CN108039171A - Sound control method and device - Google Patents
Sound control method and device Download PDFInfo
- Publication number
- CN108039171A CN108039171A CN201810015271.2A CN201810015271A CN108039171A CN 108039171 A CN108039171 A CN 108039171A CN 201810015271 A CN201810015271 A CN 201810015271A CN 108039171 A CN108039171 A CN 108039171A
- Authority
- CN
- China
- Prior art keywords
- air
- control
- conditioning
- control instruction
- natural language
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/34—Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a kind of sound control method and device.Wherein, this method includes:Natural language in air conditioner surroundings is gathered by microphone array, and determines the recognition mode of speech recognition, wherein, recognition mode includes one below:Online recognition pattern and identified off-line pattern;According to definite recognition mode, by instructing identification model, determine for being controlled control instruction corresponding with natural language to air-conditioning, and then air-conditioning is controlled according to definite control instruction, wherein, instruction identification model show that every group of data in multi-group data include using multi-group data by machine learning training:Natural language and control instruction corresponding with the natural language.The present invention solves the technical problem that voice control is not intelligent in correlation technique.
Description
Technical field
The present invention relates to air-conditioning voice control field, in particular to a kind of sound control method and device.
Background technology
Air-conditioning, as one of Modern Family's indispensability electric appliance, occupies more and more important in daily life
Status.Due to the use of frequent, the ease for operation of airconditioning control begins to seem in routine use and is even more important.With television set,
Electric fan is identical, and most of air-conditionings are manipulated in the form of controller, but since controller small volume is easy to be lost,
And then cause user due to can not find controller and can not normal use air-conditioning situation.Meanwhile because air-conditioning widely uses,
The control to air-conditioning is realized more intelligentized application, become further improve user experience important way it
One.
For it is above-mentioned the problem of, not yet propose effective solution at present.
The content of the invention
An embodiment of the present invention provides a kind of sound control method and device, at least to solve voice control in correlation technique
Not intelligent technical problem.
One side according to embodiments of the present invention, there is provided a kind of sound control method, including:Pass through microphone array
Gather the natural language in air conditioner surroundings;Determine the recognition mode of speech recognition, wherein, the recognition mode include it is following it
One:Online recognition pattern and identified off-line pattern;According to the definite recognition mode, by instructing identification model, determine to use
In being controlled control instruction corresponding with the natural language to the air-conditioning, wherein, described instruction identification model is makes
Drawn with multi-group data by machine learning training, every group of data in the multi-group data include:Natural language and with
The corresponding control instruction of the natural language;The air-conditioning is controlled according to the definite control instruction.
Optionally, determining the recognition mode of speech recognition includes:Judge whether can communicate with high in the clouds by network;
In the case where the judgment result is yes, the recognition mode for determining speech recognition is the online recognition pattern;And/or
In the case that judging result is no, the recognition mode for determining speech recognition is the identified off-line pattern.
Optionally, according to the definite recognition mode, by described instruction identification model, determine to be used for the sky
Before adjusting the control instruction corresponding with the natural language being controlled, further include:Sample in the air conditioner surroundings not
Same age, the natural language of different tone colors, and control instruction corresponding with the natural language of sampling;To the natural language of sampling
Speech, and control instruction corresponding with the natural language of sampling are trained, and obtain described instruction identification model.
Optionally, after the natural language in the air conditioner surroundings is gathered, further include:Whether judge the air-conditioning
Open voice control function;In the case where the judgment result is yes, the natural language of collection is segmented
As a result;Judge whether include the predetermined control instruction for being controlled to the air-conditioning in the word segmentation result;Judging
As a result it is that in the case of being, the air-conditioning is controlled using predetermined control instruction.
Optionally, after being controlled according to the definite control instruction to the air-conditioning, further include:Receive and
Instructed from the controller for being controlled to the air-conditioning sent in air-conditioner controller;Judge the scene residing for the air-conditioning
Under, whether the priority of the controller instruction is higher than the control instruction;In the case where the judgment result is yes, according to described in
Controller instruction is controlled the air-conditioning.
Optionally, before being controlled according to the definite control instruction to the air-conditioning, further include:To determining
The control instruction reported;Alternatively, after being controlled according to the definite control instruction to the air-conditioning, also
Including:Control result after being controlled to air-conditioning is reported.
Optionally, before the natural language in air conditioner surroundings is gathered by the microphone array, further include:Connect
Receive wake-up word;The speech recognition that wake-up word wake-up according to receiving includes microphone array and the voice plate is set
It is standby, wherein, the voice plate is used to, according to the definite recognition mode, by instructing identification model, determine to be used for described
The control instruction corresponding with the natural language that air-conditioning is controlled.
Optionally, the air-conditioning is controlled according to the definite control instruction including:In the control instruction category
In the case of the control class for operating control, the control of the control class is carried out to the air-conditioning according to the control instruction
System;In the case where the control instruction belongs to the service class of the service of offer, the air-conditioning is carried out according to the control instruction
The control of the service class;In the case of belonging to the tool-class for providing function instrument in the control instruction, according to the control
Instruct the control that the tool-class is carried out to the air-conditioning.
Optionally, the control class includes at least one of:The air conditioner operation of air conditioner operation is instructed, volume is carried out
The volume control instruction of control, to whether opening the music control instruction of music;The service class includes at least one of:It is right
The broadcasting control instruction that music is controlled, the weather lookup control instruction being controlled to weather lookup, broadcasts news
The news report instruction being controlled is reported, the Tang poetry being controlled is reported to Tang poetry and reports control instruction, children stories are carried out
The children stories broadcast command of report;The tool-class includes at least one of:The time inquiring inquired about the time refers to
Order, to the calculator with calculator using instruction, the word translation instruction translated to word.
Another aspect according to embodiments of the present invention, additionally provides a kind of phonetic controller, including:Acquisition module, is used
Natural language in by microphone array collection air conditioner surroundings;First determining module, for determining the identification of speech recognition
Pattern, wherein, the recognition mode includes one below:Online recognition pattern and identified off-line pattern;Second determining module, is used
According to the definite recognition mode, by instructing identification model, determine for the air-conditioning is controlled with it is described
The corresponding control instruction of natural language, wherein, described instruction identification model is trained by machine learning using multi-group data
Go out, every group of data in the multi-group data include:Natural language and control instruction corresponding with the natural language;First
Control module, for being controlled according to the definite control instruction to the air-conditioning.
In embodiments of the present invention, by the way of voice control, oneself in air conditioner surroundings is gathered by microphone array
Right language, and determine the recognition mode of speech recognition, and then according to definite recognition mode, and instruction identification model, determine to use
In being controlled control instruction corresponding with natural language to air-conditioning, and air-conditioning is controlled according to definite control instruction
System.Wherein, above-mentioned recognition mode includes one below:Online recognition pattern and identified off-line pattern, above-metioned instruction identification model
Show that every group of data in multi-group data include by machine learning training using multi-group data:Natural language and with
The corresponding control instruction of the natural language.By the sound control method in the embodiment of the present invention, having reached that air-conditioning is multi-functional should
Purpose, it is achieved thereby that the technique effect of customer experience is improved, and then it is not intelligent to solve voice control in correlation technique
Technical problem.
Brief description of the drawings
Attached drawing described herein is used for providing a further understanding of the present invention, forms the part of the application, this hair
Bright schematic description and description is used to explain the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of sound control method according to embodiments of the present invention;
Fig. 2 is the structure diagram of phonetic controller according to embodiments of the present invention;
Fig. 3 is the structure diagram of the first determining module 24 of phonetic controller according to embodiments of the present invention;
Fig. 4 is the preferred structure schematic diagram one of phonetic controller according to embodiments of the present invention;
Fig. 5 is the preferred structure schematic diagram two of phonetic controller according to embodiments of the present invention;
Fig. 6 is the preferred structure schematic diagram three of phonetic controller according to embodiments of the present invention;
Fig. 7 is the preferred structure schematic diagram four of phonetic controller according to embodiments of the present invention;
Fig. 8 is the preferred structure schematic diagram five of phonetic controller according to embodiments of the present invention;
Fig. 9 is the preferred structure schematic diagram six of phonetic controller according to embodiments of the present invention;
Figure 10 is the structure diagram of the first control module 28 of phonetic controller according to embodiments of the present invention;
Figure 11 is the voice control implementation schematic diagram of air-conditioning according to the preferred embodiment of the present invention;
Figure 12 is the online speech recognition implementation schematic diagram of air-conditioning according to the preferred embodiment of the present invention;
Figure 13 is the achievable functional schematic of air-conditioning according to the preferred embodiment of the present invention.
Embodiment
In order to make those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Attached drawing, is clearly and completely described the technical solution in the embodiment of the present invention, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
Member's all other embodiments obtained without making creative work, should all belong to the model that the present invention protects
Enclose.
It should be noted that term " first " in description and claims of this specification and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that so use
Data can exchange in the appropriate case, so as to the embodiment of the present invention described herein can with except illustrating herein or
Order beyond those of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, be not necessarily limited to for example, containing the process of series of steps or unit, method, system, product or equipment
Those steps or unit clearly listed, but may include not list clearly or for these processes, method, product
Or the intrinsic other steps of equipment or unit.
According to embodiments of the present invention, there is provided a kind of embodiment of the method for voice control is, it is necessary to illustrate, in attached drawing
The step of flow illustrates can perform in the computer system of such as a group of computer-executable instructions, although also,
Logical order is shown in flow chart, but in some cases, can be to perform shown different from order herein or retouch
The step of stating.
Fig. 1 is the flow chart of sound control method according to embodiments of the present invention, as shown in Figure 1, this method is including as follows
Step:
Step S102, the natural language in air conditioner surroundings is gathered by microphone array;
Step S104, determines the recognition mode of speech recognition, wherein, recognition mode includes one below:Online recognition mould
Formula and identified off-line pattern;
Step S106, according to definite recognition mode, by instructing identification model, determines for being controlled to air-conditioning
Control instruction corresponding with natural language, wherein, instruction identification model is to be drawn using multi-group data by machine learning training
, every group of data in multi-group data include:Natural language and control instruction corresponding with the natural language;
Step S108, is controlled air-conditioning according to definite control instruction.
In embodiments of the present invention, by the way of voice control, oneself in air conditioner surroundings is gathered by microphone array
Right language, and determine the recognition mode of speech recognition, and then according to definite recognition mode, and instruction identification model, determine to use
In being controlled control instruction corresponding with natural language to air-conditioning, and air-conditioning is controlled according to definite control instruction
System.Wherein, above-mentioned recognition mode includes one below:Online recognition pattern and identified off-line pattern, above-metioned instruction identification model
Show that every group of data in multi-group data include by machine learning training using multi-group data:Natural language and with
The corresponding control instruction of the natural language.By the sound control method in the embodiment of the present invention, having reached that air-conditioning is multi-functional should
Purpose, it is achieved thereby that the technique effect of customer experience is improved, and then it is not intelligent to solve voice control in correlation technique
Technical problem.
In view of the characteristics of network aboundresources is easily integrated on line, can pass through online recognition pattern in the embodiment of the present invention
And/or the voice of collection is identified in the mode of identified off-line pattern, and gathers Internet resources and phase is carried out to the demand of client
Should.Preferably, determining the recognition mode of speech recognition can include:Judge whether can communicate with high in the clouds by network;Sentencing
In the case that disconnected result is is, the recognition mode for determining speech recognition is online recognition pattern;And/or in judging result it is no
In the case of, the recognition mode for determining speech recognition is identified off-line pattern.By above-mentioned processing, realize that preferential use passes through net
The voice of collection is identified in the mode in network connection high in the clouds, because high in the clouds aboundresources, therefore, passes through network connection high in the clouds
It is identified, can make it that identification is more accurate;And can not be by network connection high in the clouds when, identified off-line mould can also be passed through
Formula, locally be identified, effectively realize can by network connection to high in the clouds when recognition result it is more accurate, and
Can not by network connection to high in the clouds when, the knowledge of the voice to collecting can be also realized by local identified off-line pattern
Not, effectively prevent can not be by the situation of None- identified during network connection to high in the clouds.
Preferably, according to definite recognition mode, by instructing identification model, determine for being controlled to air-conditioning
Before control instruction corresponding with natural language, it can also include:Sample all ages and classes in air conditioner surroundings, the nature of different tone colors
Language, and control instruction corresponding with the natural language of sampling;To the natural language of sampling, and the natural language with sampling
Corresponding control instruction is trained, and obtains instruction identification model.By to the different ages, the natural language of different tone colors,
And the corresponding control instruction of natural language of corresponding sampling is trained, and can cause the instruction identification model trained more
It is abundant, completely, so that it is more accurate in the recognition result identified using the instruction identification model, effectively improve user's body
Test.
For above-mentioned preferred embodiment, training data can be obtained by experiment, a large amount of by what is counted early period
Data, abundant model has been pre-established using machine learning, determines the airconditioning control instruction representated by various natural languages, and then
Corresponding control is made to air-conditioning.Can also be that the air-conditioning for widely applying the sound control method constantly gathers in use
Accumulation is reported to high in the clouds, can be with so as to obtain substantial amounts of data by being tracked to the air-conditioning sold away
For training.Optionally, the data collected in real time can be uploaded to high in the clouds with above-mentioned communication module, multiple air-conditionings, with
Train and use for machine.
Alternatively, to realize different control to different crowds, or realize some cannot be allowed to perform what is controlled
Personnel limit control air-conditioning, can determine for before being controlled control instruction corresponding with natural language to air-conditioning,
Determine the user identity of the corresponding user of voice of collection;In the case where the user identity of user is guardian, according to definite
Recognition mode, by instructing identification model, determine that the natural language of collection is identified.Pass through the use of the voice to collection
The judgement of the identity at family, determines whether the user possesses the authority by voice control electric appliance.If for example, voice pair of collection
Should in the case of children, set do not perform collection children voice control instruction, on the one hand it is possible to prevente effectively from operation
Insecurity, and the intentional or unintentional maloperation of children is effectively avoided to a certain extent.
Meanwhile because different geographical language tone color respectively has feature, different language modes can also be set, wherein, it is different
Language mode can be using region accent as distinctive elements, such as Sichuan words pattern, Hunan words pattern, Guangdong language pattern, Tibetan language pattern, Shanghai
Language pattern, mandarin pattern etc., to adapt to the speech habits of different geographical user;Can also using different language as distinctive elements,
Such as English mode, Japanese language mode, Hangul mode, German pattern, to meet the needs of the user of common foreign language exchange.
Optionally, after the natural language in collection air conditioner surroundings, can also include:Judge whether air-conditioning opens voice
Control function;In the case where the judgment result is yes, the natural language of collection is segmented to obtain word segmentation result;Judge participle
As a result the predetermined control instruction for being controlled to air-conditioning whether is included in;In the case where the judgment result is yes, use
Predetermined control instruction is controlled air-conditioning.Set by above-mentioned participle behavior, the speech recognition to user can be made finer
With it is comprehensive, can also realize and be instructed by setting section predetermined control, the vocabulary in natural language is directly judged, is such as contained
The predetermined control instruction of setting, then be controlled direct air-conditioning using predetermined control instruction, this is equivalent to natural language air-conditioning
The quick passage of control, you can by can be by a manner of the identification of different control instructions, implementing quick control to air-conditioning.
It is accustomed to according to the airconditioning control of different user, can also be excellent by setting natural language control and controller to control
First level, carries out air-conditioning the control of different mode.Preferably, after being controlled according to definite control instruction to air-conditioning,
It can also include:Receive come from that air-conditioner controller sends for the controller instruction that is controlled to air-conditioning;Judge empty
Adjust under residing scene, whether the priority of controller instruction is higher than control instruction;In the case where the judgment result is yes, foundation
Controller instruction is controlled air-conditioning.I.e. after airconditioning control is carried out according to the natural language of collection, control is such as received again
The control instruction of device, only controller instruction priority be higher than control instruction in the case of, just further according to controller instruct into
Row running state of air conditioner adjusts, and otherwise running state of air conditioner not adjusts, still the control program to be indicated in natural language.Pass through
Aforesaid operations, have effectively achieved the purpose of flexibly control air-conditioning.It should be noted that natural language control and controller control
Priority to set can be fixed setting when dispatching from the factory, or voluntarily set by user preferences and custom.
Speech recognition situation is grasped for ease of user, it is preferred that air-conditioning can carried out according to definite control instruction
Before control, further include:The control instruction determined is reported;Alternatively, can also be according to definite control instruction pair
After air-conditioning is controlled, further include:Control result after being controlled to air-conditioning is reported.It is alternatively possible to performing
Corresponding report sets the regular hour, for example, (the example in the predetermined amount of time that definite control instruction is controlled air-conditioning
Such as, 1-2 seconds), perform broadcast operation.By reporting the operation content in speech control process, user can not only be played and carried
It is shown as using, and in the case where speech recognition is wrong, user can have found mistake in time and send again correctly meet
The control instruction of demand.
Preferably, before the natural language in air conditioner surroundings is gathered by microphone array, further include:Receive wake-up
Word;Being waken up according to the wake-up word received includes the speech recognition apparatus of microphone array and voice plate, wherein, voice plate is used for
According to definite recognition mode, by instructing identification model, determine corresponding with natural language for being controlled to air-conditioning
Control instruction.Word is waken up by setting, can effectively avoid the speech recognition apparatus length for including microphone array and voice plate
Time it is in running order and increase power consumption and cut down service life the drawbacks of.Wherein, it can be that air-conditioning is manufactured to wake up word
When be fixedly installed, or voluntarily set during user's use.
By the way that by the connection of air-conditioning and high in the clouds, above-mentioned air-conditioning can both identify that various control instructed, can also obtain online
Much information resource meet the multiclass demand of user.Optionally, air-conditioning is controlled according to definite control instruction can be with
Including:In the case where control instruction belongs to the control class for operating control, class is controlled to air-conditioning according to control instruction
Control;In the case where control instruction belongs to the service class of the service of offer, service class is carried out to air-conditioning according to control instruction
Control;In the case of belonging to the tool-class that function instrument is provided in control instruction, tool-class is carried out to air-conditioning according to control instruction
Control.
Preferably, above-mentioned control class can include at least one of:The air conditioner operation of air conditioner operation is instructed, to volume
The volume control instruction being controlled, to whether opening the music control instruction of music;Above-mentioned service class can include with down toward
It is one of few:The broadcasting control instruction being controlled to music, the weather lookup control instruction being controlled to weather lookup,
The news report instruction being controlled to news report, reports Tang poetry the Tang poetry being controlled and reports control instruction, to children
The children stories broadcast command that story is reported;Above-mentioned tool-class can include at least one of:Time is inquired about
Time inquiring instruction, to calculator calculator using instruction, word is translated word translation instruction.
It is pointed out that above-mentioned control class, the content included by service class and tool-class is used only for illustrating, not
Only include the example above, the function that can be realized on air-conditioning or effect can be belonging respectively to above-mentioned classification.
Another aspect according to embodiments of the present invention, additionally provides a kind of phonetic controller, Fig. 2 is according to this hair
The structure diagram of the phonetic controller of bright embodiment, as shown in Fig. 2, the phonetic controller includes:Acquisition module 22, the
One determining module 24, the second determining module 26, the first control module 28.The phonetic controller is described in detail below.
Acquisition module 22, for gathering the natural language in air conditioner surroundings by microphone array;
First determining module 24, is connected to above-mentioned acquisition module 22, for determining the recognition mode of speech recognition, wherein,
Recognition mode includes one below:Online recognition pattern and identified off-line pattern;
Second determining module 26, is connected to above-mentioned first determining module 24, for according to definite recognition mode, passing through finger
Identification model is made, is determined for being controlled control instruction corresponding with natural language to air-conditioning, wherein, instruct identification model
Show that every group of data in multi-group data include by machine learning training using multi-group data:Natural language and with
The corresponding control instruction of the natural language;
First control module 28, is connected to above-mentioned second determining module 26, and the control instruction definite for basis is to air-conditioning
It is controlled.
Fig. 3 is the structure diagram of the first determining module 24 of phonetic controller according to embodiments of the present invention, such as Fig. 3
Shown, which includes:Judging unit 32, determination unit 34.First determining module 24 is carried out in detail below
Describe in detail bright.
Judging unit 32, for judging whether can communicate with high in the clouds by network;
Determination unit 34, is connected to above-mentioned judging unit 32, in the case where the judgment result is yes, determining that voice is known
Other recognition mode is online recognition pattern;And/or in the case where judging result is no, determine the identification mould of speech recognition
Formula is identified off-line pattern.
Fig. 4 is the preferred structure schematic diagram one of phonetic controller according to embodiments of the present invention, as shown in figure 4, the language
Sound control device in addition to all structures, is further included in containing Fig. 2:Sampling module 42, training module 44.The voice control is filled below
Put and be described in detail.
Sampling module 42, for according to definite recognition mode, by instructing identification model, determine to be used for air-conditioning into
Before the control instruction corresponding with natural language of row control, all ages and classes in air conditioner surroundings, the natural language of different tone colors are sampled
Speech, and control instruction corresponding with the natural language of sampling;
Training module 44, is connected to above-mentioned 42 and second determining module 26 of sampling module, for the natural language to sampling,
And control instruction corresponding with the natural language of sampling is trained, instruction identification model is obtained.
Fig. 5 is the preferred structure schematic diagram two of phonetic controller according to embodiments of the present invention, as shown in figure 5, the language
Sound control device in addition to all structures, is further included in containing Fig. 2:First judgment module 52, word-dividing mode 54, the second judgment module
56, the second control module 58.The phonetic controller is described in detail below.
First judgment module 52, is connected to above-mentioned acquisition module 22, for collection air conditioner surroundings in natural language it
Afterwards, judge whether air-conditioning opens voice control function;
Word-dividing mode 54, is connected to above-mentioned first judgment module 52, in the case where the judgment result is yes, to collection
Natural language segmented to obtain word segmentation result;
Whether the second judgment module 56, is connected to above-mentioned word-dividing mode 54, be used for for judging to include in word segmentation result
The predetermined control instruction being controlled to air-conditioning;
Second control module 58, is connected to above-mentioned second judgment module 56, in the case where the judgment result is yes, adopting
Air-conditioning is controlled with predetermined control instruction.
Fig. 6 is the preferred structure schematic diagram three of phonetic controller according to embodiments of the present invention, as shown in fig. 6, the language
Sound control device in addition to all structures, is further included in containing Fig. 2:Receiving module 62, the 3rd judgment module 64, the 3rd control module
66.The phonetic controller is described in detail below.
Receiving module 62, is connected to above-mentioned first control module 28, for according to definite control instruction to air-conditioning into
After row control, receive and come from the controller for being used to be controlled air-conditioning that air-conditioner controller sends and instruct;
3rd judgment module 64, is connected to above-mentioned receiving module 62, for judging under the scene residing for air-conditioning, controller refers to
Whether the priority of order is higher than control instruction;
3rd control module 66, is connected to above-mentioned 3rd judgment module 64, in the case where the judgment result is yes, according to
Air-conditioning is controlled according to controller instruction.
Fig. 7 is the preferred structure schematic diagram four of phonetic controller according to embodiments of the present invention, as shown in fig. 7, the language
Sound control device in addition to all structures, is further included in containing Fig. 2:First broadcasting module 72.The phonetic controller is carried out below
Describe in detail.
First broadcasting module 72, is connected to above-mentioned second determining module, 26 and first control module 28, for according to really
Before fixed control instruction is controlled air-conditioning, the control instruction determined is reported.
Fig. 8 is the preferred structure schematic diagram five of phonetic controller according to embodiments of the present invention, as shown in figure 8, the language
Sound control device in addition to all structures, is further included in containing Fig. 2:Second broadcasting module 82.The phonetic controller is carried out below
Describe in detail.
Second broadcasting module 82, is connected to above-mentioned first control module 28, for according to definite control instruction to sky
After tune is controlled, the control result after being controlled to air-conditioning is reported.
Fig. 9 is the preferred structure schematic diagram six of phonetic controller according to embodiments of the present invention, as shown in figure 9, the language
Sound control device in addition to all structures, is further included in containing Fig. 2:Wake up word receiving module 92, wake-up module 94.Below to the voice
Control device is described in detail.
Word receiving module 92 is waken up, for before the natural language in air conditioner surroundings is gathered by microphone array, connecing
Receive wake-up word;
Wake-up module 94, is connected to above-mentioned wake-up word receiving module 92 and acquisition module 22, for being called out according to what is received
Word of waking up wakes up the speech recognition apparatus for including microphone array and voice plate, wherein, voice plate is used for according to definite identification mould
Formula, by instructing identification model, determines for being controlled control instruction corresponding with natural language to air-conditioning.
Figure 10 is the structure diagram of the first control module 28 of phonetic controller according to embodiments of the present invention, is such as schemed
Shown in 10, which includes:First control unit 102, the second control unit 104, the 3rd control unit 106.
First control module 28 is described in detail below.
First control unit 102, in the case of belonging to the control class for operating control in control instruction, according to control
System instruction is controlled air-conditioning the control of class;
Second control unit 104, in the case of belonging to the service class for providing and servicing in control instruction, refers to according to control
Make the control that service class is carried out to air-conditioning;
3rd control unit 106, in the case of belonging to the tool-class for providing function instrument in control instruction, according to control
System instruction carries out air-conditioning the control of tool-class.
Wherein, control class includes at least one of:The air conditioner operation of air conditioner operation is instructed, volume is controlled
Volume control instructs, to whether opening the music control instruction of music;Service class includes at least one of:To music into
The broadcasting control instruction of row control, the weather lookup control instruction being controlled to weather lookup, is controlled news report
News report instruction, the Tang poetry that is controlled is reported to Tang poetry and reports control instruction, the children reported to children stories
Story broadcast command;Tool-class includes at least one of:The time inquiring instruction inquired about the time, to calculator
Calculator using instruction, word is translated word translation instruction.
Another aspect according to embodiments of the present invention, additionally provides a kind of air-conditioning, wherein, which can include upper
State any one phonetic controller.Figure 11 is that the voice control implementation of air-conditioning according to the preferred embodiment of the present invention is shown
It is intended to, as shown in figure 11, the speech recognition system included in the air-conditioning (can be 2 microphone arrays or 2 wheats by microphone array
Gram wind above array), loudspeaker, voice module composition.Wherein microphone array is used for the order word for receiving user's identification;Voice
Module is used to receive, handle phonetic order, and sends instructions to air-conditioning master control;Air-conditioning master control is used to after receiving order control accordingly
Function, such as pattern, switching on and shutting down.
Figure 12 is the online speech recognition implementation schematic diagram of air-conditioning according to the preferred embodiment of the present invention, such as Figure 12
Shown, which realizes that online Multifunctional speech controls by the information exchange of voice module and third-party server.Figure 13 is
The achievable functional schematic of air-conditioning according to the preferred embodiment of the present invention, as shown in figure 13, the air-conditioning can be realized online
Song is played, tells a story, look into the functions such as weather, translation, calculating, while, it is necessary to illustrate, only work(can be achieved in part in figure
Can, also having other, more details are not described herein for achievable function.
Optionally, partial service class control mode can be realized as follows:
1st, music reports control:Under human-computer interaction state, user can use the mode for saying order word to interact, and say
Order has relevant prompting after about 1-2 seconds, such as【It please appreciate the lustily water of Liu De China】, commenced play out after the completion of prompt tone report
The music of buffering;If without other effective orders, speech recognition can be again introduced into after 15 seconds and treat during song is played
Wake-up states, do not embody the prompt tone for exiting identification【Too】, need to wake up air-conditioning again as music need to be continuing with, and
Say recognition command word;
2nd, weather lookup controls:After word wake-up voice is waken up, user says【How is Beijing weather today】Afterwards, voice plate
The audio of relative clean can be sent into high in the clouds to be identified, after correctly identifying word, be sent into semantic understanding engine, parse
It is the intention for inquiring about weather, backstage can be formatted as a result, by place at this time【Beijing】, the time【Today】Obtained Deng keyword, with
Carry out weather content search after, weather description information is returned into voice plate with the data formatted, it is normal more than
In the case of, it after voice plate is parsed, can be reported using phonetic synthesis, relevant prompting is had after about 1-2 seconds and is reported.
3rd, children stories control:After word wake-up voice plate is waken up, microphone array can carry out noise reduction at this time, echo disappears
Remove, the processing such as wave beam pickup, user says order【I will listen the story of Andersen】Afterwards, voice plate can be by the audio of relative clean
Be sent into high in the clouds be identified, after correctly identifying word, be sent into semantic understanding engine in, parse be story program request intention,
Backstage can be formatted as a result, the keywords such as author " Andersen " are obtained at this time.After carrying out story content search therewith, by story
Link, story description information return to voice plate with the data formatted.In the case of above flow is normal, voice plate carries out
After parsing, start side buffer edge and play corresponding audio in network resources address URL (Uniform Resource Locator)
Stream.
Under the normal man-machine interaction mode, user can use to be interacted with upper type, says program request order about 1-2
Relevant prompting is had after second;If without other effective orders, voice can be again introduced into after 15 seconds and treat in playing process
Wake-up states, need to such as continue language manipulation needs to wake up again, and says voice command.Meanwhile it can be kept into when waking up
Broadcast state, the head that finishes playing can play next automatically later, until list finishes playing.
Meanwhile network can not connect or abnormal conditions under, which can automatically switch to the identification of offline local voice
Pattern carries out voice control.
Another aspect according to embodiments of the present invention, additionally provides a kind of storage medium, which includes storage
Program, wherein, equipment performs the sound control method of above-mentioned any one where controlling storage medium when program is run.
Another aspect according to embodiments of the present invention, additionally provides a kind of processor, which is used for operation program, its
In, program performs the sound control method of above-mentioned any one when running.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
In the above embodiment of the present invention, the description to each embodiment all emphasizes particularly on different fields, and does not have in some embodiment
The part of detailed description, may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed technology contents, can pass through others
Mode is realized.Wherein, device embodiment described above is only schematical, such as the division of the unit, Ke Yiwei
A kind of division of logic function, can there is an other dividing mode when actually realizing, for example, multiple units or component can combine or
Person is desirably integrated into another system, or some features can be ignored, or does not perform.Another, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, unit or module
Connect, can be electrical or other forms.
The unit illustrated as separating component may or may not be physically separate, be shown as unit
The component shown may or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On unit.Some or all of unit therein can be selected to realize the purpose of this embodiment scheme according to the actual needs.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part to contribute in other words to the prior art or all or part of the technical solution can be in the form of software products
Embody, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or network equipment etc.) perform each embodiment the method for the present invention whole or
Part steps.And foregoing storage medium includes:USB flash disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can be with store program codes
Medium.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (10)
- A kind of 1. sound control method, it is characterised in that including:Natural language in air conditioner surroundings is gathered by microphone array;Determine the recognition mode of speech recognition, wherein, the recognition mode includes one below:Online recognition pattern and offline knowledge Other pattern;According to the definite recognition mode, by instructing identification model, determine for being controlled to the air-conditioning and institute The corresponding control instruction of natural language is stated, wherein, described instruction identification model is to be trained using multi-group data by machine learning Draw, every group of data in the multi-group data include:Natural language and control instruction corresponding with the natural language;The air-conditioning is controlled according to the definite control instruction.
- 2. according to the method described in claim 1, it is characterized in that, determining the recognition mode of speech recognition includes:Judge whether can communicate with high in the clouds by network;In the case where the judgment result is yes, the recognition mode for determining speech recognition is the online recognition pattern;With/ Or, in the case where judging result is no, the recognition mode for determining speech recognition is the identified off-line pattern.
- 3. according to the method described in claim 1, it is characterized in that, according to the definite recognition mode, pass through the finger Identification model is made, is determined for before being controlled the control instruction corresponding with the natural language to the air-conditioning, Further include:Sample all ages and classes in the air conditioner surroundings, the natural language of different tone colors, and it is corresponding with the natural language of sampling Control instruction;To the natural language of sampling, and control instruction corresponding with the natural language of sampling is trained, and obtains described instruction Identification model.
- 4. according to the method described in claim 1, it is characterized in that, gather the natural language in the air conditioner surroundings it Afterwards, further include:Judge whether the air-conditioning opens voice control function;In the case where the judgment result is yes, the natural language of collection is segmented to obtain word segmentation result;Judge whether include the predetermined control instruction for being controlled to the air-conditioning in the word segmentation result;In the case where the judgment result is yes, the air-conditioning is controlled using predetermined control instruction.
- 5. according to the method described in claim 1, it is characterized in that, according to the definite control instruction to the air-conditioning into After row control, further include:Receive come from that air-conditioner controller sends for the controller instruction that is controlled to the air-conditioning;Judge under the scene residing for the air-conditioning, whether the priority of the controller instruction is higher than the control instruction;In the case where the judgment result is yes, the air-conditioning is controlled according to controller instruction.
- 6. according to the method described in claim 1, it is characterized in that,Before being controlled according to the definite control instruction to the air-conditioning, further include:The control to determining Instruction is reported;Alternatively,After being controlled according to the definite control instruction to the air-conditioning, further include:After being controlled to air-conditioning Control result is reported.
- 7. according to the method described in claim 1, it is characterized in that, gathered by the microphone array in air conditioner surroundings Before the natural language, further include:Receive wake-up word;Being waken up according to the wake-up word received includes the speech recognition apparatus of microphone array and the voice plate, wherein, The voice plate is used to, according to the definite recognition mode, by instructing identification model, determine to be used to carry out the air-conditioning The control instruction corresponding with the natural language of control.
- 8. method according to any one of claim 1 to 7, it is characterised in that according to the definite control instruction pair The air-conditioning be controlled including:In the case where the control instruction belongs to the control class for operating control, according to the control instruction to the air-conditioning Carry out the control of the control class;In the case where the control instruction belongs to the service class of the service of offer, the air-conditioning is carried out according to the control instruction The control of the service class;In the case of belonging to the tool-class for providing function instrument in the control instruction, according to the control instruction to the air-conditioning Carry out the control of the tool-class.
- 9. according to the method described in claim 8, it is characterized in that,The control class includes at least one of:The air conditioner operation of air conditioner operation is instructed, the volume being controlled to volume Control instruction, to whether opening the music control instruction of music;The service class includes at least one of:The broadcasting control instruction being controlled to music, to weather lookup into The weather lookup control instruction of row control, the news report instruction being controlled to news report, reports Tang poetry and is controlled Tang poetry report control instruction, the children stories broadcast command that children stories are reported;The tool-class includes at least one of:The time inquiring instruction inquired about the time, to the meter with calculator Device is calculated using instruction, the word translation instruction translated to word.
- A kind of 10. phonetic controller, it is characterised in that including:Acquisition module, for gathering the natural language in air conditioner surroundings by microphone array;First determining module, for determining the recognition mode of speech recognition, wherein, the recognition mode includes one below: Line recognition mode and identified off-line pattern;Second determining module, for according to the definite recognition mode, by instructing identification model, determining to be used for the sky The control instruction corresponding with the natural language being controlled is adjusted, wherein, described instruction identification model is to use multi-group data Drawn by machine learning training, every group of data in the multi-group data include:Natural language and with the natural language Corresponding control instruction;First control module, for being controlled according to the definite control instruction to the air-conditioning.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810015271.2A CN108039171A (en) | 2018-01-08 | 2018-01-08 | Sound control method and device |
PCT/CN2018/118963 WO2019134474A1 (en) | 2018-01-08 | 2018-12-03 | Voice control method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810015271.2A CN108039171A (en) | 2018-01-08 | 2018-01-08 | Sound control method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108039171A true CN108039171A (en) | 2018-05-15 |
Family
ID=62099323
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810015271.2A Pending CN108039171A (en) | 2018-01-08 | 2018-01-08 | Sound control method and device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108039171A (en) |
WO (1) | WO2019134474A1 (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109102873A (en) * | 2018-05-31 | 2018-12-28 | 上海联影医疗科技有限公司 | C-arm equipment and its training method, device, Medical Imaging System and storage medium |
CN109147782A (en) * | 2018-09-04 | 2019-01-04 | 深圳国美云智科技有限公司 | Control method, device and the air-conditioning of air-conditioning |
CN109469967A (en) * | 2018-09-29 | 2019-03-15 | 佛山市中格威电子有限公司 | A kind of air-conditioning system with child custody mode |
CN109949802A (en) * | 2019-01-25 | 2019-06-28 | 广州灵聚信息科技有限公司 | It is a kind of from the NLP system and its working method unified online, device |
WO2019134474A1 (en) * | 2018-01-08 | 2019-07-11 | 珠海格力电器股份有限公司 | Voice control method and device |
CN110030704A (en) * | 2019-05-20 | 2019-07-19 | 珠海格力电器股份有限公司 | Control method, device, storage medium and the air-conditioning of air-conditioning |
CN110108008A (en) * | 2019-05-20 | 2019-08-09 | 珠海格力电器股份有限公司 | Control method, device and the air-conditioning of voice air conditioner light |
CN110543129A (en) * | 2019-09-30 | 2019-12-06 | 深圳市酷开网络科技有限公司 | intelligent electric appliance control method, intelligent electric appliance control system and storage medium |
CN110570850A (en) * | 2019-07-30 | 2019-12-13 | 珠海格力电器股份有限公司 | Voice control method, device, computer equipment and storage medium |
WO2020048296A1 (en) * | 2018-09-05 | 2020-03-12 | 深圳追一科技有限公司 | Machine learning method and device, and storage medium |
CN110941188A (en) * | 2018-09-25 | 2020-03-31 | 珠海格力电器股份有限公司 | Intelligent household control method and device |
CN111475206A (en) * | 2019-01-04 | 2020-07-31 | 优奈柯恩(北京)科技有限公司 | Method and apparatus for waking up wearable device |
CN111493868A (en) * | 2019-01-30 | 2020-08-07 | 西门子医疗有限公司 | System for performing magnetic resonance tomography and method of controlling an MR scanner |
CN111883126A (en) * | 2020-07-27 | 2020-11-03 | 珠海格力电器股份有限公司 | Data processing mode selection method and device and electronic equipment |
CN112306355A (en) * | 2019-07-24 | 2021-02-02 | 北京迪文科技有限公司 | Display device and method supporting voice recognition |
CN112634902A (en) * | 2020-12-11 | 2021-04-09 | 天津讯飞极智科技有限公司 | Voice transcription method, device, recording pen and storage medium |
CN112735414A (en) * | 2020-12-25 | 2021-04-30 | 肯特智能技术(深圳)股份有限公司 | Online and offline dual-mode voice control method and system and storage medium |
CN113053369A (en) * | 2019-12-26 | 2021-06-29 | 青岛海尔空调器有限总公司 | Voice control method and device of intelligent household appliance and intelligent household appliance |
CN113744743A (en) * | 2021-08-27 | 2021-12-03 | 海信(山东)冰箱有限公司 | Voice interaction method and device for washing machine |
US11937964B2 (en) | 2018-05-31 | 2024-03-26 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for controlling an X-ray imaging device |
CN117784632A (en) * | 2024-02-28 | 2024-03-29 | 深圳市轻生活科技有限公司 | Intelligent household control system based on offline voice recognition |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1997188A (en) * | 2006-01-06 | 2007-07-11 | 乐金电子(中国)研究开发中心有限公司 | A recognition method of the user identity and its handset |
CN201129826Y (en) * | 2007-11-20 | 2008-10-08 | 珠海格力电器股份有限公司 | Air conditioner control device |
CN101794120A (en) * | 2010-02-09 | 2010-08-04 | 张文中 | Voice control system used for fuzzy control of household appliances |
CN103187055A (en) * | 2011-12-28 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Data processing system based on vehicle-mounted application |
CN103281223A (en) * | 2013-05-15 | 2013-09-04 | 五邑大学 | Modernized intelligent home security system |
US8554559B1 (en) * | 2012-07-13 | 2013-10-08 | Google Inc. | Localized speech recognition with offload |
CN104882142A (en) * | 2015-04-30 | 2015-09-02 | 大连楼兰科技股份有限公司 | Voice control method and apparatus for vehicle device based on OBD interface |
CN105700372A (en) * | 2016-03-11 | 2016-06-22 | 珠海格力电器股份有限公司 | Intelligent device and control method thereof |
CN106926818A (en) * | 2016-11-21 | 2017-07-07 | 德阳九鼎智远知识产权运营有限公司 | A kind of intelligent automobile with memory function |
CN107120791A (en) * | 2017-04-27 | 2017-09-01 | 珠海格力电器股份有限公司 | A kind of air conditioning control method, device and air conditioner |
CN107424607A (en) * | 2017-07-04 | 2017-12-01 | 珠海格力电器股份有限公司 | Voice command mode switching method, device and the equipment with the device |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3726871B2 (en) * | 1999-05-27 | 2005-12-14 | 日本電気株式会社 | Device operating system and device operating method |
CN103292437B (en) * | 2013-06-17 | 2016-01-20 | 广东美的制冷设备有限公司 | Voice interactive air conditioner and control method thereof |
CN104916283A (en) * | 2015-06-11 | 2015-09-16 | 百度在线网络技术(北京)有限公司 | Voice recognition method and device |
CN105202721B (en) * | 2015-07-31 | 2018-05-11 | 广东美的制冷设备有限公司 | Air conditioner and its control method |
CN107464567A (en) * | 2017-07-24 | 2017-12-12 | 深圳云知声信息技术有限公司 | Audio recognition method and device |
CN108039171A (en) * | 2018-01-08 | 2018-05-15 | 珠海格力电器股份有限公司 | Sound control method and device |
-
2018
- 2018-01-08 CN CN201810015271.2A patent/CN108039171A/en active Pending
- 2018-12-03 WO PCT/CN2018/118963 patent/WO2019134474A1/en active Application Filing
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1997188A (en) * | 2006-01-06 | 2007-07-11 | 乐金电子(中国)研究开发中心有限公司 | A recognition method of the user identity and its handset |
CN201129826Y (en) * | 2007-11-20 | 2008-10-08 | 珠海格力电器股份有限公司 | Air conditioner control device |
CN101794120A (en) * | 2010-02-09 | 2010-08-04 | 张文中 | Voice control system used for fuzzy control of household appliances |
CN103187055A (en) * | 2011-12-28 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Data processing system based on vehicle-mounted application |
US8554559B1 (en) * | 2012-07-13 | 2013-10-08 | Google Inc. | Localized speech recognition with offload |
CN103281223A (en) * | 2013-05-15 | 2013-09-04 | 五邑大学 | Modernized intelligent home security system |
CN104882142A (en) * | 2015-04-30 | 2015-09-02 | 大连楼兰科技股份有限公司 | Voice control method and apparatus for vehicle device based on OBD interface |
CN105700372A (en) * | 2016-03-11 | 2016-06-22 | 珠海格力电器股份有限公司 | Intelligent device and control method thereof |
CN106926818A (en) * | 2016-11-21 | 2017-07-07 | 德阳九鼎智远知识产权运营有限公司 | A kind of intelligent automobile with memory function |
CN107120791A (en) * | 2017-04-27 | 2017-09-01 | 珠海格力电器股份有限公司 | A kind of air conditioning control method, device and air conditioner |
CN107424607A (en) * | 2017-07-04 | 2017-12-01 | 珠海格力电器股份有限公司 | Voice command mode switching method, device and the equipment with the device |
Non-Patent Citations (2)
Title |
---|
赵杰: "《搜索引擎技术》", 30 November 2007, 哈尔滨工程大学出版社 * |
马慧彬: "《基于机器学习的乳腺图像辅助诊断算法研究》", 31 August 2016 * |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019134474A1 (en) * | 2018-01-08 | 2019-07-11 | 珠海格力电器股份有限公司 | Voice control method and device |
CN109102873A (en) * | 2018-05-31 | 2018-12-28 | 上海联影医疗科技有限公司 | C-arm equipment and its training method, device, Medical Imaging System and storage medium |
US11937964B2 (en) | 2018-05-31 | 2024-03-26 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for controlling an X-ray imaging device |
CN109147782A (en) * | 2018-09-04 | 2019-01-04 | 深圳国美云智科技有限公司 | Control method, device and the air-conditioning of air-conditioning |
WO2020048296A1 (en) * | 2018-09-05 | 2020-03-12 | 深圳追一科技有限公司 | Machine learning method and device, and storage medium |
CN110941188A (en) * | 2018-09-25 | 2020-03-31 | 珠海格力电器股份有限公司 | Intelligent household control method and device |
CN109469967A (en) * | 2018-09-29 | 2019-03-15 | 佛山市中格威电子有限公司 | A kind of air-conditioning system with child custody mode |
CN111475206A (en) * | 2019-01-04 | 2020-07-31 | 优奈柯恩(北京)科技有限公司 | Method and apparatus for waking up wearable device |
CN109949802A (en) * | 2019-01-25 | 2019-06-28 | 广州灵聚信息科技有限公司 | It is a kind of from the NLP system and its working method unified online, device |
CN111493868A (en) * | 2019-01-30 | 2020-08-07 | 西门子医疗有限公司 | System for performing magnetic resonance tomography and method of controlling an MR scanner |
CN110030704A (en) * | 2019-05-20 | 2019-07-19 | 珠海格力电器股份有限公司 | Control method, device, storage medium and the air-conditioning of air-conditioning |
CN110108008A (en) * | 2019-05-20 | 2019-08-09 | 珠海格力电器股份有限公司 | Control method, device and the air-conditioning of voice air conditioner light |
CN112306355A (en) * | 2019-07-24 | 2021-02-02 | 北京迪文科技有限公司 | Display device and method supporting voice recognition |
CN110570850A (en) * | 2019-07-30 | 2019-12-13 | 珠海格力电器股份有限公司 | Voice control method, device, computer equipment and storage medium |
CN110543129A (en) * | 2019-09-30 | 2019-12-06 | 深圳市酷开网络科技有限公司 | intelligent electric appliance control method, intelligent electric appliance control system and storage medium |
CN113053369A (en) * | 2019-12-26 | 2021-06-29 | 青岛海尔空调器有限总公司 | Voice control method and device of intelligent household appliance and intelligent household appliance |
CN111883126A (en) * | 2020-07-27 | 2020-11-03 | 珠海格力电器股份有限公司 | Data processing mode selection method and device and electronic equipment |
CN112634902A (en) * | 2020-12-11 | 2021-04-09 | 天津讯飞极智科技有限公司 | Voice transcription method, device, recording pen and storage medium |
CN112735414A (en) * | 2020-12-25 | 2021-04-30 | 肯特智能技术(深圳)股份有限公司 | Online and offline dual-mode voice control method and system and storage medium |
CN113744743A (en) * | 2021-08-27 | 2021-12-03 | 海信(山东)冰箱有限公司 | Voice interaction method and device for washing machine |
CN113744743B (en) * | 2021-08-27 | 2022-11-08 | 海信冰箱有限公司 | Voice interaction method and device for washing machine |
CN117784632A (en) * | 2024-02-28 | 2024-03-29 | 深圳市轻生活科技有限公司 | Intelligent household control system based on offline voice recognition |
Also Published As
Publication number | Publication date |
---|---|
WO2019134474A1 (en) | 2019-07-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108039171A (en) | Sound control method and device | |
CN209310172U (en) | Air purifier with voice control function | |
CN104575504A (en) | Method for personalized television voice wake-up by voiceprint and voice identification | |
CN103700370A (en) | Broadcast television voice recognition method and system | |
CN107135443A (en) | A kind of signal processing method and electronic equipment | |
CN108320753A (en) | Control method, the device and system of electrical equipment | |
CN109493849A (en) | Voice awakening method, device and electronic equipment | |
CN107767861A (en) | voice awakening method, system and intelligent terminal | |
CN105304081A (en) | Smart household voice broadcasting system and voice broadcasting method | |
CN109147782A (en) | Control method, device and the air-conditioning of air-conditioning | |
CN105244026A (en) | Voice processing method and device | |
CN104731549A (en) | Voice recognition man-machine interaction device based on mouse and method thereof | |
CN111145721A (en) | Personalized prompt language generation method, device and equipment | |
CN112002315B (en) | Voice control method and device, electrical equipment, storage medium and processor | |
CN109741735A (en) | The acquisition methods and device of a kind of modeling method, acoustic model | |
CN108053023A (en) | A kind of self-action intent classifier method and device | |
CN110399315A (en) | A kind of processing method of voice broadcast, device, terminal device and storage medium | |
CN105588287A (en) | Control method and system of intelligent music air conditioner | |
CN112669838A (en) | Intelligent sound box audio playing method and device, electronic equipment and storage medium | |
CN111787168A (en) | Voice recognition quality inspection allocation method based on artificial intelligence technology | |
CN109377993A (en) | Intelligent voice system and its voice awakening method and intelligent sound equipment | |
CN112242135A (en) | Voice data processing method and intelligent customer service device | |
CN112735423B (en) | Voice interaction method and device, electronic equipment and storage medium | |
CN107180629B (en) | Voice acquisition and recognition method and system | |
CN109918502A (en) | Document explains method, apparatus, computer installation and computer readable storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180515 |
|
RJ01 | Rejection of invention patent application after publication |