CN109920416A - A kind of sound control method, device, storage medium and control system - Google Patents
A kind of sound control method, device, storage medium and control system Download PDFInfo
- Publication number
- CN109920416A CN109920416A CN201910085633.XA CN201910085633A CN109920416A CN 109920416 A CN109920416 A CN 109920416A CN 201910085633 A CN201910085633 A CN 201910085633A CN 109920416 A CN109920416 A CN 109920416A
- Authority
- CN
- China
- Prior art keywords
- equipment
- solicited message
- audio
- voiceprint
- recognition result
- 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
Links
Abstract
The invention discloses a kind of sound control method, device, storage medium and control systems, this method comprises: obtaining the solicited message that one or more equipment is uploaded in the case where receiving voice messaging in the same family group；Determine that an equipment in one or more equipment is to response apparatus according at least to the solicited message；Control should respond the voice messaging to response apparatus.The solution of the present invention, can solve in more air-conditionings while which platform equipment is unable to decision out be on earth in response to the request of user and there are user's inconvenient problem with use while receiving voice messaging, achieve the effect that promote property easy to use.
Description
Technical field
The invention belongs to voice control technology fields, and in particular to a kind of sound control method, device, storage medium and control
System processed more particularly to a kind of method, apparatus, storage medium and control system for determining more air-conditionings and uniquely responding.
Background technique
Voice air conditioner at this stage brings convenience to our life, but it is undesirable also to produce many users simultaneously
Scene occurs, such as: two voice air conditioners have been put in parlor to certain user at home, and then this user loudly calls in parlor
" so-and-so air-conditioning ", two air-conditionings can all respond at this time.If the air-conditioning in that family is more and more, we are slightly louder called
Air-conditioning will lead to all devices while respond.This is that user is not intended to see, user wishes that air-conditioning can " clever one
Point ", user wish that air-conditioning can independently determine which platform air-conditioning response bottom is.
That is, the prior art, when more air-conditionings receive the voice of someone simultaneously, being unable to decision out is which on earth
The request of one equipment response user, but all equipment all responds.Concrete scene: someone placed a sky in parlor
It adjusts, an air-conditioning is placed in room, and user calls " so-and-so air-conditioning ", this two air-conditionings can all be rung in the case where having received voice
Using the request at family, and say " I ", real user is desirable to only roomed air-conditioning response, not so if loudly exhaled at home
" so-and-so air-conditioning " is called out, that all air-conditioning for receiving voice can all respond.If issuing an order " playing music ", user
Every air-conditioning in family can all play music, this is very bad.User only wants to a certain equipment and responds oneself order to ask
It asks.And this is that the prior art is also not achieved.
Summary of the invention
It is an object of the present invention in view of the foregoing drawbacks, a kind of sound control method, device, storage medium and control are provided
System processed, to solve to be unable to decision out when more air-conditionings receive voice messaging simultaneously in the prior art to be which platform equipment on earth
The request for responding user achievees the effect that promote property easy to use there are user's inconvenient problem with use.
The present invention provides a kind of sound control method, comprising: obtains one or more equipment in the same family group and is receiving
The solicited message uploaded in the case where voice messaging；The solicited message, comprising: audio-frequency information, device parameter and temporal information；
Determine that an equipment in one or more equipment is to response apparatus according at least to the solicited message；Control should be to response apparatus
Respond the voice messaging.
Optionally, wherein the audio-frequency information is every equipment in one or more equipment in the same family group for same
The reception information of voice messaging；And/or the temporal information, comprising: timestamp.
Optionally, the request that one or more equipment is uploaded in the case where receiving voice messaging in the same family group is obtained
Information, comprising: the same time, obtain the same family group in one or more equipment in the case where receiving same voice messaging on
A solicited message of an equipment in more than one solicited message passed.
Optionally, according at least to the solicited message determine an equipment in one or more equipment be to response apparatus,
Include: to the same time obtain an equipment a solicited message in audio-frequency information identify, obtain recognition result；
The record that the recognition result under the same time in family's group whether is stored in the database of setting determined；If the database
In the not stored record for having the recognition result under the same time in family's group, then respond the recognition result corresponding request letter
Breath, the corresponding equipment of the recognition result is determined as to response apparatus；Alternatively, if being stored with family's group in the database
The record of the recognition result under the interior same time, then to one or more record of the recognition result under the same time in family's group
Carry out Application on Voiceprint Recognition.
Optionally, according at least to the solicited message determine an equipment in one or more equipment be to response apparatus,
Further include: the audio-frequency information in a solicited message of the equipment obtained to the same time is identified and is identified
As a result in the case where, the time in the audio-frequency information and its recognition result, the device parameter of this equipment, the solicited message is believed
In the database of the deposit setting of family's group information belonging to breath and this equipment.
Optionally, Application on Voiceprint Recognition, packet are carried out to one or more record of the recognition result under the same time in family's group
It includes: obtaining one or more record of the recognition result under the same time in family's group；Audio to this in one or more record
Information carries out Application on Voiceprint Recognition, to determine in the corresponding voiceprint of audio-frequency information in one or more record, there is several vocal prints
Information voiceprint corresponding with the voice messaging is identical；If the corresponding vocal print letter of audio-frequency information in one or more record
There is voiceprint voiceprint corresponding with the voice messaging identical in breath, then responds identification belonging to this voiceprint
The corresponding equipment of this voiceprint is determined as to response apparatus by as a result corresponding solicited message；Alternatively, if this with
There is two or more voiceprints vocal print corresponding with the voice messaging in the corresponding voiceprint of audio-frequency information in upper record
Information is identical, then carries out sound intensity comparison to two or more the voiceprints.
Optionally, wherein respond the corresponding solicited message of the recognition result, comprising: semantic solution is carried out to the recognition result
Analysis, and parsing result is back to this equipment；And/or sound intensity comparison, packet are carried out to two or more the voiceprints
Include: obtain corresponding two of two or more the voiceprints or more record in audio-frequency information sound intensity, and by two with
The corresponding equipment of maximum value in upper sound intensity is determined as to response apparatus.
Match with the above method, another aspect of the present invention provides a kind of phonetic controller, comprising: acquiring unit is used
In the solicited message that one or more equipment is uploaded in the case where receiving voice messaging in acquisition the same family group；The request
Information, comprising: audio-frequency information, device parameter and temporal information；Control unit, for determining one according at least to the solicited message
An equipment in the above equipment of platform is to response apparatus；Described control unit, institute should be responded to response apparatus by being also used to control
State voice messaging.
Optionally, wherein the audio-frequency information is every equipment in one or more equipment in the same family group for same
The reception information of voice messaging；And/or the temporal information, comprising: timestamp.
Optionally, the acquiring unit obtains in the same family group one or more equipment the case where receiving voice messaging
The solicited message of lower upload, comprising: the same time obtains one or more equipment in the same family group and receiving same voice letter
A solicited message of an equipment in more than one solicited message uploaded in the case where breath.
Optionally, described control unit determines that an equipment in one or more equipment is according at least to the solicited message
To response apparatus, comprising: identify, obtain to the audio-frequency information in a solicited message of an equipment of acquisition of same time
To recognition result；The record that the recognition result under the same time in family's group whether is stored in the database of setting determined；
If the not stored record for having the recognition result under the same time in family's group, responds the recognition result pair in the database
The corresponding equipment of the recognition result is determined as to response apparatus by the solicited message answered；Alternatively, if being stored in the database
There is the record of the recognition result under the same time in family's group, then to one of the recognition result under the same time in family's group
It is more than item that record carries out Application on Voiceprint Recognition.
Optionally, described control unit determines that an equipment in one or more equipment is according at least to the solicited message
To response apparatus, further includes: the audio-frequency information in a solicited message of the equipment obtained to the same time is known
In the case where not obtaining recognition result, by the audio-frequency information and its recognition result, the device parameter of this equipment, request letter
In the database of the deposit setting of family's group information belonging to temporal information and this equipment in breath.
Optionally, described control unit carries out one or more record of the recognition result under the same time in family's group
Application on Voiceprint Recognition, comprising: obtain one or more record of the recognition result under the same time in family's group；To this, one or more is remembered
Audio-frequency information in record carries out Application on Voiceprint Recognition, to determine in the corresponding voiceprint of audio-frequency information in one or more record,
There is several voiceprints voiceprint corresponding with the voice messaging identical；If the audio-frequency information pair in one or more record
There is voiceprint voiceprint corresponding with the voice messaging identical in the voiceprint answered, then responds this vocal print letter
The corresponding solicited message of recognition result, the corresponding equipment of this voiceprint is determined as to response apparatus belonging to ceasing；Alternatively,
If having two or more voiceprints and the voice messaging in the corresponding voiceprint of audio-frequency information in one or more record
Corresponding voiceprint is identical, then carries out sound intensity comparison to two or more the voiceprints.
Optionally, wherein described control unit responds the corresponding solicited message of the recognition result, comprising: to the identification knot
Fruit carries out semantic parsing, and parsing result is back to this equipment；And/or described control unit is to two or more the vocal prints
Information carries out sound intensity comparison, comprising: obtains the audio letter in corresponding two of two or more the voiceprints or more record
The sound intensity of breath, and the corresponding equipment of maximum value in more than two sound intensities is determined as to response apparatus.
Match with above-mentioned apparatus, further aspect of the present invention provides a kind of control system, comprising: above-described voice control
Device processed.
Match with the above method, further aspect of the present invention provides a kind of storage medium, comprising: deposited in the storage medium
Contain a plurality of instruction；The a plurality of instruction, for being loaded by processor and executing above-described sound control method.
Match with the above method, further aspect of the present invention provides a kind of control system, comprising: processor, for executing
A plurality of instruction；Memory, for storing a plurality of instruction；Wherein, a plurality of instruction, for being stored by the memory, and by
The processor loads and executes above-described sound control method.
The solution of the present invention, by speech recognition, Application on Voiceprint Recognition, the loudness of sound and timestamp come the voice to user
Input is determined specifically which platform equipment response, realizes and there was only an equipment response, Ke Yiti under same voice messaging
Rise the convenience that user uses.
Further, the solution of the present invention, by speech recognition, Application on Voiceprint Recognition, the loudness of sound and timestamp come to
The voice input at family is determined that specifically which platform equipment response, same user call air-conditioning in the environment of more air-conditionings,
An air-conditioning response is only had, it is energy saving.
Further, the solution of the present invention, by speech recognition, Application on Voiceprint Recognition, the loudness of sound and timestamp come to
The voice input at family is determined specifically which platform equipment response, is conveniently used under same voice only controlling an equipment,
User experience is good.
Further, the solution of the present invention goes out to use by the loudness using speech recognition, Application on Voiceprint Recognition combination sound come decision
The equipment of the same instruction of the same sound in family family group in the response same time, can be requested with quick response user,
Treatment effeciency is high.
Further, the solution of the present invention goes out to use by the loudness using speech recognition, Application on Voiceprint Recognition combination sound come decision
The equipment of the same instruction of the same sound in family family group in the response same time, the use that can satisfy user need
It asks, and avoids multiple devices while responding to interfere, high reliablity, hommization are good.
The solution of the present invention as a result, by speech recognition, Application on Voiceprint Recognition, the loudness of sound and timestamp come to user
Voice input determined specifically which platform equipment response, solve to receive voice letter simultaneously in more air-conditionings in the prior art
It is the request of which platform equipment response user on earth that decision is unable to when breath out, and there are user's inconvenient problems with use, thus, gram
The defect of inconvenient to use in the prior art, waste of energy and poor user experience is taken, realizes easy to use, energy saving and user
The beneficial effect experienced.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
Detailed description of the invention
Fig. 1 is the flow diagram of an embodiment of sound control method of the invention；
Fig. 2 is to determine that an equipment in one or more equipment is in method of the invention according at least to the solicited message
The flow diagram of an embodiment to response apparatus；
Fig. 3 is to carry out in method of the invention to one or more record of the recognition result under the same time in family's group
The flow diagram of one embodiment of Application on Voiceprint Recognition；
Fig. 4 is the structural schematic diagram of an embodiment of phonetic controller of the invention；
Fig. 5 is the control flow schematic diagram of an embodiment of control system (such as Cloud Server) of the invention.
In conjunction with attached drawing, appended drawing reference is as follows in the embodiment of the present invention:
102- acquiring unit；104- control unit.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the specific embodiment of the invention and
Technical solution of the present invention is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
According to an embodiment of the invention, providing a kind of sound control method, the one of method of the invention is real as shown in Figure 1
Apply the flow diagram of example.The sound control method may include: step S110 to step S130.
At step S110, obtains one or more equipment in the same family group and uploaded in the case where receiving voice messaging
Solicited message.The solicited message, be the same family group in one or more equipment based on the voice messaging received and on
The solicited message of biography.The solicited message may include: audio-frequency information, device parameter and temporal information.
Specifically, the audio-frequency information is that every equipment is directed to same voice in one or more equipment in the same family group
The reception information of information.
As a result, by accordingly being set with one or more equipment in the same family group for the reception information of same voice messaging
The standby audio-frequency information uploaded is convenient for speech recognition and voice control, and precisely, reliably.
Specifically, the temporal information may include: timestamp.
As a result, by using timestamp as temporal information, can more accurately determine that every equipment uploads audio-frequency information
Time, to be conducive to more accurate and reliably determine to response apparatus.
Optionally, in step S110 obtain the same family group in one or more equipment in the case where receiving voice messaging
The solicited message of upload may include: the same time, obtains one or more equipment in the same family group and is receiving same voice
A solicited message of an equipment in more than one solicited message uploaded in the case where information.
Such as: multiple devices are connected in the family's group of oneself by user, hear the wake-up of user simultaneously in multiple devices
When word or order, the audio received and the parameter of itself and current time stamp are transferred to cloud service simultaneously by multiple devices
Device, Cloud Server receive the request of a certain equipment.
As a result, by receiving the solicited message that an equipment uploads in the same time, can more accurately determine same
One time upload solicited message, so as to more precisely and reliably determine to response apparatus.
At step S120, determine that an equipment in one or more equipment is wait respond according at least to the solicited message
Equipment.
It is alternatively possible to determine one or more according at least to the solicited message in method of the invention as shown in connection with fig. 2
An equipment in equipment is the embodiment flow diagram to response apparatus, further illustrate in step S120 according at least to
The solicited message determines that an equipment in one or more equipment is the detailed process to response apparatus, may include: step
S210 to step S240.
Step S210, to the same time obtain an equipment a solicited message in audio-frequency information identify,
Obtain recognition result.
Such as: after Cloud Server receives the request of a certain equipment, its audio of speech recognition.
Step S220 determines in the database of setting whether be stored in family's group the recognition result under the same time
Record.Such as: the record that same recognition result under the same time in family's group whether is stored in the database of setting determined.
Such as: after Cloud Server receives audio-frequency information request, interior other of domestic consumer group are inquired in the database and are set
In standby same timestamp and the record of same recognition result.
Step S230, if the not stored record for having the recognition result under the same time in family's group in the database,
The corresponding solicited message of the recognition result is then responded, the corresponding equipment of the recognition result is determined as to response apparatus.
Such as: if qualified data are not present in database, then it represents that the same time does not have in active user family group
There are more air-conditionings to receive same instruction, Cloud Server directly in response to present video recognition result request (to audio identification
As a result it is parsed and returns to processing result to equipment).
More optionally, the corresponding solicited message of the recognition result is responded in step step S230, may include: to the identification
As a result semantic parsing is carried out, and parsing result is back to this equipment.
The parsing result this is back to and then the recognition result to audio-frequency information carries out semantic parse as a result, to set
It is standby, to be realized based on the voice messaging that user sends to the voice control of this equipment, high reliablity and user experience is good.
Alternatively, step S240, if being stored with the note of the recognition result under the same time in family's group in the database
Record then carries out Application on Voiceprint Recognition to one or more record of the recognition result under the same time in family's group, by family's group
It is to response apparatus that one, which records a corresponding equipment, in one or more record of the recognition result under the interior same time.
By the corresponding equipment of the solicited message when as a result, by received solicited message of same time without identical recordings
Further according to the identical recordings when being determined as to response apparatus, and having identical recordings in received solicited message of same time
The corresponding voiceprint of several solicited messages determine to response apparatus so that treat respond the voice messaging to response apparatus
Determination it is simple and reliable.
More it is alternatively possible to as shown in connection with fig. 3 to the identification knot under the same time in family's group in method of the invention
One or more record of fruit carries out an embodiment flow diagram of Application on Voiceprint Recognition, further illustrates in step S240 to the family
One or more record of the recognition result carries out the detailed process of Application on Voiceprint Recognition under the same time in group, may include: step
S310 to step S340.
Step S310 obtains one or more record of the recognition result under the same time in family's group.
Step S320, the audio-frequency information to this in one or more record carry out Application on Voiceprint Recognition, to determine one or more note
In the corresponding voiceprint of audio-frequency information in record, there is several voiceprints voiceprint phase corresponding with the voice messaging
Together.
Step S330, if having in the corresponding voiceprint of audio-frequency information in this one or more record a voiceprint with
The corresponding voiceprint of the voice messaging is identical, then responds the corresponding solicited message of the affiliated recognition result of this voiceprint,
Being determined as the corresponding equipment of this voiceprint to response apparatus.
Alternatively, step S340, if having two or more in the corresponding voiceprint of audio-frequency information in one or more record
Voiceprint voiceprint corresponding with the voice messaging is identical, then carries out sound intensity ratio to two or more the voiceprints
Compared with by the maximum audio letter of the sound intensity of the audio-frequency information in corresponding two of two or more the voiceprints or more record
Corresponding equipment is ceased to be determined as to response apparatus.
Such as: it records if it exists, obtains all qualified records, audio-frequency information therein is subjected to Application on Voiceprint Recognition,
Detect whether it is identical with the Application on Voiceprint Recognition result of current sound, if the audio vocal print recognition result of current request and all records
Application on Voiceprint Recognition result is all different, then it represents that within the same time, the other equipment in family's group are not received by be worked as with sending
The same sound of the people of preceding audio, then it represents that the same time only has an air-conditioning to have received someone's in active user family group
Instruction, Cloud Server is directly in response to current request.
Further in the several of the identical recordings when as a result, by having identical recordings in received solicited message of same time
It is true when only one voiceprint is identical as voiceprint corresponding to voice messaging in the corresponding voiceprint of a solicited message
The fixed corresponding equipment of the voiceprint is to response message, and there are two the above voiceprint and languages in several solicited messages
It is further determined according to intensity of sound to response apparatus when the corresponding voiceprint of message breath is identical, responds the language so that treating
The determination to response apparatus of message breath is accurate and reliable.
Further optionally, sound intensity comparison is carried out to two or more the voiceprints in step S340, can wrap
Include: obtain corresponding two of two or more the voiceprints or more record in audio-frequency information sound intensity, and by two with
The corresponding equipment of maximum value in upper sound intensity is determined as to response apparatus.
Such as: it is inputted and is carried out come the voice to user by speech recognition, Application on Voiceprint Recognition, the loudness of sound and timestamp
Which determine to be specifically platform equipment response.Such as go out user house using the loudness of speech recognition, Application on Voiceprint Recognition combination sound come decision
The equipment of the same instruction of the same sound in the group of front yard in the response same time.
Such as: if the wherein recognition result phase of the Application on Voiceprint Recognition result of some or all audio frequency and present video
Together, then it represents that there are have multiple devices to have received same user's same instructions in the same time in active user family group
Situation, at this point, the identical audio of Application on Voiceprint Recognition result to carry out the comparison of sound intensity, if worked as with the audio of current request
The loudness of the sound of preceding request is the largest, then Cloud Server is directly in response to current request；If the loudness of current sound is not
If maximum, Cloud Server is just not responding to current request.It wherein, is made a concrete analysis of to a request here, thus ' when
Before ' some request that is handling of the Cloud Server that just refers to.
By in several solicited messages, there are two voiceprints corresponding to the above voiceprint and voice messaging as a result,
Further intensity of sound the maximum is determined as that the equipment nearest apart from user being determined as wait ring to response apparatus when identical
Equipment is answered, it is precisely and reliable.
Still optionally further, determine that one in one or more equipment sets according at least to the solicited message in step S120
Standby is to response apparatus, can also include: that can specifically include the process of recognition result deposit database: to same a period of time
Between in the case that audio-frequency information in the solicited message of an equipment that obtains identified and obtains recognition result, by this
Audio-frequency information and its recognition result, the device parameter of this equipment, the temporal information in the solicited message and this equipment institute
In the database of family's group information deposit setting of category.
Such as: after receiving the request of a certain equipment and speech recognition its audio, audio-frequency information, recognition result, equipment are joined
Number, obtained timestamp and owning user family group information deposit database.
As a result, by the way that corresponding information is stored in database after newly identifying to the audio in each solicited message, just
It is accurate and reliable in record and comparison.
At step S130, control should respond the voice messaging to response apparatus.
Such as: same user calls air-conditioning in the environment of more air-conditionings, only has an air-conditioning response.Solve one
The case where someone speaks by multiple devices while receiving audio-frequency information and responding simultaneously in a subscriber household group.
As a result, by being uploaded according at least to one or more equipment in the same family group in the case where receiving voice messaging
Solicited message, determine an equipment in one or more equipment be wait respond the voice messaging to response apparatus, and then control
System to response apparatus should respond the voice messaging, avoid multiple devices while responding the speech ciphering equipment and the use to user causes
Inconvenience, to greatly promote the convenience that user uses.
Through a large amount of verification experimental verification, using the technical solution of the present embodiment, pass through speech recognition, Application on Voiceprint Recognition, sound
Loudness and timestamp input specifically which platform equipment response determined come the voice to user, realize and believe in same voice
The lower only equipment response of breath, can promote the convenience that user uses.
According to an embodiment of the invention, additionally providing a kind of phonetic controller corresponding to sound control method.Referring to
The structural schematic diagram of one embodiment of the device of the invention shown in Fig. 4.The phonetic controller may include: acquiring unit 102
With control unit 104.
In an optional example, acquiring unit 102 can be used for obtaining one or more equipment in the same family group and connect
The solicited message uploaded in the case where receiving voice messaging.The solicited message is one or more equipment in the same family group
The solicited message uploaded based on the voice messaging received.The solicited message may include: audio-frequency information, device parameter
And temporal information.The concrete function of the acquiring unit 102 and processing are referring to step S110.
Specifically, the audio-frequency information is that every equipment is directed to same voice in one or more equipment in the same family group
The reception information of information.
As a result, by accordingly being set with one or more equipment in the same family group for the reception information of same voice messaging
The standby audio-frequency information uploaded is convenient for speech recognition and voice control, and precisely, reliably.
Specifically, the temporal information may include: timestamp.
As a result, by using timestamp as temporal information, can more accurately determine that every equipment uploads audio-frequency information
Time, to be conducive to more accurate and reliably determine to response apparatus.
Optionally, the acquiring unit 102 obtains one or more equipment in the same family group and is receiving voice messaging
In the case of the solicited message that uploads, may include: the acquiring unit 102, specifically can be also used for the same time, obtain same
One in more than one solicited message that one or more equipment is uploaded in the case where receiving same voice messaging in family's group
One solicited message of equipment.
Such as: multiple devices are connected in the family's group of oneself by user, hear the wake-up of user simultaneously in multiple devices
When word or order, the audio received and the parameter of itself and current time stamp are transferred to cloud service simultaneously by multiple devices
Device, Cloud Server receive the request of a certain equipment.
As a result, by receiving the solicited message that an equipment uploads in the same time, can more accurately determine same
One time upload solicited message, so as to more precisely and reliably determine to response apparatus.
In an optional example, control unit 104 can be used for determining one or more according at least to the solicited message
An equipment in equipment is to response apparatus.The concrete function of the control unit 104 and processing are referring to step S120.
Optionally, described control unit 104 determines that one in one or more equipment sets according at least to the solicited message
Standby is that may include: to response apparatus
Described control unit 104 specifically can be also used for a solicited message of the equipment obtained to the same time
In audio-frequency information identified, obtain recognition result.The concrete function of the control unit 104 and processing see also step
S210。
Such as: after Cloud Server receives the request of a certain equipment, its audio of speech recognition.
Described control unit 104 specifically can be also used for determining whether be stored in family's group in the database set
The record of the recognition result under the same time.Such as: determine whether be stored in family's group in the database of setting with for the moment
Between under same recognition result record.The concrete function of the control unit 104 and processing see also step S220.
Such as: after Cloud Server receives audio-frequency information request, interior other of domestic consumer group are inquired in the database and are set
In standby same timestamp and the record of same recognition result.
Described control unit 104, if specifically can be also used in the database it is not stored have in family's group with for the moment
Between the lower recognition result record, then the corresponding solicited message of the recognition result is responded, by the corresponding equipment of the recognition result
It is determined as to response apparatus.The concrete function of the control unit 104 and processing see also step S230.
Such as: if qualified data are not present in database, then it represents that the same time does not have in active user family group
There are more air-conditionings to receive same instruction, Cloud Server directly in response to present video recognition result request (to audio identification
As a result it is parsed and returns to processing result to equipment).
More optionally, described control unit 104 responds the corresponding solicited message of the recognition result, may include: the control
Unit 104 processed specifically can be also used for carrying out the recognition result semantic parsing, and parsing result be back to this equipment.
The parsing result this is back to and then the recognition result to audio-frequency information carries out semantic parse as a result, to set
It is standby, to be realized based on the voice messaging that user sends to the voice control of this equipment, high reliablity and user experience is good.
Alternatively, described control unit 104, if specifically can be also used for being stored in the database same in family's group
The record of the recognition result under time, then to one or more record carry out sound of the recognition result under the same time in family's group
Line identification, by under the same time in family's group in one or more record of the recognition result one record corresponding one and set
Standby is to response apparatus.The concrete function of the control unit 104 and processing see also step S240.
By the corresponding equipment of the solicited message when as a result, by received solicited message of same time without identical recordings
Further according to the identical recordings when being determined as to response apparatus, and having identical recordings in received solicited message of same time
The corresponding voiceprint of several solicited messages determine to response apparatus so that treat respond the voice messaging to response apparatus
Determination it is simple and reliable.
More optionally, one or more note of described control unit 104 to the recognition result under the same time in family's group
Record carries out Application on Voiceprint Recognition, may include:
Described control unit 104 specifically can be also used for obtaining in family's group one of the recognition result under the same time
It more than item records.The concrete function of the control unit 104 and processing see also step S310.
Described control unit 104 specifically can be also used for the audio-frequency information to this in one or more record and carry out vocal print knowledge
Not, to determine in the corresponding voiceprint of audio-frequency information in one or more record, there are several voiceprints and the voice
The corresponding voiceprint of information is identical.The concrete function of the control unit 104 and processing see also step S320.
Described control unit 104, if specifically can be also used for the corresponding vocal print of audio-frequency information in one or more record
There is voiceprint voiceprint corresponding with the voice messaging identical in information, then responds and know belonging to this voiceprint
The corresponding solicited message of other result, the corresponding equipment of this voiceprint is determined as to response apparatus.The control unit 104
Concrete function and processing see also step S330.
Alternatively, described control unit 104, if the audio-frequency information that specifically can be also used in one or more record is corresponding
There is two or more voiceprints voiceprint corresponding with the voice messaging identical in voiceprint, then to two or more the sound
Line information carries out sound intensity comparison, by the audio-frequency information in corresponding two of two or more the voiceprints or more record
The corresponding equipment of the maximum audio-frequency information of sound intensity is determined as to response apparatus.The concrete function of the control unit 104 and place
Reason sees also step S340.
Such as: it records if it exists, obtains all qualified records, audio-frequency information therein is subjected to Application on Voiceprint Recognition,
Detect whether it is identical with the Application on Voiceprint Recognition result of current sound, if the audio vocal print recognition result of current request and all records
Application on Voiceprint Recognition result is all different, then it represents that within the same time, the other equipment in family's group are not received by be worked as with sending
The same sound of the people of preceding audio, then it represents that the same time only has an air-conditioning to have received someone's in active user family group
Instruction, Cloud Server is directly in response to current request.
Further in the several of the identical recordings when as a result, by having identical recordings in received solicited message of same time
It is true when only one voiceprint is identical as voiceprint corresponding to voice messaging in the corresponding voiceprint of a solicited message
The fixed corresponding equipment of the voiceprint is to response message, and there are two the above voiceprint and languages in several solicited messages
It is further determined according to intensity of sound to response apparatus when the corresponding voiceprint of message breath is identical, responds the language so that treating
The determination to response apparatus of message breath is accurate and reliable.
Further optionally, described control unit 104 carries out sound intensity comparison to two or more the voiceprints, can
To include: described control unit 104, it specifically can be also used for obtaining corresponding two of two or more the voiceprints or more and record
In audio-frequency information sound intensity, and the corresponding equipment of maximum value in more than two sound intensities is determined as setting wait respond
It is standby.
Such as: it is inputted and is carried out come the voice to user by speech recognition, Application on Voiceprint Recognition, the loudness of sound and timestamp
Which determine to be specifically platform equipment response.Such as go out user house using the loudness of speech recognition, Application on Voiceprint Recognition combination sound come decision
The equipment of the same instruction of the same sound in the group of front yard in the response same time.
Such as: if the wherein recognition result phase of the Application on Voiceprint Recognition result of some or all audio frequency and present video
Together, then it represents that there are have multiple devices to have received same user's same instructions in the same time in active user family group
Situation, at this point, the identical audio of Application on Voiceprint Recognition result to carry out the comparison of sound intensity, if worked as with the audio of current request
The loudness of the sound of preceding request is the largest, then Cloud Server is directly in response to current request；If the loudness of current sound is not
If maximum, Cloud Server is just not responding to current request.It wherein, is made a concrete analysis of to a request here, thus ' when
Before ' some request that is handling of the Cloud Server that just refers to.
By in several solicited messages, there are two voiceprints corresponding to the above voiceprint and voice messaging as a result,
Further intensity of sound the maximum is determined as that the equipment nearest apart from user being determined as wait ring to response apparatus when identical
Equipment is answered, it is precisely and reliable.
Still optionally further, described control unit 104 determines in one or more equipment according at least to the solicited message
One equipment is to response apparatus, can also include: that can specifically include the process of recognition result deposit database: described
Control unit 104 specifically can be also used for the audio letter in a solicited message of the equipment obtained to the same time
In the case that breath is identified and obtains recognition result, by the audio-frequency information and its recognition result, this equipment device parameter,
In the database of the deposit setting of family's group information belonging to temporal information and this equipment in the solicited message.
Such as: after receiving the request of a certain equipment and speech recognition its audio, audio-frequency information, recognition result, equipment are joined
Number, obtained timestamp and owning user family group information deposit database.
As a result, by the way that corresponding information is stored in database after newly identifying to the audio in each solicited message, just
It is accurate and reliable in record and comparison.
In an optional example, described control unit 104, can be also used for control should respond institute's predicate to response apparatus
Message breath.The concrete function of the control unit 104 and processing see also step S130.
The processing and function realized by the device of the present embodiment essentially correspond to earlier figures 1 to method shown in Fig. 3
Embodiment, principle and example, therefore not detailed place in the description of the present embodiment may refer to mutually speaking on somebody's behalf in previous embodiment
Bright, this will not be repeated here.
Through a large amount of verification experimental verification, using technical solution of the present invention, by speech recognition, Application on Voiceprint Recognition, sound sound
Degree and timestamp input specifically which platform equipment response determined come the voice to user, and same user is in more air-conditionings
In the environment of call air-conditioning, only have the response of air-conditioning, it is energy saving.
According to an embodiment of the invention, additionally providing a kind of control system corresponding to phonetic controller.The control system
System may include: above-described phonetic controller.
In an optional embodiment, the solution of the present invention, by the loudness of speech recognition, Application on Voiceprint Recognition, sound with
And specifically which platform equipment response determined come the voice input to user for timestamp.In this way, same user is in more skies
In the environment of tune, air-conditioning is called, only has an air-conditioning response.
In an optional example, the solution of the present invention is determined using the loudness of speech recognition, Application on Voiceprint Recognition combination sound
The equipment that plan goes out the same instruction of the same sound in subscriber household group in the response same time.
In an optional specific embodiment, example shown in fig. 5 may refer to, to the specific reality of the solution of the present invention
Existing process illustrates.
Wherein, the solution of the present invention provide a kind of method for determining more air-conditionings and uniquely responding, mainly by speech recognition,
Application on Voiceprint Recognition, sound intensity compare three parts Composition of contents.
In an optional specific example, example shown in Figure 5, a kind of judgement more of the solution of the present invention offer
The method that air-conditioning uniquely responds may include: that multiple devices are connected in the family's group of oneself by user, multiple devices simultaneously
When hearing wake-up word or the order of user, multiple devices are simultaneously by the audio received and the parameter of itself and current time
Stamp is transferred to Cloud Server, and Cloud Server receives the request of a certain equipment, its audio of speech recognition, and by audio-frequency information, identification
As a result (result of such as speech recognition), device parameter, obtained timestamp and owning user family group information are stored in database.
Such as: the parameter of itself may include: device model, equipment unique identification etc., it is therefore an objective to make server according to
The parameter of equipment unique identification etc. itself obtains family's group belonging to the equipment.
Specifically, when coming server to a request, Cloud Server can do the work that following steps complete screening:
Step 1 after receiving audio-frequency information request, inquires the domestic consumer in the database and organizes interior other equipment with for the moment
Between stab in and same recognition result record.
Optionally, if qualified data are not present in database, then it represents that the same time in active user family group
There is no more air-conditionings to receive same instruction, Cloud Server directly in response to present video recognition result request (to audio identification
Result parsed and return to processing result to equipment).
Such as: condition here can be the query result in step 1.That is: if step 1 is in the database
The result checked out is sky, then it represents that the same time does not have more air-conditionings to receive same instruction in active user family group,
Request of the Cloud Server directly in response to present video recognition result.
Optionally, it records if it exists, obtains all qualified records, audio-frequency information therein is subjected to vocal print knowledge
, do not detect whether it is identical with the Application on Voiceprint Recognition result of current sound, if the audio vocal print recognition result of current request and all notes
The Application on Voiceprint Recognition result of record is all different, then it represents that within the same time, the other equipment in family's group are not received by and send out
The same sound of the people of present video out, then it represents that the same time only has an air-conditioning to have received some in active user family group
The instruction of people, Cloud Server is directly in response to current request.
Optionally, if the wherein recognition result phase of the Application on Voiceprint Recognition result of some or all audio frequency and present video
Together, then it represents that there are have multiple devices to have received same user's same instructions in the same time in active user family group
Situation, at this point, the identical audio of Application on Voiceprint Recognition result to carry out the comparison of sound intensity, if worked as with the audio of current request
The loudness of the sound of preceding request is the largest, then Cloud Server is directly in response to current request；If the loudness of current sound is not
If maximum, Cloud Server is just not responding to current request.It wherein, is made a concrete analysis of to a request here, thus ' when
Before ' some request that is handling of the Cloud Server that just refers to.
As it can be seen that speak this addresses the problem someone in a subscriber household group by multiple devices while receiving audio letter
The case where ceasing and responding simultaneously.
Such as: user placed an air-conditioning in the parlor of own home, and an air-conditioning is also placed in bedroom.User exists
The door in bedroom to be opened in bedroom, and calls " so-and-so air-conditioning ", the air-conditioning in bedroom and the air-conditioning in parlor all receive voice, and this two
Air-conditioning can all respond " I ", and user continues issue an order " playing music ", this two air-conditionings still have received language at this time
Sound can all respond and play music.And the solution of the present invention it will be realized that this two equipment same times all receive some
When the voice of user, the request for only having an air-conditioning response user (that is only has the air-conditioning in bedroom that can just respond " so-and-so
Air-conditioning ", and the instruction of " playing music ").
The processing and function realized by the control system of the present embodiment essentially correspond to aforementioned device shown in Fig. 4
Embodiment, principle and example, therefore not detailed place in the description of the present embodiment, may refer to mutually speaking on somebody's behalf in previous embodiment
Bright, this will not be repeated here.
Through a large amount of verification experimental verification, using technical solution of the present invention, by speech recognition, Application on Voiceprint Recognition, sound sound
Degree and timestamp input specifically which platform equipment response determined come the voice to user, are conveniently used in same voice
One equipment of lower control, user experience are good.
According to an embodiment of the invention, additionally providing a kind of storage medium corresponding to sound control method.The storage is situated between
Matter may include: that a plurality of instruction is stored in the storage medium；The a plurality of instruction, for being loaded by processor and being executed
Above-described sound control method.
The processing and function realized by the storage medium of the present embodiment essentially correspond to earlier figures 1 to shown in Fig. 3
Embodiment, principle and the example of method, therefore not detailed place in the description of the present embodiment, may refer to the phase in previous embodiment
It speaks on somebody's behalf bright, this will not be repeated here.
Through a large amount of verification experimental verification, using technical solution of the present invention, by utilizing speech recognition, Application on Voiceprint Recognition combination sound
The loudness of sound carrys out the equipment that decision goes out the same instruction of the same sound in subscriber household group in the response same time, can be with
Quick response user request, treatment effeciency are high.
According to an embodiment of the invention, additionally providing a kind of control system corresponding to sound control method.The control system
System, may include: processor, for executing a plurality of instruction；Memory, for storing a plurality of instruction；Wherein, a plurality of finger
It enables, for being stored by the memory, and is loaded by the processor and execute above-described sound control method.
The processing and function realized by the control system of the present embodiment essentially correspond to earlier figures 1 to shown in Fig. 3
Embodiment, principle and the example of method, therefore not detailed place in the description of the present embodiment, may refer to the phase in previous embodiment
It speaks on somebody's behalf bright, this will not be repeated here.
Through a large amount of verification experimental verification, using technical solution of the present invention, by utilizing speech recognition, Application on Voiceprint Recognition combination sound
The loudness of sound carrys out the equipment that decision goes out the same instruction of the same sound in subscriber household group in the response same time, can be with
Meet the use demand of user, and avoid multiple devices while responding to interfere, high reliablity, hommization are good.
To sum up, it will be readily appreciated by those skilled in the art that under the premise of not conflicting, above-mentioned each advantageous manner can be certainly
It combined, be superimposed by ground.
The above description is only an embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should be included within scope of the presently claimed invention.
Claims (17)
1. a kind of sound control method characterized by comprising
Obtain the solicited message that one or more equipment is uploaded in the case where receiving voice messaging in the same family group；It is described to ask
Seek information, comprising: audio-frequency information, device parameter and temporal information；
Determine that an equipment in one or more equipment is to response apparatus according at least to the solicited message；
Control should respond the voice messaging to response apparatus.
2. the method according to claim 1, wherein wherein,
The audio-frequency information is that every equipment is believed for the reception of same voice messaging in one or more equipment in the same family group
Breath；And/or
The temporal information, comprising: timestamp.
3. method according to claim 1 or 2, which is characterized in that obtain one or more equipment in the same family group and connecing
The solicited message uploaded in the case where receiving voice messaging, comprising:
The same time obtains one or more equipment is uploaded in the case where receiving same voice messaging in the same family group one
A solicited message of an equipment in a above solicited message.
4. method described in one of -3 according to claim 1, which is characterized in that according at least to the solicited message determine one with
An equipment in upper equipment is to response apparatus, comprising:
Audio-frequency information in one solicited message of one equipment of acquisition of same time is identified, recognition result is obtained；
The record that the recognition result under the same time in family's group whether is stored in the database of setting determined；
If the not stored record for having the recognition result under the same time in family's group, responds the identification knot in the database
The corresponding solicited message of fruit, the corresponding equipment of the recognition result is determined as to response apparatus；
Alternatively, if the record of the recognition result under the same time in family's group is stored in the database, to the family
One or more record of the recognition result carries out Application on Voiceprint Recognition under the same time in group.
5. according to the method described in claim 4, it is characterized in that, determining one or more equipment according at least to the solicited message
In an equipment be to response apparatus, further includes:
Audio-frequency information in a solicited message of the equipment obtained to the same time, which is identified, obtains identification knot
In the case where fruit, the time in the audio-frequency information and its recognition result, the device parameter of this equipment, the solicited message is believed
In the database of the deposit setting of family's group information belonging to breath and this equipment.
6. method according to claim 4 or 5, which is characterized in that the recognition result under the same time in family's group
One or more record carry out Application on Voiceprint Recognition, comprising:
Obtain one or more record of the recognition result under the same time in family's group；
Audio-frequency information to this in one or more record carries out Application on Voiceprint Recognition, to determine the audio-frequency information in one or more record
In corresponding voiceprint, there is several voiceprints voiceprint corresponding with the voice messaging identical；
If having a voiceprint and the voice messaging in the corresponding voiceprint of audio-frequency information in one or more record
Corresponding voiceprint is identical, then the corresponding solicited message of the affiliated recognition result of this voiceprint is responded, by this vocal print
The corresponding equipment of information is determined as to response apparatus；
Alternatively, if having in the corresponding voiceprint of audio-frequency information in this one or more record two or more voiceprints with it is described
The corresponding voiceprint of voice messaging is identical, then carries out sound intensity comparison to two or more the voiceprints.
7. according to the method described in claim 6, it is characterized in that, wherein,
Respond the corresponding solicited message of the recognition result, comprising:
Semantic parsing is carried out to the recognition result, and parsing result is back to this equipment；
And/or
Sound intensity comparison is carried out to two or more the voiceprints, comprising:
Obtain corresponding two of two or more the voiceprints or more record in audio-frequency information sound intensity, and by two with
The corresponding equipment of maximum value in upper sound intensity is determined as to response apparatus.
8. a kind of phonetic controller characterized by comprising
Acquiring unit is asked for obtain that one or more equipment in the same family group uploads in the case where receiving voice messaging
Seek information；The solicited message, comprising: audio-frequency information, device parameter and temporal information；
Control unit, for determining that an equipment in one or more equipment is to set wait respond according at least to the solicited message
It is standby；
Described control unit, the voice messaging should be responded to response apparatus by being also used to control.
9. device according to claim 8, which is characterized in that wherein,
The audio-frequency information is that every equipment is believed for the reception of same voice messaging in one or more equipment in the same family group
Breath；And/or
The temporal information, comprising: timestamp.
10. device according to claim 8 or claim 9, which is characterized in that the acquiring unit obtains in the same family group one
The solicited message that the above equipment is uploaded in the case where receiving voice messaging, comprising:
The same time obtains one or more equipment is uploaded in the case where receiving same voice messaging in the same family group one
A solicited message of an equipment in a above solicited message.
11. the device according to one of claim 8-10, which is characterized in that described control unit is according at least to the request
Information determines that an equipment in one or more equipment is to response apparatus, comprising:
Audio-frequency information in one solicited message of one equipment of acquisition of same time is identified, recognition result is obtained；
The record that the recognition result under the same time in family's group whether is stored in the database of setting determined；
If the not stored record for having the recognition result under the same time in family's group, responds the identification knot in the database
The corresponding solicited message of fruit, the corresponding equipment of the recognition result is determined as to response apparatus；
Alternatively, if the record of the recognition result under the same time in family's group is stored in the database, to the family
One or more record of the recognition result carries out Application on Voiceprint Recognition under the same time in group.
12. device according to claim 11, which is characterized in that described control unit is true according at least to the solicited message
An equipment in fixed one or more equipment is to response apparatus, further includes:
Audio-frequency information in a solicited message of the equipment obtained to the same time, which is identified, obtains identification knot
In the case where fruit, the time in the audio-frequency information and its recognition result, the device parameter of this equipment, the solicited message is believed
In the database of the deposit setting of family's group information belonging to breath and this equipment.
13. device according to claim 11 or 12, which is characterized in that described control unit is to a period of time same in family's group
Between one or more record of the lower recognition result carry out Application on Voiceprint Recognition, comprising:
Obtain one or more record of the recognition result under the same time in family's group；
Audio-frequency information to this in one or more record carries out Application on Voiceprint Recognition, to determine the audio-frequency information in one or more record
In corresponding voiceprint, there is several voiceprints voiceprint corresponding with the voice messaging identical；
If having a voiceprint and the voice messaging in the corresponding voiceprint of audio-frequency information in one or more record
Corresponding voiceprint is identical, then the corresponding solicited message of the affiliated recognition result of this voiceprint is responded, by this vocal print
The corresponding equipment of information is determined as to response apparatus；
Alternatively, if having in the corresponding voiceprint of audio-frequency information in this one or more record two or more voiceprints with it is described
The corresponding voiceprint of voice messaging is identical, then carries out sound intensity comparison to two or more the voiceprints.
14. device according to claim 13, which is characterized in that wherein,
Described control unit responds the corresponding solicited message of the recognition result, comprising:
Semantic parsing is carried out to the recognition result, and parsing result is back to this equipment；
And/or
Described control unit carries out sound intensity comparison to two or more the voiceprints, comprising:
Obtain corresponding two of two or more the voiceprints or more record in audio-frequency information sound intensity, and by two with
The corresponding equipment of maximum value in upper sound intensity is determined as to response apparatus.
15. a kind of control system characterized by comprising the phonetic controller as described in claim 8-14 is any.
16. a kind of storage medium, which is characterized in that be stored with a plurality of instruction in the storage medium；The a plurality of instruction, is used for
It is loaded by processor and executes sound control method as claimed in claim 1.
17. a kind of control system characterized by comprising
Processor, for executing a plurality of instruction；
Memory, for storing a plurality of instruction；
Wherein, a plurality of instruction for being stored by the memory, and is loaded by the processor and is executed such as claim
Any sound control method of 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910085633.XA CN109920416A (en) | 2019-01-29 | 2019-01-29 | A kind of sound control method, device, storage medium and control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910085633.XA CN109920416A (en) | 2019-01-29 | 2019-01-29 | A kind of sound control method, device, storage medium and control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109920416A true CN109920416A (en) | 2019-06-21 |
Family
ID=66961002
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910085633.XA Pending CN109920416A (en) | 2019-01-29 | 2019-01-29 | A kind of sound control method, device, storage medium and control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109920416A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262273A (en) * | 2019-07-12 | 2019-09-20 | 珠海格力电器股份有限公司 | A kind of home equipment control method, device, storage medium and smart home system |
| CN110364153A (en) * | 2019-07-30 | 2019-10-22 | 恒大智慧科技有限公司 | A kind of distributed sound control method, system, computer equipment and storage medium |
| CN110457077A (en) * | 2019-08-09 | 2019-11-15 | 百度在线网络技术（北京）有限公司 | Intelligent Service method, device and equipment |
| CN110515307A (en) * | 2019-08-27 | 2019-11-29 | 珠海格力电器股份有限公司 | A kind of method and the network equipment controlling smart home device |
| CN110660390A (en) * | 2019-09-17 | 2020-01-07 | 百度在线网络技术（北京）有限公司 | Intelligent device wake-up method, intelligent device and computer readable storage medium |
| CN110925944A (en) * | 2019-11-27 | 2020-03-27 | 珠海格力电器股份有限公司 | Control method and control device of air conditioning system and air conditioning system |
| CN114110912A (en) * | 2021-11-08 | 2022-03-01 | 珠海格力电器股份有限公司 | Voice distributed recognition method combined with PLC |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104007678A (en) * | 2014-05-26 | 2014-08-27 | 邯郸美的制冷设备有限公司 | Method, terminal and system for household appliance voice control |
| CN105788599A (en) * | 2016-04-14 | 2016-07-20 | 北京小米移动软件有限公司 | Speech processing method, router and intelligent speech control system |
| CN106357497A (en) * | 2016-11-10 | 2017-01-25 | 北京智能管家科技有限公司 | Control system of intelligent home network |
| CN107564515A (en) * | 2016-06-30 | 2018-01-09 | 广东美的制冷设备有限公司 | Sound control method and system, microphone and server based on multi-microphone |
| CN107622767A (en) * | 2016-07-15 | 2018-01-23 | 青岛海尔智能技术研发有限公司 | The sound control method and appliance control system of appliance system |
| CN108615528A (en) * | 2018-03-30 | 2018-10-02 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
-
2019
- 2019-01-29 CN CN201910085633.XA patent/CN109920416A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104007678A (en) * | 2014-05-26 | 2014-08-27 | 邯郸美的制冷设备有限公司 | Method, terminal and system for household appliance voice control |
| CN105788599A (en) * | 2016-04-14 | 2016-07-20 | 北京小米移动软件有限公司 | Speech processing method, router and intelligent speech control system |
| CN107564515A (en) * | 2016-06-30 | 2018-01-09 | 广东美的制冷设备有限公司 | Sound control method and system, microphone and server based on multi-microphone |
| CN107622767A (en) * | 2016-07-15 | 2018-01-23 | 青岛海尔智能技术研发有限公司 | The sound control method and appliance control system of appliance system |
| CN106357497A (en) * | 2016-11-10 | 2017-01-25 | 北京智能管家科技有限公司 | Control system of intelligent home network |
| CN108615528A (en) * | 2018-03-30 | 2018-10-02 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262273A (en) * | 2019-07-12 | 2019-09-20 | 珠海格力电器股份有限公司 | A kind of home equipment control method, device, storage medium and smart home system |
| CN110364153A (en) * | 2019-07-30 | 2019-10-22 | 恒大智慧科技有限公司 | A kind of distributed sound control method, system, computer equipment and storage medium |
| CN110457077A (en) * | 2019-08-09 | 2019-11-15 | 百度在线网络技术（北京）有限公司 | Intelligent Service method, device and equipment |
| CN110457077B (en) * | 2019-08-09 | 2022-05-17 | 百度在线网络技术（北京）有限公司 | Intelligent service method, device and equipment |
| CN110515307A (en) * | 2019-08-27 | 2019-11-29 | 珠海格力电器股份有限公司 | A kind of method and the network equipment controlling smart home device |
| CN110660390A (en) * | 2019-09-17 | 2020-01-07 | 百度在线网络技术（北京）有限公司 | Intelligent device wake-up method, intelligent device and computer readable storage medium |
| US11330521B2 (en) | 2019-09-17 | 2022-05-10 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method for waking up intelligent device in group wake-up mode, intelligent device and computer-readable storage medium |
| CN110925944A (en) * | 2019-11-27 | 2020-03-27 | 珠海格力电器股份有限公司 | Control method and control device of air conditioning system and air conditioning system |
| CN110925944B (en) * | 2019-11-27 | 2021-02-12 | 珠海格力电器股份有限公司 | Control method and control device of air conditioning system and air conditioning system |
| CN114110912A (en) * | 2021-11-08 | 2022-03-01 | 珠海格力电器股份有限公司 | Voice distributed recognition method combined with PLC |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109920416A (en) | A kind of sound control method, device, storage medium and control system | |
| US20210280172A1 (en) | Voice Response Method and Device, and Smart Device | |
| US10708423B2 (en) | Method and apparatus for processing voice information to determine emotion based on volume and pacing of the voice | |
| JP2020525903A (en) | Managing Privilege by Speaking for Voice Assistant System | |
| WO2016045479A1 (en) | Customer service call processing method and apparatus | |
| CN109712624A (en) | A kind of more voice assistant coordination approach, device and system | |
| CN108922528B (en) | Method and apparatus for processing speech | |
| CN109036374B (en) | Data processing method and device | |
| US11062708B2 (en) | Method and apparatus for dialoguing based on a mood of a user | |
| CN109192208A (en) | A kind of control method of electrical equipment, system, device, equipment and medium | |
| KR102535790B1 (en) | Methods and apparatus for managing holds | |
| CN109417583A (en) | It is a kind of by audio signal real time transcription be text system and method | |
| CN111508491A (en) | Intelligent voice interaction equipment based on deep learning | |
| CN109271503A (en) | Intelligent answer method, apparatus, equipment and storage medium | |
| CN109509468A (en) | A kind of equipment executes the method and device of voice broadcast task | |
| CN109151564A (en) | Apparatus control method and device based on microphone | |
| CN109600703A (en) | Sound reinforcement system and its public address method and computer readable storage medium | |
| CN109101212A (en) | A kind of playback method and system of intelligent sound box | |
| CN108877785A (en) | Speech-sound intelligent housekeeping service system | |
| CN109410942A (en) | A kind of sound control method, device, storage medium and air-conditioning | |
| JP2008011272A5 (en) | ||
| CN112634879B (en) | Voice conference management method, device, equipment and medium | |
| CN115118820A (en) | Call processing method and device, computer equipment and storage medium | |
| CN113132214B (en) | Dialogue method, dialogue device, dialogue server and dialogue storage medium | |
| CN108663942A (en) | A kind of speech recognition apparatus control method, speech recognition apparatus and control server |
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 |