether judge the interaction scenarios is that audio plays scene;
If it is, playing the corresponding audio of target interactive instruction, and holding state is switched to by working condition.
Optionally, methods described also includes:
At least one of following information is obtained, and the target time interval threshold value is determined according to the information obtained Value:
The word speed of user;
The communicative habits of user;
Ambient noise parameter.
Second aspect, the embodiment of the present invention additionally provides a kind of plant control unit, applied to smart machine, described device Including:
First judge module, respond module, the first handover module;
Wherein,
First judge module, for having responded after the corresponding interactive instruction of the first user speech information, is continuously in Working condition, and judge whether very first time interval is less than or equal to target time interval threshold value, wherein, first user speech Information is:The last user speech receive, not comprising standby audio section after working condition is switched to from holding state Information, the standby audio section is:The audio section for presetting standby word, the very first time interval are included in voice identification result For:Do not received at the time of the corresponding interactive instruction of the first user speech information has been responded between the time of user speech information Every;
The respond module, if the judged result for first judge module is yes, detects and receives use again During the voice messaging of family, target interactive instruction is responded, wherein, the target interactive instruction is:The user speech letter received again Cease corresponding interactive instruction;
First handover module, if the judged result for first judge module is no, is switched by working condition To holding state.
Optionally, the respond module, including:
Judging submodule, when receiving user speech information again for detecting, judges the user's language received again Whether the standby audio section is included in message breath;
Switching submodule, if the judged result for the judging submodule is comprising standby audio section, by work shape State switches to holding state.
Optionally, described device also includes:
Second judge module, when being in holding state for the smart machine, judges the user speech information received In whether comprising wake up audio section, wherein, it is described wake-up audio section be:The default audio for waking up word is included in voice identification result Section;
Second handover module, if the judged result for second judge module is comprising audio section is waken up, by standby State switches to working condition, and determines the intended recipient direction of the user speech information comprising the wake-up audio section;
The first user speech information is:Switched to from holding state the last receiving, next after working condition User speech information from the intended recipient direction, not comprising standby audio section;
The user speech information that receives again is:User receiving again, from the intended recipient direction Voice messaging.
Optionally, the respond module, including:
Speech recognition submodule, for carrying out speech recognition to the user speech information received again, obtains identification knot Really;
Interaction scenarios submodule is determined, for the user speech information for determining to receive again according to the recognition result Interaction scenarios;
Submodule is responded, for responding target interactive instruction according to the interaction scenarios.
Optionally, it is described response submodule specifically for:
Whether judge the interaction scenarios is that audio plays scene;
If it is, playing the corresponding audio of target interactive instruction, and holding state is switched to by working condition.
Optionally, described device also includes:
Target time interval threshold module is adjusted, for obtaining at least one of following information, and according to being obtained Information determines the value of the target time interval threshold value:
The word speed of user;
The communicative habits of user;
Ambient noise parameter.
The third aspect, the embodiment of the present invention additionally provides a kind of smart machine, and the smart machine includes:Housing, processing Device, memory, circuit board and power circuit, wherein, circuit board is placed in the interior volume that housing is surrounded, processor and memory Set on circuit boards;Power circuit, for being powered for each circuit or device of electronic equipment;Memory is used to store and can hold Line program code;The executable program code that processor is stored by reading in memory is run and executable program code pair The program answered, the apparatus control method described in any one of 1-6 is required for perform claim.
Compared with prior art, scheme provided in an embodiment of the present invention is responding the corresponding friendship of the first user speech information Mutually after instruction, smart machine is continuously in working condition, when the very first time, interval was less than or equal to target time interval threshold value, Receive again after user speech information, respond the corresponding interactive instruction of user speech information received again, so as to Realizing at the time of the corresponding interactive instruction of the first user speech information has been responded, in target time interval threshold value, user Smart machine need not be waken up again just can again be interacted with smart machine, and process is easy, better user experience.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with Other accompanying drawings are obtained according to these accompanying drawings.
A kind of flow chart for apparatus control method that Fig. 1 is provided by the embodiment of the present invention;
A kind of another flow chart for apparatus control method that Fig. 2 is provided by the embodiment of the present invention;
A kind of structural representation for plant control unit that Fig. 3 is provided by the embodiment of the present invention;
A kind of another structural representation for plant control unit that Fig. 4 is provided by the embodiment of the present invention;
A kind of structural representation for smart machine that Fig. 5 is provided by the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made Embodiment, belongs to the scope of protection of the invention.
In order to solve prior art problem, the embodiments of the invention provide a kind of smart machine control method, device and electricity Sub- equipment, to simplify the interaction of user and smart machine, improves Consumer's Experience.
First the concept being related in the embodiment of the present invention is introduced below.
It is default to wake up word:Refer to that the word of smart machine can be waken up.For example, it is " Xiao Ming " to wake up word, smart machine exists Receive after user speech information, obtain voice identification result, when including " Xiao Ming " in voice identification result, smart machine quilt Wake up, that is to say, that smart machine switches to working condition by holding state.
Preset standby word:Refer to the word that smart machine can be made to switch to holding state by working condition.For example, standby Word is " end ", and smart machine obtains voice identification result after user speech information is received, when bag in voice identification result During containing " end ", smart machine switches to holding state by working condition.
Wake up audio section:Refer in voice identification result comprising the audio section for waking up word.
Standby audio section:Refer to the audio section for including standby word in voice identification result.
Holding state:Refer to the state for meeting situations below:After user opens smart machine, user speech letter is received Breath, but in order to reduce power consumption, the corresponding interactive instruction of user speech information of response bag audio section containing wake-up, and be not responding to connect The other users voice messaging received.
Working condition:After referring to that smart machine is waken up comprising the user speech information for waking up audio section, it can respond The state of the corresponding interactive instruction of user speech information.
After the concept being related in the embodiment of the present invention is introduced, the embodiment of the present invention will be provided below A kind of apparatus control method is introduced.
It should be noted that a kind of apparatus control method that the embodiment of the present invention is provided is applied in smart machine, should Smart machine can be:Smart mobile phone, smart home product are (such as:Intelligent sound box), intelligent vehicle-carried equipment, Intelligent worn device, Robot etc., this is all rational;, can also and the smart machine can be worked by the way of being connected with server communication Work independently, the application is defined not to this.
In addition, in a kind of application scenarios, the above-mentioned smart machine as executive agent is with microphone or microphone The equipment of array.
As shown in figure 1, a kind of apparatus control method that the embodiment of the present invention is provided, comprises the following steps:
S101, has been responded after the corresponding interactive instruction of the first user speech information, is continuously in working condition, and judge Whether one time interval is less than or equal to target time interval threshold value, if it is, S102 is performed, if it is not, then performing S103;
When smart machine is in holding state, if receiving comprising the user speech information for waking up audio section, understand from standby State switches to working condition, when the user speech information received is the first user speech information, responds first user's language Message ceases corresponding interactive instruction, and after the first user speech information has been responded, unlike the prior art, smart machine will not Holding state is immediately entered, but working condition is persistently kept in target time interval threshold value, therefore, smart machine need not Being waken up again just can perform S102, i.e., receive user speech information again.
Specifically, not including standby audio section in above-mentioned first user speech information, if including standby audio section, intelligence Energy equipment can switch to holding state, it is impossible to perform we after the first user speech information is received from working condition The subsequent step of case;In addition, the first user speech information is to switch to the last time after working condition from holding state to receive User speech information, so, smart machine has been responded after the first user speech information, judges whether very first time interval small In equal to target time interval threshold value, that is to say, that judge responding the corresponding interactive instruction of the first user speech information From moment, smart machine is within target time interval threshold value, if receive user speech information again, if it is judged that To have received user speech information again, then S102 is performed, if it is judged that not receive user speech letter again Breath, then perform S103.
It should be noted that in different interaction scenarios, to having responded the corresponding interactive instruction of the first user speech information At the time of can have different definition, specifically, it is considered that at the time of having responded the corresponding interactive instruction of user speech information It is related to the emphasis point of this interactive instruction.
For example, when the voice identification result of the first user speech information is " which nearest school has ", intelligence Equipment obtains nearest school information, and plays obtained information.In this interaction scenarios, what user mutual was instructed focuses on Point has on which on earth in school, can be understood as having responded the first user speech information pair so the information of school is played The interactive instruction answered.
And when the voice identification result of the first user speech information is " latest songs for playing Zhou Jielun ", smart machine Obtain Zhou Jielun latest songs and broadcasting.In this interaction scenarios, in broadcasting, this is moved the emphasis point of user mutual instruction In work and Zhou Jielun latest songs, so the latest songs for commencing play out Zhou Jielun can be regarded as to have responded the first use The corresponding interactive instruction of family voice messaging.
Realized it should be noted that above-mentioned emphasis point can be exploit person for the progress of various types of user speech information What mark was obtained, it can also be what is determined by speech analysis mode, the application is defined not to this.
In addition, target time interval threshold value, can be fixed value set in advance, for example, could be arranged to 5 seconds, 10 seconds, 15 seconds, 20 seconds etc., these were all rational;Target time interval can also be determined according to communicative habits, word speed of user etc. Threshold value, for example, when the communicative habits of user be speak pause frequency is higher or during slower word speed, can set larger Target time interval threshold value, in case when user speech information is also imperfect, smart machine has been put into holding state;In addition, Target time interval threshold value can also be determined according to ambient noise parameters, when environmental noise is larger, can be set larger Object time threshold value, to obtain the user speech information for needing to respond, when environmental noise is too big, in order to prevent receiving user by mistake Voice messaging, smart machine directly can switch to holding state by working condition.
Moreover, it is also possible to which both or three in the noise parameters for passing through the age of user, word speed and environment integrate Target time interval threshold value is determined, it is, of course, also possible to determine target time interval threshold value according to other specification, the application is not This is defined.
S102, is detected when receiving user speech information again, responds target interactive instruction.
From at the time of smart machine judges to have responded the first user speech information, if within target time interval threshold value User speech information is received again, then responds target interactive instruction, the user that the target interactive instruction is as received again The corresponding interactive instruction of voice messaging.
For example, it is assumed that target time interval is 5 seconds, at the time of having responded the first user speech information from smart machine Rise, received user speech information again in 5 seconds, voice identification result is " latest songs for playing Zhou Jielun ", then intelligence Equipment responds the corresponding interactive instruction of user speech information, that is to say, that obtain Zhou Jielun latest songs, and plays this most New song.
It is emphasized that voice identification result can correspond to a user speech for " latest songs for playing Zhou Jielun " Information, can also correspond to a plurality of user speech information.
Specifically, when user speak than it is smoother when, smart machine receives a user speech information, and to this with Family information carries out speech recognition, and obtained voice identification result is " latest songs for playing Zhou Jielun ";
When user speaks it is not smooth when, that is to say, that user speaks when having pause, and smart machine receives a plurality of user's language Message ceases, and carries out speech recognition respectively to a plurality of user profile, and obtained voice identification result also has multiple, for example, respectively For " broadcasting ", " Zhou Jielun ", " newest ", " song ";Due to " broadcasting ", " Zhou Jielun ", " newest ", " song " this four lists Only word sentence is imperfect and without complete implication, and now, smart machine can carry out semantic parsing, and this four words are spelled Connect, when be spliced into sentence it is complete and meaningful if when, that is, when being spliced into " play Zhou Jielun latest songs ", just respond again The corresponding interactive instruction of user speech information received.So as to reduce Consumer's Experience is influenceed because responding by mistake.
In addition, under special circumstances, such as user just starts to interact with smart machine, just as other thing shadows Ring and stopped with smart machine when interacting, the voice identification result in above-mentioned example may also this be single for " broadcasting " Word, now, smart machine can play " I does not understand ", " pardon " etc., when user hears what smart machine was played During sound, it can be interacted again with smart machine in 5 seconds.
It is understood that upper speech recognition result can be:Smart machine is believed the user speech received again Breath carries out the voice identification result that speech recognition is obtained.In this case, smart machine can be obtained from local or server end The corresponding response contents of above-mentioned target interactive instruction are obtained, and respond above-mentioned target interactive instruction.For example:Target interactive instruction is: Zhou Jielun latest songs are played, then smart machine can obtain Zhou Jielun latest songs from server, and play the song; Smart machine can also be from locally obtaining Zhou Jielun latest songs, and plays the song.
Upper speech recognition result can also be:Smart machine sends the user speech information received again to service Obtained voice identification result is identified to the user speech information received in device, server.In this case, server can Directly to determine the response contents of target interactive instruction according to upper speech recognition result, and response contents sent to intelligence to set It is standby, above-mentioned target interactive instruction is responded by smart machine.
Alternatively, it is described to detect when receiving user speech information again in a kind of embodiment, respond mesh The step of marking interactive instruction, including:
Detect when receiving user speech information again, judge whether included in the user speech information received again The standby audio section;
If comprising switching to holding state by working condition.
Specifically, it is assumed that it is " end " to preset standby word, if the user speech information received again is after speech recognition Comprising " end ", this presets standby word, then smart machine switches to holding state by working condition.
For example, it is assumed that target time interval threshold value is 5 seconds, and smart machine is responding the first user speech information pair From at the time of the interactive instruction answered, user speech information was received again in 5 seconds, through the speech recognition user speech information pair The word answered is " today, how is weather" when, obtain and play the weather condition of today;If playing the weather of today After situation, i.e., after response terminates, user speech information is received in 5 seconds again, through speech recognition user speech information correspondence Word comprising " ends " this default standby word, then smart machine holding state is switched to by working condition.
Therefore, when smart machine is in running order, smart machine is to have responded any user voice messaging corresponding From at the time of interactive instruction, in target time interval threshold value, when receiving a user speech information again, this can be responded The corresponding interactive instruction of user speech information, until including standby audio section in the user speech information received again, intelligently sets It is standby that holding state is just switched to by working condition.So user only needs to wake up a smart machine, it is possible to smart machine Repeatedly interacted, so as to simplify interaction, improve Consumer's Experience.
S103, holding state is switched to by working condition.
From at the time of smart machine judges to have responded the first user speech information, within target time interval threshold value, Do not receive user speech information, illustrate that user does not interact temporarily with smart machine, in order to reduce power consumption, smart machine by Working condition switches to holding state.
For example, it is assumed that target time interval threshold value is 5 seconds, and smart machine is responding the first user speech information pair From at the time of the interactive instruction answered, user speech information was not received in 5 seconds, then smart machine is switched to by working condition and treated Machine state.
Compared with prior art, this programme is intelligently set after the corresponding interactive instruction of the first user speech information has been responded It is standby to be continuously in working condition, when the very first time, interval was less than or equal to target time interval threshold value, user is being received again During voice messaging, response receives the corresponding interactive instruction of user speech information again, so as to realize from having responded first From at the time of the corresponding interactive instruction of user speech information, in target time interval threshold value, user need not wake up intelligence again Energy equipment just can again be interacted with smart machine, and process is easy, better user experience.
As shown in Fig. 2 a kind of apparatus control method that the embodiment of the present invention is provided can also include:
Whether S104, when the smart machine is in holding state, judges to include in the user speech information received and call out Awake audio section, if including, performs S105.
Wherein, the wake-up audio section is:The default audio section for waking up word is included in voice identification result;
S105, working condition is switched to by holding state, and determines to include the user speech information of the wake-up audio section Intended recipient direction.
The first user speech information is:Switched to from holding state the last receiving, next after working condition User speech information from the intended recipient direction, not comprising standby audio section;
The user speech information that receives again is:User receiving again, from the intended recipient direction Voice messaging.
It should be noted that when smart machine is in holding state, user speech information is continued to, and to being connect The voice messaging of receipts carries out speech recognition, but in this case, smart machine only recognizes received user speech letter Whether comprising audio section is waken up in breath, when identifying in the user speech information received comprising audio section is waken up, intelligence Can equipment working condition is switched to by holding state, and using the reception direction comprising the user speech information for waking up audio section as Intended recipient direction, this is due to that smart machine is waken up from the intended recipient direction, then the first user speech information and again The probability that the secondary user speech information received comes from the intended recipient direction is larger, therefore, the first user speech now Information and the user speech information received again are defined to come from intended recipient direction.
, can be by being carried out to the user speech information from intended recipient direction in a kind of implementation of the application Wave beam enhancing is handled, and noise suppressed processing is carried out to the user speech information from other directions, to reduce from other directions Interference of the user speech information to the user speech information in intended recipient direction, and then obtain more preferably accurate first user language Message ceases.
It should be noted that under normal circumstances, microphone array is provided with smart machine, so intended recipient direction The method of determination can be:At least two microphones in microphone array receive the time of the voice messaging from all directions Difference, to determine intended recipient direction, wherein it is determined that the method in intended recipient direction has a variety of, such as Time-delay Prediction method is not right herein Determine that the method in intended recipient direction is specifically limited.
Certainly, smart machine can also simultaneously be received and except that can receive the user speech information in intended recipient direction User speech information from other directions, so, user can respond the corresponding friendship of the user speech information from all directions Mutually instruction, prevent because receive direction it is single and caused by can not respond the corresponding interactive instruction of other users voice messaging, this is one Determine that Consumer's Experience can also be improved in degree.
Compared with prior art, can be by including the user for waking up audio section when smart machine is in holding state Voice messaging makes smart machine switch to working condition by holding state, and will receive comprising the user speech for waking up audio section The reception direction of information is defined as intended recipient direction, in target prefixed time interval threshold value, and reception comes from intended recipient The first user speech information in direction, and respond the corresponding interactive instruction of the first user speech information, and receive again User speech information also comes from user speech information, so as to avoid the dry of the user speech information from other directions Disturb, improve Consumer's Experience.
Optionally, in any of the above-described embodiment, it is described response target interactive instruction the step of, can include:
Speech recognition is carried out to the user speech information received again, recognition result is obtained;
The interaction scenarios for the user speech information for determining to receive again according to the recognition result;
Target interactive instruction is responded according to the interaction scenarios.
From smart machine is at the time of the first user speech information has been responded, in target time interval threshold value, connect again When receiving user speech information, speech recognition is carried out to the user speech information received again, it is true according to voice identification result The interaction scenarios of the fixed user speech information received again, then according to the interaction scenarios of determination, what response was received again The corresponding interactive instruction of user speech information, the interactive instruction is target interactive instruction.Due to the user's language received again Message breath has a variety of, and therefore, the interaction scenarios determined according to voice identification result also have a variety of, different interaction scenarios to have Different response modes.
For example, when the voice identification result of the user speech information received again is " how is the weather of today ", smart machine is according to the recognition result, in the Weather information of local or server lookup today, and by the weather of today Information is converted into speech play and come out;And the voice identification result for the user speech information that ought be received again is " broadcasting Zhou Jie The nearest song of human relations ", smart machine is according to the recognition result, in local or server lookup Zhou Jielun latest songs, if In local search Zhou Jielun latest songs, then the song inquired is directly played, if in the newest of server lookup Zhou Jielun Song, then it is the latest songs inquired are locally downloading, then play out, when commencing play out song, can force again The state of smart machine is switched into holding state by working condition.It can be seen that different interaction scenarios have different responders Formula.Optionally, in one implementation, the step of response target interactive instruction according to the interaction scenarios, including:
Whether judge the interaction scenarios is that audio plays scene;
If it is, playing the corresponding audio of target interactive instruction, and holding state is switched to by working condition.
After smart machine receives user speech information again, the voice of the user speech information received again is obtained Recognition result, when in recognition result comprising the similar information such as " broadcasting music " or " broadcasting audio ", then judges to connect again The interaction scenarios of the user speech information received are " audio broadcasting scene ", and play the corresponding audio of target interactive instruction, intelligence The state of energy equipment switches to holding state by working condition.At this moment when smart machine receives user speech information again, intelligence Energy equipment can only detect whether, comprising audio section is waken up, during comprising waking up audio section, to wake up smart machine, can just proceed to respond to use The interactive instruction at family, during not comprising waking up audio section, is not responding to the interactive instruction of user.So it is possible to prevente effectively from other users Voice messaging is played to audio and interfered.
For example, the voice identification result for the user speech information that smart machine is received again is " broadcasting Zhou Jielun Latest songs ", then judge interaction scenarios now be audio play scene, smart machine play Zhou Jielun latest songs ", From at the time of Zhou Jielun latest songs are commenced play out, in target time interval, user speech may be received again Information, the voice identification result of the user speech information for example received again is " today, how is weather", smart machine Obtain the Weather information of today and play the weather condition of today, therefore, smart machine may suspend broadcasting Zhou Jielun most New song transfers to report the weather condition of today, so as to influence user to listen to Zhou Jielun latest songs, reduces Consumer's Experience.
It is not over it should be noted that if audio is played, but user wants to stop, then and user must be again by intelligence Equipment wakes up, and could terminate the broadcasting of audio.Specifically, smart machine is received comprising the user speech information for waking up audio section Afterwards, smart machine is waken up, at the time of smart machine is waken up, in target time interval, the use received again When family voice messaging includes " stopping playing " through the corresponding word of speech recognition, the broadcasting of audio could be terminated.
With reference to specific application example, a kind of apparatus control method provided the embodiment of the present invention is situated between Continue, in the application example, the default wake-up word of smart machine is " Xiao Ming ", and standby wakeup word is " end ", between the object time Every threshold value be 5 seconds.Mainly include following 8 steps:
1st, user is by making " Xiao Ming " smart machine is switched to working condition from holding state;
2nd, after smart machine switches to working condition, at the time of smart machine switches to working condition, at 5 seconds Interior, smart machine receives a user speech information, and voice identification result is " today is either with or without haze", smart machine according to Whether the voice identification result, inquiry has haze today, and according to Query Result, plays the haze situation of today;
3rd, after response terminates, smart machine received a user speech information again in 5 seconds, and voice identification result is " outdoor temperature of today is how many", smart machine inquires about the outdoor temperature of today according to the voice identification result, and plays The outdoor temperature of today.Because voice identification result is " outdoor temperature of today is how many" corresponding user speech information is The last user speech information received after working condition is switched to from holding state, then the first user speech information is knowledge Other result is " outdoor temperature of today is how many" corresponding user speech information;
4th, after the corresponding interactive instruction of the first user speech information has been responded, smart machine is continuously in work shape State;
5th, after the corresponding interactive instruction of the first user speech information has been responded, user speech was received again in 5 seconds Information, voice identification result is " nearest school ", and smart machine inquires about nearest school, and plays the title of nearest school And route;
6th, still, if when having responded the first user speech information, in 5 seconds, user speech information not being received, is intelligently set It is standby that holding state is also switched to by working condition;And if the voice identification result of the user speech information received again is included " end ", then switch to holding state by working condition.
7th, smart machine be in holding state when, user can also by making " Xiao Ming " to wake up smart machine, even if Smart machine switches to working condition by holding state;
8th, after smart machine is waken up, at the time of being waken up, can also be received in 5 seconds user speech letter Breath, and respond the user speech information received;From at the time of the user speech information received has been responded, in 5 seconds also User speech information can be received again, and responds the user speech information received again.That is, user can be with Smart machine is repeatedly talked with.
Compared with prior art, in the application example, user only needs to wake up a smart machine, it is possible to intelligence Equipment is repeatedly interacted, so as to simplify interaction, improves Consumer's Experience.
Corresponding to above method embodiment, the embodiments of the invention provide a kind of plant control unit, set applied to intelligence It is standby, as shown in figure 3, described device can include:
First judge module 310, respond module 320, the first handover module 330;
Wherein,
First judge module 310, for having responded after the corresponding interactive instruction of the first user speech information, lasting place In working condition, and judge whether very first time interval is more than target time interval threshold value, wherein, the first user speech letter Cease and be:The last user speech letter receive, not comprising standby audio section after working condition is switched to from holding state Cease, the standby audio section is:Voice identification result include preset standby word audio section, the very first time at intervals of:From The time interval of user speech information is not received from the time of having responded the corresponding interactive instruction of the first user speech information;
The respond module 320, if the judged result for first judge module 310 is no, detects and connects again When receiving user speech information, target interactive instruction is responded, wherein, the target interactive instruction is:The user received again The corresponding interactive instruction of voice messaging;
First handover module 330, if if the judged result for first judge module 310 is yes, by working State switches to holding state.
Compared with prior art, this this programme is after the corresponding interactive instruction of the first user speech information has been responded, intelligence Equipment is continuously in working condition, and when the very first time, interval was less than or equal to target time interval threshold value, use is being received again During the voice messaging of family, response receives the corresponding interactive instruction of user speech information again, so as to realize from having responded the From at the time of the corresponding interactive instruction of one user speech information, in target time interval threshold value, user need not wake up again Smart machine just can again be interacted with smart machine, and process is easy, better user experience.
Optionally, in one embodiment, the respond module, can include:
Judging submodule, when receiving user speech information again for detecting, judges the user's language received again Whether the standby audio section is included in message breath;
Switching submodule, if for comprising switching to holding state by working condition.
Further, on the basis of comprising the first judge module 310, respond module 320, the first handover module 330, As shown in figure 4, a kind of plant control unit that the embodiment of the present invention is provided can also include:
Second judge module 340, when being in holding state for the smart machine, judges the user speech letter received Whether comprising wake-up audio section in breath, wherein, the wake-up audio section is:The default sound for waking up word is included in voice identification result Frequency range;
Second handover module 350, if the judged result for the second judge module 340 is comprising audio section is waken up, by treating Machine state switches to working condition, and determines the reception direction of the user speech information comprising the wake-up audio section, to be used as mesh Tag splice debit to;
The first user speech information is:Switched to from holding state the last receiving, next after working condition User speech information from the intended recipient direction, not comprising standby audio section;
The user speech that receives again is:User speech letter receive again, from the intended recipient direction Breath.
Compared with prior art, can be by including the use for waking up audio section when being in holding state from smart machine Family voice messaging makes smart machine switch to working condition by holding state, and will receive comprising the user's language for waking up audio section The reception direction of message breath is defined as intended recipient direction, in target prefixed time interval threshold value, and reception comes from target and connect Debit to the first user speech information, and respond the corresponding interactive instruction of the first user profile, and the use received again Family voice messaging also comes from user speech information, so as to avoid the interference of the user speech information from other directions, Improve Consumer's Experience.
Optionally, in any of the above-described embodiment, the respond module, including:
Speech recognition submodule, for carrying out speech recognition to the user speech information received again, obtains identification knot Really;
Interaction scenarios submodule is determined, for the user speech information for determining to receive again according to the recognition result Interaction scenarios;
Submodule is responded, for responding target interactive instruction according to the interaction scenarios.
Optionally, in the above-described embodiment, it is described response submodule specifically for:
Whether judge the interaction scenarios is that audio plays scene;
If it is, playing the corresponding audio of target interactive instruction, and holding state is switched to by working condition.
Optionally, in the above-described embodiment, described device also includes:
Target time interval threshold module is adjusted, for obtaining at least one of following information, and according to being obtained Information adjusts the value of the target time interval threshold value:
The word speed of user;
The communicative habits of user;
Ambient noise parameter.
In addition, the embodiment of the present invention additionally provides a kind of smart machine, as shown in figure 5, the smart machine can include:Shell Body 501, processor 502, memory 503, circuit board 504 and power circuit 505, wherein, circuit board 504 is placed in housing 501 The interior volume surrounded, processor 502 and memory 503 are arranged on circuit board 504;Power circuit 505, for being set for electronics Each standby circuit or device are powered;Memory 503 is used to store executable program code;Processor 502 is stored by reading The executable program code stored in device 503 runs program corresponding with executable program code, for performing the application The apparatus control method that embodiment is provided.
In a kind of implementation of the application, the said equipment control method, including:
Respond after the corresponding interactive instruction of the first user speech information, be continuously in working condition, and when judging first Between be spaced whether be less than or equal to target time interval threshold value, wherein, the first user speech information is:From holding state switching The last user speech information receive, not comprising standby audio section after to working condition, the standby audio section is: Voice identification result include preset standby word audio section, the very first time at intervals of:Believe from the first user speech has been responded The time interval of user speech information is not received from the time of ceasing corresponding interactive instruction;
If it is, detecting when receiving user speech information again, target interactive instruction is responded, wherein, the target Interactive instruction is:The corresponding interactive instruction of user speech information received again;
If it has not, switching to holding state by working condition.
Other implementations of the said equipment control method are identical with the implementation in preceding method embodiment, here not Repeat again.
Processor 502 is to the specific implementation procedure and processor 502 of above-mentioned steps by running executable program code The step of further to perform, the description of Fig. 1-4 illustrated embodiments of the present invention is may refer to, be will not be repeated here.
From above-mentioned, in the embodiment of the present invention, smart machine is responding the corresponding interaction of the first user speech information After instruction, smart machine is continuously in working condition, when the very first time, interval was less than or equal to target time interval threshold value, again Secondary when receiving user speech information, response receives the corresponding interactive instruction of user speech information again, so as to realize At the time of the corresponding interactive instruction of the first user speech information has been responded, in target time interval threshold value, user is not required to To wake up smart machine again just can again be interacted with smart machine, and process is easy, better user experience.
For device, smart machine embodiment, because it is substantially similar to embodiment of the method, so the comparison of description Simply, the relevent part can refer to the partial explaination of embodiments of method.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality Body or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or deposited between operating In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to Nonexcludability is included, so that process, method, article or equipment including a series of key elements not only will including those Element, but also other key elements including being not expressly set out, or also include being this process, method, article or equipment Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that Also there is other identical element in process, method, article or equipment including the key element.
Each embodiment in this specification is described by the way of related, identical similar portion between each embodiment Divide mutually referring to what each embodiment was stressed is the difference with other embodiment.It is real especially for system Apply for example, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method Part explanation.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all Any modification, equivalent substitution and improvements made within the spirit and principles in the present invention etc., are all contained in protection scope of the present invention It is interior.

Claims (10)

1. a kind of apparatus control method, it is characterised in that applied to smart machine, methods described includes:
Respond after the corresponding interactive instruction of the first user speech information, be continuously in working condition, and judged between the very first time Every whether be less than or equal to target time interval threshold value, wherein, the first user speech information is:Work is switched to from holding state Make the last user speech information receive, not comprising standby audio section after state, the standby audio section is:Voice Recognition result include preset standby word audio section, the very first time at intervals of:From having responded the first user speech information pair The time interval of user speech information is not received from the time of the interactive instruction answered;
If it is, detecting when receiving user speech information again, target interactive instruction is responded, wherein, the target interaction Instruct and be:The corresponding interactive instruction of user speech information received again;
If it has not, switching to holding state by working condition.
2. according to the method described in claim 1, it is characterised in that described to detect when receiving user speech information again, The step of responding target interactive instruction, including:
Detect when receiving user speech information again, whether judge in the user speech information received again comprising described Standby audio section;
If comprising switching to holding state by working condition.
3. according to the method described in claim 1, it is characterised in that methods described also includes:
When the smart machine is in holding state, judge whether comprising wake-up audio section in the user speech information received, Wherein, the wake-up audio section is:The default audio section for waking up word is included in voice identification result;
If comprising, working condition is switched to by holding state, and determination includes the user speech information for waking up audio section Intended recipient direction;
The first user speech information is:From holding state switch to after working condition it is the last it is receiving, from institute State intended recipient direction, user speech information not comprising standby audio section;
The user speech information that receives again is:User speech receiving again, from the intended recipient direction Information.
4. the method according to any one of claim 1-3, it is characterised in that the step of the response target interactive instruction Suddenly, including:
Speech recognition is carried out to the user speech information received again, recognition result is obtained;
The interaction scenarios for the user speech information for determining to receive again according to the recognition result;
Target interactive instruction is responded according to the interaction scenarios.
5. method according to claim 4, it is characterised in that described to respond target interactive instruction according to the interaction scenarios The step of, including:
Whether judge the interaction scenarios is that audio plays scene;
If it is, playing the corresponding audio of target interactive instruction, and holding state is switched to by working condition.
6. method according to claim 4, it is characterised in that methods described also includes:
At least one of following information is obtained, and taking for the target time interval threshold value is determined according to the information obtained Value:
The word speed of user;
The communicative habits of user;
Ambient noise parameter.
7. a kind of plant control unit, it is characterised in that applied to smart machine, described device includes:
First judge module, respond module, the first handover module;
Wherein,
First judge module, for having responded after the corresponding interactive instruction of the first user speech information, is continuously in work State, and judge whether very first time interval is less than or equal to target time interval threshold value, wherein, the first user speech information For:The last user speech information receive, not comprising standby audio section after working condition is switched to from holding state, The standby audio section is:In voice identification result comprising preset standby word audio section, the very first time at intervals of:From sound The time interval of user speech information is not received from having answered at the time of the corresponding interactive instruction of the first user speech information;
The respond module, if the judged result for first judge module is yes, detects and receives user's language again When message ceases, target interactive instruction is responded, wherein, the target interactive instruction is:The user speech information pair received again The interactive instruction answered;
First handover module, if the judged result for first judge module is no, is switched to by working condition and treated Machine state.
8. device according to claim 7, it is characterised in that the respond module, including:
Judging submodule, when receiving user speech information again for detecting, judges the user speech letter received again Whether the standby audio section is included in breath;
Switching submodule, if the judged result for the judging submodule is comprising standby audio section, is cut by working condition Shift to holding state.
9. device according to claim 7, it is characterised in that described device also includes:
Second judge module, when being in holding state for the smart machine, be in the user speech information that judgement is received No include wakes up audio section, wherein, the wake-up audio section is:The default audio section for waking up word is included in voice identification result;
Second handover module, if the judged result for second judge module is comprising audio section is waken up, by holding state Working condition is switched to, and determines the intended recipient direction of the user speech information comprising the wake-up audio section;
The first user speech information is:From holding state switch to after working condition it is the last it is receiving, from institute State intended recipient direction, user speech information not comprising standby audio section;
The user speech information that receives again is:User speech receiving again, from the intended recipient direction Information.
10. a kind of smart machine, it is characterised in that the smart machine includes:Housing, processor, memory, circuit board and electricity Source circuit, wherein, circuit board is placed in the interior volume that housing is surrounded, and processor and memory are set on circuit boards;Power supply Circuit, for being powered for each circuit or device of electronic equipment;Memory is used to store executable program code;Processor leads to Cross and read in memory the executable program code that stores to run program corresponding with executable program code, for performing Apparatus control method described in claim any one of 1-6.
CN201710229949.2A 2017-04-10 2017-04-10 Apparatus control method, device and smart machine Pending CN107145329A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710229949.2A CN107145329A (en) 2017-04-10 2017-04-10 Apparatus control method, device and smart machine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710229949.2A CN107145329A (en) 2017-04-10 2017-04-10 Apparatus control method, device and smart machine

Publications (1)

Publication Number Publication Date
CN107145329A true CN107145329A (en) 2017-09-08

Family

ID=59774253

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710229949.2A Pending CN107145329A (en) 2017-04-10 2017-04-10 Apparatus control method, device and smart machine

Country Status (1)

Country Link
CN (1) CN107145329A (en)

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107895573A (en) * 2017-11-15 2018-04-10 百度在线网络技术(北京)有限公司 Method and device for identification information
CN108182943A (en) * 2017-12-29 2018-06-19 北京奇艺世纪科技有限公司 A kind of smart machine control method, device and smart machine
CN108376058A (en) * 2018-02-09 2018-08-07 斑马网络技术有限公司 Sound control method and device and electronic equipment and storage medium
CN108600219A (en) * 2018-04-23 2018-09-28 海信(广东)空调有限公司 A kind of sound control method and equipment
CN108670150A (en) * 2018-05-23 2018-10-19 佛山市顺德区美的洗涤电器制造有限公司 Sound control method, device and the readable storage medium storing program for executing of drawer dishwasher
CN108737933A (en) * 2018-05-30 2018-11-02 上海与德科技有限公司 A kind of dialogue method, device and electronic equipment based on intelligent sound box
CN108806681A (en) * 2018-05-28 2018-11-13 江西午诺科技有限公司 Sound control method, device, readable storage medium storing program for executing and projection device
CN108831455A (en) * 2018-05-25 2018-11-16 四川斐讯全智信息技术有限公司 A kind of method and system of intelligent sound box streaming interaction
CN108962250A (en) * 2018-09-26 2018-12-07 出门问问信息科技有限公司 Audio recognition method, device and electronic equipment
CN108962283A (en) * 2018-01-29 2018-12-07 北京猎户星空科技有限公司 A kind of question terminates the determination method, apparatus and electronic equipment of mute time
CN109493856A (en) * 2017-09-12 2019-03-19 合肥美的智能科技有限公司 Identify method and apparatus, household electrical appliance and the machine readable storage medium of voice
CN109545206A (en) * 2018-10-29 2019-03-29 百度在线网络技术(北京)有限公司 Voice interaction processing method, device and the smart machine of smart machine
CN109671426A (en) * 2018-12-06 2019-04-23 珠海格力电器股份有限公司 A kind of sound control method, device, storage medium and air-conditioning
CN109686372A (en) * 2019-01-02 2019-04-26 百度在线网络技术(北京)有限公司 Resource control method for playing back and device
CN109712621A (en) * 2018-12-27 2019-05-03 维沃移动通信有限公司 A kind of interactive voice control method and terminal
CN109817226A (en) * 2019-03-29 2019-05-28 四川虹美智能科技有限公司 A kind of offline audio recognition method and device
CN110473537A (en) * 2019-08-22 2019-11-19 百度在线网络技术(北京)有限公司 Control method, device, equipment and the storage medium of voice technical ability
WO2020119542A1 (en) * 2018-12-11 2020-06-18 阿里巴巴集团控股有限公司 Voice interaction method, device and system
US11205431B2 (en) 2019-01-02 2021-12-21 Baidu Online Network Technology (Beijing) Co., Ltd. Method, apparatus and device for presenting state of voice interaction device, and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103677198A (en) * 2012-09-03 2014-03-26 联想(北京)有限公司 Electronic equipment control method and electronic equipment
CN104464723A (en) * 2014-12-16 2015-03-25 科大讯飞股份有限公司 Voice interaction method and system
CN104658533A (en) * 2013-11-20 2015-05-27 中兴通讯股份有限公司 Terminal unlocking method and device as well as terminal
CN105810196A (en) * 2016-06-02 2016-07-27 佛山市顺德区美的电热电器制造有限公司 Method and device for voice control on cooking appliance and cooking appliance
CN106155621A (en) * 2015-04-20 2016-11-23 钰太芯微电子科技(上海)有限公司 The key word voice of recognizable sound source position wakes up system and method and mobile terminal up

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103677198A (en) * 2012-09-03 2014-03-26 联想(北京)有限公司 Electronic equipment control method and electronic equipment
CN104658533A (en) * 2013-11-20 2015-05-27 中兴通讯股份有限公司 Terminal unlocking method and device as well as terminal
CN104464723A (en) * 2014-12-16 2015-03-25 科大讯飞股份有限公司 Voice interaction method and system
CN106155621A (en) * 2015-04-20 2016-11-23 钰太芯微电子科技(上海)有限公司 The key word voice of recognizable sound source position wakes up system and method and mobile terminal up
CN105810196A (en) * 2016-06-02 2016-07-27 佛山市顺德区美的电热电器制造有限公司 Method and device for voice control on cooking appliance and cooking appliance

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109493856A (en) * 2017-09-12 2019-03-19 合肥美的智能科技有限公司 Identify method and apparatus, household electrical appliance and the machine readable storage medium of voice
CN107895573A (en) * 2017-11-15 2018-04-10 百度在线网络技术(北京)有限公司 Method and device for identification information
CN108182943A (en) * 2017-12-29 2018-06-19 北京奇艺世纪科技有限公司 A kind of smart machine control method, device and smart machine
CN108182943B (en) * 2017-12-29 2021-03-26 北京奇艺世纪科技有限公司 Intelligent device control method and device and intelligent device
CN108962283A (en) * 2018-01-29 2018-12-07 北京猎户星空科技有限公司 A kind of question terminates the determination method, apparatus and electronic equipment of mute time
CN108376058A (en) * 2018-02-09 2018-08-07 斑马网络技术有限公司 Sound control method and device and electronic equipment and storage medium
CN108600219B (en) * 2018-04-23 2020-09-11 海信(广东)空调有限公司 Voice control method and device
CN108600219A (en) * 2018-04-23 2018-09-28 海信(广东)空调有限公司 A kind of sound control method and equipment
CN108670150A (en) * 2018-05-23 2018-10-19 佛山市顺德区美的洗涤电器制造有限公司 Sound control method, device and the readable storage medium storing program for executing of drawer dishwasher
CN108670150B (en) * 2018-05-23 2021-11-23 佛山市顺德区美的洗涤电器制造有限公司 Voice control method and device for drawer type dish washing machine and readable storage medium
CN108831455A (en) * 2018-05-25 2018-11-16 四川斐讯全智信息技术有限公司 A kind of method and system of intelligent sound box streaming interaction
CN108806681A (en) * 2018-05-28 2018-11-13 江西午诺科技有限公司 Sound control method, device, readable storage medium storing program for executing and projection device
CN108737933A (en) * 2018-05-30 2018-11-02 上海与德科技有限公司 A kind of dialogue method, device and electronic equipment based on intelligent sound box
CN108962250A (en) * 2018-09-26 2018-12-07 出门问问信息科技有限公司 Audio recognition method, device and electronic equipment
CN109545206A (en) * 2018-10-29 2019-03-29 百度在线网络技术(北京)有限公司 Voice interaction processing method, device and the smart machine of smart machine
CN109671426A (en) * 2018-12-06 2019-04-23 珠海格力电器股份有限公司 A kind of sound control method, device, storage medium and air-conditioning
WO2020119542A1 (en) * 2018-12-11 2020-06-18 阿里巴巴集团控股有限公司 Voice interaction method, device and system
CN109712621A (en) * 2018-12-27 2019-05-03 维沃移动通信有限公司 A kind of interactive voice control method and terminal
CN109686372A (en) * 2019-01-02 2019-04-26 百度在线网络技术(北京)有限公司 Resource control method for playing back and device
US11205431B2 (en) 2019-01-02 2021-12-21 Baidu Online Network Technology (Beijing) Co., Ltd. Method, apparatus and device for presenting state of voice interaction device, and storage medium
CN109686372B (en) * 2019-01-02 2022-02-22 百度在线网络技术(北京)有限公司 Resource playing control method and device
CN109817226A (en) * 2019-03-29 2019-05-28 四川虹美智能科技有限公司 A kind of offline audio recognition method and device
CN110473537A (en) * 2019-08-22 2019-11-19 百度在线网络技术(北京)有限公司 Control method, device, equipment and the storage medium of voice technical ability
CN110473537B (en) * 2019-08-22 2022-04-26 百度在线网络技术(北京)有限公司 Voice skill control method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN107145329A (en) Apparatus control method, device and smart machine
CN109166593B (en) Audio data processing method, device and storage medium
CN107146612A (en) Voice guide method, device, smart machine and server
CN107274897A (en) Voice control method and mobile terminal apparatus
CN105190746A (en) Method and apparatus for detecting a target keyword
CN107613132A (en) Voice answering method and mobile terminal apparatus
CN205508398U (en) Intelligent robot with high in clouds interactive function
CN108962241B (en) Position prompting method and device, storage medium and electronic equipment
US20190333514A1 (en) Method and apparatus for dialoguing based on a mood of a user
CN104601538A (en) Server, speaking control method, speaking device, and speaking system
CN109903773B (en) Audio processing method, device and storage medium
CN109686372B (en) Resource playing control method and device
CN108804070B (en) Music playing method and device, storage medium and electronic equipment
CN108806673A (en) A kind of smart machine control method, device and smart machine
CN110865710A (en) Terminal control method and device, mobile terminal and storage medium
CN108735217A (en) Control method of electronic device, device, storage medium and electronic equipment
CN108694947A (en) Sound control method, device, storage medium and electronic equipment
CN105407445B (en) A kind of connection method and the first electronic equipment
CN109871238A (en) Voice interactive method, device and storage medium
CN108922528A (en) Method and apparatus for handling voice
CN108922523B (en) Position prompting method and device, storage medium and electronic equipment
CN103677582A (en) Method for controlling electronic device, and electronic device
CN108989551B (en) Position prompting method and device, storage medium and electronic equipment
CN112735418A (en) Voice interaction processing method and device, terminal and storage medium
CN108231077A (en) Sound control method and system, server, intelligent terminal, the computer readable storage medium of kitchen ventilator

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination