CN109410936A - Air-conditioning equipment sound control method and device based on scene - Google Patents
Air-conditioning equipment sound control method and device based on scene Download PDFInfo
- Publication number
- CN109410936A CN109410936A CN201811350509.3A CN201811350509A CN109410936A CN 109410936 A CN109410936 A CN 109410936A CN 201811350509 A CN201811350509 A CN 201811350509A CN 109410936 A CN109410936 A CN 109410936A
- Authority
- CN
- China
- Prior art keywords
- scene
- air
- conditioning equipment
- instruction
- word
- 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
- 238000004378 air conditioning Methods 0.000 title claims abstract description 96
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012549 training Methods 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims 1
- 238000005266 casting Methods 0.000 abstract description 23
- 230000000694 effects Effects 0.000 abstract description 14
- 230000007423 decrease Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 230000002618 waking effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/52—Indication arrangements, e.g. displays
- F24F11/526—Indication arrangements, e.g. displays giving audible indications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/56—Remote control
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
- G10L2015/228—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of application context
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The present invention proposes a kind of air-conditioning equipment sound control method and device based on scene, wherein, method includes: the scene image that acquisition air-conditioning equipment is presently in when recognizing the wake-up word of user's input, and scene type is determined according to scene image, target scene line off instruction model identification voice messaging corresponding with scene type is called when receiving the voice messaging of user's input within a preset time, the broadcasting control parameter of corresponding with instruction word feedback corpus and air-conditioning equipment is obtained when identifying that voice messaging is to instruct word, feedback corpus is played according to control parameter is played.Thus, the ambient noise that solving air-conditioning equipment in the prior art can not adapt under several scenes changes, and cause to instruct the decline of word recognition effect, and the technical issues of can not being fed back for the flexible casting under several scenes, instruction word recognition effect is improved, realizes and carries out different casting content and casting volume under different scenes.
Description
Technical field
The present invention relates to air-conditioning equipment control technology field more particularly to a kind of air-conditioning equipment voice controls based on scene
Method and apparatus.
Background technique
With the fast development of artificial intelligence technology, the household appliance for having speech identifying function is also more and more, greatly
The interaction and experience for improving user and household appliance.
In the related technology, the speech recognition system of an air-conditioning equipment generally only adapts to some scene (such as domestic environment)
Use.If it instructs word discrimination that can decreased significantly when changing to other scenes, the reduction of user experience is caused.Moreover,
The casting of the speech recognition system, which feeds back one edition, to be set for a certain special scenes, including broadcasting the content of feedback and broadcasting
Report volume etc. all has been cured, and lacks flexibility in actual use.
Summary of the invention
The present invention provides a kind of air-conditioning equipment sound control method and device based on scene, for solving air-conditioning equipment
The ambient noise variation under several scenes can not be adapted to, and causes to instruct the decline of word recognition effect, and can not be directed to a variety of
The technical issues of flexible casting under scene is fed back.
One aspect of the present invention embodiment provides a kind of air-conditioning equipment sound control method based on scene, comprising:
When the wake-up word for recognizing user's input, then the scene image that air-conditioning equipment is presently in is acquired, and according to described
Scene image determines scene type;
If receiving the voice messaging of user's input within a preset time, target corresponding with the scene type is called
Scene line off instruction model identifies the voice messaging, when identifying that the voice messaging is instruction word, then obtains and described instruction
The broadcasting control parameter of the corresponding feedback corpus and the air-conditioning equipment of word;
The feedback corpus is played according to the broadcasting control parameter.
Another aspect of the present invention embodiment provides a kind of air-conditioning equipment phonetic controller based on scene, comprising:
Identification module is waken up, for when the wake-up word for recognizing user's input, then acquiring the field that air-conditioning equipment is presently in
Scape image;
Scene Recognition module, for determining scene type according to the scene image;
Application schedules module, if for receive within a preset time user input voice messaging, call with it is described
The corresponding target scene line off instruction model of scene type identifies the voice messaging, when the identification voice messaging is instruction
Word then obtains the broadcasting control parameter of corresponding with described instruction word feedback corpus and the air-conditioning equipment;
Voice playing module, for playing the feedback corpus according to the broadcasting control parameter.
Another aspect of the invention embodiment provides a kind of air-conditioning equipment, including memory, processor and is stored in memory
Computer program that is upper and can running on a processor, when the processor executes the computer program, realizes such as above-mentioned reality
Apply the air-conditioning equipment sound control method described in example based on scene.
Further aspect of the present invention embodiment provides a kind of non-transitorycomputer readable storage medium, is stored thereon with calculating
Machine program realizes the air-conditioning equipment language based on scene as described in above-described embodiment when the computer program is executed by processor
Sound controlling method.
Technical solution of the present invention at least realizes following beneficial technical effect:
The scene image that acquisition air-conditioning equipment is presently in when recognizing the wake-up word of user's input, and according to scene figure
As determining scene type, target corresponding with scene type is called when receiving the voice messaging of user's input within a preset time
Scene line off instruction model identifies voice messaging, and backchannel corresponding with instruction word is obtained when identifying that voice messaging is instruction word
The broadcasting control parameter of material and air-conditioning equipment plays feedback corpus according to control parameter is played.It solves as a result, in the prior art
Air-conditioning equipment can not adapt to the variation of the ambient noise under several scenes, and cause to instruct the decline of word recognition effect, and can not
The technical issues of feeding back for the flexible casting under several scenes, by scene Recognition, calling is applicable under different noise scenes
Target scene line off instruction model carries out instruction word identification, improves instruction word recognition effect, carries out under realization different scenes different
Casting content and casting volume.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is a kind of process signal of the air-conditioning equipment sound control method based on scene provided by the embodiment of the present invention
Figure;
Fig. 2 is that the process of air-conditioning equipment sound control method of the another kind based on scene provided by the embodiment of the present invention is shown
It is intended to;
Fig. 3 is the application scenarios of the air-conditioning equipment sound control method based on scene of one embodiment according to the present invention
Schematic diagram;
Fig. 4 is the structural representation of the air-conditioning equipment phonetic controller according to an embodiment of the invention based on scene
Figure;
Fig. 5 is the structural representation of the air-conditioning equipment phonetic controller in accordance with another embodiment of the present invention based on scene
Figure;
Fig. 6 is the structural representation of the air-conditioning equipment phonetic controller based on scene of another embodiment according to the present invention
Figure;And
Fig. 7 is the structural representation of the air-conditioning equipment phonetic controller based on scene of further embodiment according to the present invention
Figure.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings the air-conditioning equipment sound control method and device based on scene of the embodiment of the present invention are described.Its
In, air-conditioning equipment includes air-conditioning, fan, refrigeration machine etc..
The air-conditioning equipment being previously mentioned in technology based on the above background can not adapt to the variation of the ambient noise under several scenes, and
The technical issues of causing to instruct the decline of word recognition effect, and can not being fed back for the flexible casting under several scenes, this hair
It is bright to provide through scene Recognition, it calls the target scene line off instruction model being applicable under different noise scenes to carry out instruction word and knows
Not, and in the present invention, word recognition effect can be instructed thus, it is possible to improve for the flexible casting feedback under several scenes,
It realizes and carries out different casting content and casting volume under different scenes.
Fig. 1 is a kind of process signal of the air-conditioning equipment sound control method based on scene provided by the embodiment of the present invention
Figure.As shown in Figure 1, this method comprises:
Step 101, when the wake-up word for recognizing user's input, then the scene image that air-conditioning equipment is presently in is acquired, and
Scene type is determined according to scene image.
Specifically, point for waking up word and instructing word is had in air-conditioning equipment voice control, can be used by waking up word model
In identifying corresponding wake-up word, after air-conditioning equipment powers on, can enter to wake-up states, it, can be with the considerations of for lower power consumption
Operation is corresponding to wake up word model, waits user to bark out wake-up word and carries out air-conditioning equipment wake-up.Wherein it is possible to there is one or more
Wake up word.
It is understood that when the wake-up word for recognizing user's input, then air-conditioning equipment has been waken up, while by such as
The scene image that the equipment such as ultra high-definition camera acquisition air-conditioning equipment is presently in, is then determined by the identification to scene image
Scene type.Wherein, scene type can be household scene, sales field scene etc..
It illustrates as a kind of scene, under household scene, user, which barks out air-conditioning equipment, to be waken up word and be identified as correctly
After waking up word, the scene image that air-conditioning equipment is presently in is obtained, carries out the corresponding scene type of scene image Recognition feedback
For household scene.
It should be noted that the scene background noise that air-conditioning equipment is presently in can also be acquired, and obtain scene background
The corresponding wake-up model trained in advance of noise, and word is waken up by wake-up model identification trained in advance.
It is understood that scene background noise under available different scenes trains wake-up model, i.e., it is different
Scene background noise corresponds to different wake-up models trained in advance.
In embodiments of the present invention, in order to improve the wake-up rate under several scenes noise, need to obtain a variety of different fields
The wake up instruction sample training collection of recording under scape carries out noise training according to wake up instruction sample training collection and generates training in advance
Wake-up model.It wakes up in the training process of model and needle is carried out using the wake up instruction sample training collection recorded under several scenes
It makes an uproar training to property band.
In embodiments of the present invention, scene type can also be determined according to scene image and scene background noise, as one
Kind scene citing, obtains the scene image that air-conditioning equipment is presently in, and carries out the corresponding scene type of scene image Recognition feedback
For household scene, while determining that scene type is household scene according to scene background noise, it is determined that air-conditioning equipment is presently in
Scene be household scene;It illustrates as another scene, obtains the scene image that air-conditioning equipment is presently in, carry out scene figure
The picture corresponding scene type of Recognition feedback is household scene, while determining that scene type is sales field according to scene background noise
Scape, then according to preset screening strategy, such as using the scene type of scene image identification as preference policies, it is determined that air-conditioning
The scene that equipment is presently in is household scene.
Step 102, it if receiving the voice messaging of user's input within a preset time, calls corresponding with scene type
Target scene line off instruction model identifies voice messaging, and when identification voice messaging is instruction word, then acquisition is corresponding with instruction word
Feed back the broadcasting control parameter of corpus and air-conditioning equipment.
Step 103, feedback corpus is played according to broadcasting control parameter.
In embodiments of the present invention, it in order to improve the instruction word recognition effect under several scenes noise, needs to obtain more
The phonetic order sample training collection of recording under kind different scenes carries out noise training according to phonetic order sample training collection and generates
Multiple target scene line off instruction models.
Specifically, different scene types corresponds to different target scene line off instruction models, it is therefore desirable to training in advance
Multiple target scene line off instruction models, these target scene line off instruction models be based on depth recognition technology, target scene from
Line model uses the phonetic order sample training collection recorded under several scenes to carry out specific aim band in the training process and makes an uproar instruction
Practice, the voice messaging identification being adapted under different noise scenarios.In entry instruction word identification state, the voice letter of user is responded
Breath.
It should be noted that can be based on the target scene line off instruction model that the training of different scenes noise obtains identical
Instruction word, be also possible to identify different instruction word.
Specifically, it after recognizing the voice messaging of user in target scene line off instruction model as instruction word, can obtain
The broadcasting control parameter of corresponding with instruction word feedback corpus and air-conditioning equipment, and backchannel is played according to control parameter is played
Material.
Therefore, several scenes can be directed to, by carrying out scene Recognition, call the target field being applicable under different noise scenes
Scape line off instruction model carries out instruction word identification, both may be implemented to bring consistent recognition effect to user under different scenes,
Also it may be implemented to carry out perhaps broadcasting volume output under different scenes in different castings.
Such as under household scene, realize casting volume can for medium volume, and air conditioner be placed on sales field or
When museum shows, the automatic casting for realizing max volume.
It is understood that can have identical, there can also be different feedback corpus such as to broadcast content, and casting
Broadcasting control parameter such as volume setting, tone color setting etc..
It should be noted that can not only execute the combination casting of recording file, it is also possible to based on offline speech synthesis
The real-time voice of engine synthesizes casting.
In embodiments of the present invention, if not acquiring the scene image that air-conditioning equipment is presently in, preset mesh is called
It marks scene line off instruction model and identifies voice messaging.
In embodiments of the present invention, if being not received by the voice messaging of user's input within a preset time, sky is controlled
Equipment is adjusted to enter to awakening mode, to reduce power consumption.That is, after air-conditioning equipment is waken up, target scene line off instruction mould
The voice messaging that type waits user further to input can switch back into automatically if being more than the waiting time and wake up word model.
It is understood that current scene can not be recognized, or be more than the waiting time, preset mesh can be called immediately
Mark scene line off instruction model namely defaults the target scene line off instruction model under scene, entry instruction word recognition mode.
To in entry instruction word recognition mode, start simultaneously at timing (for example being 15 seconds), user is waited to input voice letter
Breath, if the voice messaging that user does not input in 15 seconds, exit instruction word recognition mode calls and wakes up word model, returns
To waiting awakening mode.
In embodiments of the present invention, as shown in Fig. 2, after step 103, further includes:
Step 201, the operating parameter of air-conditioning equipment corresponding with instruction word is obtained.
Step 202, air-conditioning equipment work is controlled according to operating parameter.
Specifically, in instruction word recognition mode when, receive user input voice messaging, and by with scene
When the corresponding target scene line off instruction model identification of type is real instruction word, the instruction word is parsed, is obtained and instruction word
Operating parameter of corresponding air-conditioning equipment, such as temperature, wind direction etc. control air-conditioning equipment work according to operating parameter, such as
Refrigeration, heating, pendulum wind etc..Further increase the flexibility of air-conditioning equipment control.
In order to more clearly describe the air-conditioning equipment sound control method based on scene of the embodiment of the present invention, tie below
Specifically application scenarios are closed to illustrate, as shown in Figure 3:
Contained in the air-conditioning equipment voice control single microphone voice input source and offline speech recognition system, and
Loudspeaker.
Specifically, it when the wake-up word for recognizing user's input by wake-up model trained in advance, is then taken the photograph by ultra high-definition
Determine that scene type is household scene as the scene image A that head acquisition air-conditioning equipment is presently in, and according to scene image A;Or
Person acquires the scene image B that air-conditioning equipment is presently in by ultra high-definition camera, and determines scene type according to scene image B
For sales field scene;Or the scene image C that air-conditioning equipment is presently in is acquired by ultra high-definition camera, and according to scene image
C determines that scene type is museum's scene.
Then the voice messaging of user's input is received within a preset time, then is called corresponding with scene type household scene
Household scene line off instruction model identify voice messaging;Or call sales field corresponding with scene type sales field scene scene from
Line model identifies voice messaging;Or museum's scene line off instruction model corresponding with scene type museum scene is called to know
Other voice messaging.
It it should be noted that if can not identify scene type after receiving the wake-up word that user inputs, or is more than to wait
Time can call the target scene line off instruction model under default scene, into line off instruction word recognition mode immediately.
To in the voice messaging for receiving user's input, and by calling household scene line off instruction model either
Sales field scene line off instruction model either museum's scene line off instruction model, identifies whether the instruction word for being, if instruction word,
The instruction word is then parsed, casting feedback and corresponding movement output are executed.
Specifically, if the air-conditioning equipment is placed under sales field or museum's scene as displaying model machine, after being waken up,
Receiving determining scene type is sales field/museum's scene, can call sales field/museum's scene line off instruction model, entry instruction word
Recognition mode.Corresponding sales field/museum's scene, ambient background noise can be very noisy, corresponding to sell under such acoustic environment
Field/museum's scene line off instruction model ensured with instruction word discrimination consistent in household scene, while it is anti-broadcast
When feedback, broadcasting control parameter can be automatically adjusted, for example setting max volume is broadcasted, and is realized clearer under noisy environment
Sound feedback improves interactive experience.
To sum up, the air-conditioning equipment sound control method based on scene of the embodiment of the present invention, when calling out by training in advance
The scene image that acquisition air-conditioning equipment is presently in when awake model recognizes the wake-up word of user's input, and it is true according to scene image
Determine scene type, calls target scene corresponding with scene type when receiving the voice messaging of user's input within a preset time
Line off instruction model identifies voice messaging, obtained when identifying that voice messaging is instruction word with instruct the corresponding feedback corpus of word and
The broadcasting control parameter of air-conditioning equipment plays feedback corpus according to control parameter is played.Solves air-conditioning in the prior art as a result,
Equipment can not adapt to the variation of the ambient noise under several scenes, and cause to instruct the decline of word recognition effect, and can not be directed to
The technical issues of flexible casting under several scenes is fed back calls the target being applicable under different noise scenes by scene Recognition
Scene line off instruction model carries out instruction word identification, improves instruction word recognition effect, realizes and carries out different broadcast under different scenes
Report content and casting volume.
In order to realize above-described embodiment, the invention also provides a kind of air-conditioning equipment phonetic controller based on scene,
Fig. 4 is the structural schematic diagram of the air-conditioning equipment phonetic controller according to an embodiment of the invention based on scene, such as Fig. 4 institute
Show, being somebody's turn to do the air-conditioning equipment phonetic controller based on scene includes: to wake up identification module 10, scene Recognition module 20, using tune
Spend module 30 and voice playing module 40.
Wherein, scene Recognition module 10, for determining scene type according to scene image.
Application schedules module 20, if the voice messaging for receiving user's input within a preset time, calling and field
The corresponding target scene line off instruction model of scape type identifies voice messaging, when identification voice messaging is instruction word, then obtain with
Instruct the broadcasting control parameter of the corresponding feedback corpus and air-conditioning equipment of word.
Voice playing module 30, for playing feedback corpus according to broadcasting control parameter.
In one embodiment of the invention, the scene background noise that acquisition air-conditioning equipment is presently in obtains scene back
The corresponding wake-up model trained in advance of scape noise wakes up word by wake-up model identification trained in advance.
In one embodiment of the invention, scene Recognition module 10 is also used to be made an uproar according to scene image and scene background
Sound determines scene type.
In one embodiment of the invention, as shown in figure 5, on the basis of as shown in Figure 4, further includes: work output
Module 50.
Wherein, application schedules module 30 is also used to obtain the operating parameter of air-conditioning equipment corresponding with instruction word.
Work output module 50, for controlling air-conditioning equipment work according to operating parameter.
In one embodiment of the invention, as shown in fig. 6, on the basis of as shown in Figure 4, first obtains 60 He of module
First training module 70.
Wherein, first module 60 is obtained, for obtaining the wake up instruction sample training collection of the recording under a variety of different scenes.
First training module 70 generates calling out for training in advance for carrying out noise training according to wake up instruction sample training collection
Awake model.
In one embodiment of the invention, as shown in fig. 7, on the basis of as shown in Figure 4, second obtains 80 He of module
Second training module 90.
Wherein, the second acquisition module 80 is used to obtain the phonetic order sample training collection of the recording under a variety of different scenes.
Second training module 90 generates multiple target scenes for carrying out noise training according to phonetic order sample training collection
Line off instruction model.
In one embodiment of the invention, if scene Recognition module 10 does not acquire the scene that air-conditioning equipment is presently in
Image then calls preset target scene line off instruction model identification voice messaging.
It should be noted that the explanation of the aforementioned air-conditioning equipment sound control method embodiment concentrated on based on scene
It is also applied for the air-conditioning equipment phonetic controller based on scene of the embodiment of the present invention, realization principle is similar, herein no longer
It repeats.
To sum up, the air-conditioning equipment phonetic controller based on scene of the embodiment of the present invention, when calling out by training in advance
The scene image that acquisition air-conditioning equipment is presently in when awake model recognizes the wake-up word of user's input, and it is true according to scene image
Determine scene type, calls target scene corresponding with scene type when receiving the voice messaging of user's input within a preset time
Line off instruction model identifies voice messaging, obtained when identifying that voice messaging is instruction word with instruct the corresponding feedback corpus of word and
The broadcasting control parameter of air-conditioning equipment plays feedback corpus according to control parameter is played.Solves air-conditioning in the prior art as a result,
Equipment can not adapt to the variation of the ambient noise under several scenes, and cause to instruct the decline of word recognition effect, and can not be directed to
The technical issues of flexible casting under several scenes is fed back calls the target being applicable under different noise scenes by scene Recognition
Scene line off instruction model carries out instruction word identification, improves instruction word recognition effect, realizes and carries out different broadcast under different scenes
Report content and casting volume.
In order to realize above-described embodiment, the invention also provides a kind of air-conditioning equipments, including memory, processor and storage
On a memory and the computer program that can run on a processor, it when the processor executes the computer program, realizes
Air-conditioning equipment sound control method based on scene as in the foregoing embodiment.
In order to realize above-described embodiment, the invention also provides a kind of non-transitorycomputer readable storage mediums, thereon
It is stored with computer program, is realized when the computer program is executed by processor as in the foregoing embodiment based on scene
Air-conditioning equipment sound control method.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or N number of embodiment or example.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present invention, " N number of " is meant that at least two, such as two, three
Deng unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
One or it is more N number of for realizing custom logic function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: being electrically connected with one or N number of wiring
Socket part (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory (ROM),
Erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk read-only storage
(CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other suitable Jie
Matter, because can then be edited, be interpreted or when necessary with other for example by carrying out optical scanner to paper or other media
Suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that N number of step or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.Such as, if realized with hardware in another embodiment, following skill well known in the art can be used
Any one of art or their combination are realized: have for data-signal is realized the logic gates of logic function from
Logic circuit is dissipated, the specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene can compile
Journey gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above
The embodiment of the present invention is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as to limit of the invention
System, those skilled in the art can be changed above-described embodiment, modify, replace and become within the scope of the invention
Type.
Claims (10)
1. a kind of air-conditioning equipment sound control method based on scene, which comprises the following steps:
When the wake-up word for recognizing user's input, then the scene image that air-conditioning equipment is presently in is acquired, and according to the scene
Image determines scene type;
If receiving the voice messaging of user's input within a preset time, target scene corresponding with the scene type is called
Line off instruction model identifies the voice messaging, when identifying that the voice messaging is instruction word, then obtains and described instruction word pair
The broadcasting control parameter of the feedback corpus and the air-conditioning equipment answered;
The feedback corpus is played according to the broadcasting control parameter.
2. the method as described in claim 1, which is characterized in that before the wake-up word of identification user's input, further includes:
The scene background noise that acquisition air-conditioning equipment is presently in obtains calling out for the corresponding training in advance of the scene background noise
Awake model;
The wake-up word is identified by the wake-up model trained in advance;
3. method according to claim 2, which is characterized in that described to determine scene type according to the scene image, comprising:
The scene type is determined according to the scene image and the scene background noise.
4. the method as described in claim 1, which is characterized in that further include:
Obtain the operating parameter of the air-conditioning equipment corresponding with described instruction word;
The air-conditioning equipment work is controlled according to the operating parameter.
5. method according to claim 2, which is characterized in that further include:
Obtain the wake up instruction sample training collection of the recording under a variety of different scenes;
Noise training, which is carried out, according to the wake up instruction sample training collection generates the wake-up model trained in advance.
6. the method as described in claim 1, which is characterized in that further include:
Obtain the phonetic order sample training collection of the recording under a variety of different scenes;
Noise training, which is carried out, according to the phonetic order sample training collection generates multiple target scene line off instruction models.
7. the method as described in claim 1, which is characterized in that further include:
If being not received by the voice messaging of user's input within a preset time, the air-conditioning equipment is controlled into mould to be waken up
Formula.
8. a kind of air-conditioning equipment phonetic controller based on scene characterized by comprising
Identification module is waken up, for recognizing the wake-up word of user's input when the wake-up model by training in advance, then acquires sky
The scene image for adjusting equipment to be presently in;
Scene Recognition module, for determining scene type according to the scene image;
Application schedules module is called and the scene if the voice messaging for receiving user's input within a preset time
The corresponding target scene line off instruction model of type identifies the voice messaging, when identifying that the voice messaging is instruction word, then
Obtain the broadcasting control parameter of corresponding with described instruction word feedback corpus and the air-conditioning equipment;
Voice playing module, for playing the feedback corpus according to the broadcasting control parameter.
9. a kind of air-conditioning equipment, which is characterized in that on a memory and can be on a processor including memory, processor and storage
The computer program of operation when the processor executes the computer program, is realized as described in any in claim 1-7
Air-conditioning equipment sound control method based on scene.
10. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the meter
The air-conditioning equipment voice control based on scene as described in any in claim 1-7 is realized when calculation machine program is executed by processor
Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811350509.3A CN109410936A (en) | 2018-11-14 | 2018-11-14 | Air-conditioning equipment sound control method and device based on scene |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811350509.3A CN109410936A (en) | 2018-11-14 | 2018-11-14 | Air-conditioning equipment sound control method and device based on scene |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109410936A true CN109410936A (en) | 2019-03-01 |
Family
ID=65473263
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811350509.3A Pending CN109410936A (en) | 2018-11-14 | 2018-11-14 | Air-conditioning equipment sound control method and device based on scene |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109410936A (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110047487A (en) * | 2019-06-05 | 2019-07-23 | 广州小鹏汽车科技有限公司 | Awakening method, device, vehicle and the machine readable media of vehicle-mounted voice equipment |
CN110379421A (en) * | 2019-04-03 | 2019-10-25 | 深圳市尚可饰科技有限公司 | A kind of dialect phonetic AI control method, device and terminal |
CN110486910A (en) * | 2019-08-19 | 2019-11-22 | 珠海格力电器股份有限公司 | Air conditioning control method, device and air-conditioning system based on region keyword |
CN110515449A (en) * | 2019-08-30 | 2019-11-29 | 北京安云世纪科技有限公司 | Wake up the method and device of smart machine |
CN110544468A (en) * | 2019-08-23 | 2019-12-06 | Oppo广东移动通信有限公司 | Application awakening method and device, storage medium and electronic equipment |
CN110569913A (en) * | 2019-09-11 | 2019-12-13 | 北京云迹科技有限公司 | Scene classifier training method and device, scene recognition method and robot |
CN110808030A (en) * | 2019-11-22 | 2020-02-18 | 珠海格力电器股份有限公司 | Voice awakening method, system, storage medium and electronic equipment |
CN111081254A (en) * | 2019-12-26 | 2020-04-28 | 苏州思必驰信息科技有限公司 | Voice recognition method and device |
CN111951787A (en) * | 2020-07-31 | 2020-11-17 | 北京小米松果电子有限公司 | Voice output method, device, storage medium and electronic equipment |
CN112201222A (en) * | 2020-12-03 | 2021-01-08 | 深圳追一科技有限公司 | Voice interaction method, device, equipment and storage medium based on voice call |
CN112235168A (en) * | 2019-06-28 | 2021-01-15 | 广东美的制冷设备有限公司 | Household appliance and reminding method and device thereof |
CN112309399A (en) * | 2020-10-30 | 2021-02-02 | 上海淇玥信息技术有限公司 | Method and device for executing task based on voice and electronic equipment |
CN112786055A (en) * | 2020-12-25 | 2021-05-11 | 北京百度网讯科技有限公司 | Resource mounting method, device, equipment, storage medium and computer program product |
CN112787899A (en) * | 2021-01-08 | 2021-05-11 | 青岛海尔特种电冰箱有限公司 | Equipment voice interaction method, computer readable storage medium and refrigerator |
CN112802470A (en) * | 2020-12-30 | 2021-05-14 | 厦门市美亚柏科信息股份有限公司 | Offline voice control method and terminal |
CN113362821A (en) * | 2021-05-31 | 2021-09-07 | 东风商用车有限公司 | Control method, device and equipment of air suspension and storage medium |
CN113450795A (en) * | 2021-06-28 | 2021-09-28 | 深圳七号家园信息技术有限公司 | Image recognition method and system with voice awakening function |
CN113534780A (en) * | 2021-06-21 | 2021-10-22 | 上汽通用五菱汽车股份有限公司 | Remote control parking parameter and function definition method, automobile and readable storage medium |
CN113763942A (en) * | 2020-06-03 | 2021-12-07 | 广东美的制冷设备有限公司 | Interaction method and interaction system of voice household appliances and computer equipment |
CN114023305A (en) * | 2021-11-26 | 2022-02-08 | 北京百度网讯科技有限公司 | Instruction scheduling method and device based on voice and electronic equipment |
CN114120979A (en) * | 2022-01-25 | 2022-03-01 | 荣耀终端有限公司 | Optimization method, training method, device and medium of voice recognition model |
WO2023279746A1 (en) * | 2021-07-05 | 2023-01-12 | 青岛海尔空调器有限总公司 | Method, system and apparatus for switching timbre of air conditioner, electronic device, and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105009204A (en) * | 2012-12-11 | 2015-10-28 | 亚马逊技术有限公司 | Speech recognition power management |
CN105448292A (en) * | 2014-08-19 | 2016-03-30 | 北京羽扇智信息科技有限公司 | Scene-based real-time voice recognition system and method |
CN108257596A (en) * | 2017-12-22 | 2018-07-06 | 北京小蓦机器人技术有限公司 | It is a kind of to be used to provide the method and apparatus that information is presented in target |
CN108564948A (en) * | 2018-03-30 | 2018-09-21 | 联想(北京)有限公司 | A kind of audio recognition method and electronic equipment |
US20180293983A1 (en) * | 2017-04-06 | 2018-10-11 | Samsung Electronics Co., Ltd. | Method and electronic device for providing contents based on natural language understanding |
CN108810739A (en) * | 2018-05-22 | 2018-11-13 | 出门问问信息科技有限公司 | A kind of speech playing method and device, storage medium, electronic equipment |
-
2018
- 2018-11-14 CN CN201811350509.3A patent/CN109410936A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105009204A (en) * | 2012-12-11 | 2015-10-28 | 亚马逊技术有限公司 | Speech recognition power management |
CN105448292A (en) * | 2014-08-19 | 2016-03-30 | 北京羽扇智信息科技有限公司 | Scene-based real-time voice recognition system and method |
US20180293983A1 (en) * | 2017-04-06 | 2018-10-11 | Samsung Electronics Co., Ltd. | Method and electronic device for providing contents based on natural language understanding |
CN108257596A (en) * | 2017-12-22 | 2018-07-06 | 北京小蓦机器人技术有限公司 | It is a kind of to be used to provide the method and apparatus that information is presented in target |
CN108564948A (en) * | 2018-03-30 | 2018-09-21 | 联想(北京)有限公司 | A kind of audio recognition method and electronic equipment |
CN108810739A (en) * | 2018-05-22 | 2018-11-13 | 出门问问信息科技有限公司 | A kind of speech playing method and device, storage medium, electronic equipment |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110379421A (en) * | 2019-04-03 | 2019-10-25 | 深圳市尚可饰科技有限公司 | A kind of dialect phonetic AI control method, device and terminal |
CN110047487A (en) * | 2019-06-05 | 2019-07-23 | 广州小鹏汽车科技有限公司 | Awakening method, device, vehicle and the machine readable media of vehicle-mounted voice equipment |
CN112235168A (en) * | 2019-06-28 | 2021-01-15 | 广东美的制冷设备有限公司 | Household appliance and reminding method and device thereof |
CN110486910A (en) * | 2019-08-19 | 2019-11-22 | 珠海格力电器股份有限公司 | Air conditioning control method, device and air-conditioning system based on region keyword |
CN110544468A (en) * | 2019-08-23 | 2019-12-06 | Oppo广东移动通信有限公司 | Application awakening method and device, storage medium and electronic equipment |
CN110515449A (en) * | 2019-08-30 | 2019-11-29 | 北京安云世纪科技有限公司 | Wake up the method and device of smart machine |
CN110515449B (en) * | 2019-08-30 | 2021-06-04 | 北京安云世纪科技有限公司 | Method and device for awakening intelligent equipment |
CN110569913A (en) * | 2019-09-11 | 2019-12-13 | 北京云迹科技有限公司 | Scene classifier training method and device, scene recognition method and robot |
CN110808030A (en) * | 2019-11-22 | 2020-02-18 | 珠海格力电器股份有限公司 | Voice awakening method, system, storage medium and electronic equipment |
CN110808030B (en) * | 2019-11-22 | 2021-01-22 | 珠海格力电器股份有限公司 | Voice awakening method, system, storage medium and electronic equipment |
CN111081254A (en) * | 2019-12-26 | 2020-04-28 | 苏州思必驰信息科技有限公司 | Voice recognition method and device |
CN113763942A (en) * | 2020-06-03 | 2021-12-07 | 广东美的制冷设备有限公司 | Interaction method and interaction system of voice household appliances and computer equipment |
CN111951787A (en) * | 2020-07-31 | 2020-11-17 | 北京小米松果电子有限公司 | Voice output method, device, storage medium and electronic equipment |
CN112309399A (en) * | 2020-10-30 | 2021-02-02 | 上海淇玥信息技术有限公司 | Method and device for executing task based on voice and electronic equipment |
CN112201222B (en) * | 2020-12-03 | 2021-04-06 | 深圳追一科技有限公司 | Voice interaction method, device, equipment and storage medium based on voice call |
CN112201222A (en) * | 2020-12-03 | 2021-01-08 | 深圳追一科技有限公司 | Voice interaction method, device, equipment and storage medium based on voice call |
CN112786055A (en) * | 2020-12-25 | 2021-05-11 | 北京百度网讯科技有限公司 | Resource mounting method, device, equipment, storage medium and computer program product |
CN112802470A (en) * | 2020-12-30 | 2021-05-14 | 厦门市美亚柏科信息股份有限公司 | Offline voice control method and terminal |
CN112787899A (en) * | 2021-01-08 | 2021-05-11 | 青岛海尔特种电冰箱有限公司 | Equipment voice interaction method, computer readable storage medium and refrigerator |
CN112787899B (en) * | 2021-01-08 | 2022-10-28 | 青岛海尔特种电冰箱有限公司 | Equipment voice interaction method, computer readable storage medium and refrigerator |
CN113362821A (en) * | 2021-05-31 | 2021-09-07 | 东风商用车有限公司 | Control method, device and equipment of air suspension and storage medium |
CN113534780A (en) * | 2021-06-21 | 2021-10-22 | 上汽通用五菱汽车股份有限公司 | Remote control parking parameter and function definition method, automobile and readable storage medium |
CN113450795A (en) * | 2021-06-28 | 2021-09-28 | 深圳七号家园信息技术有限公司 | Image recognition method and system with voice awakening function |
WO2023279746A1 (en) * | 2021-07-05 | 2023-01-12 | 青岛海尔空调器有限总公司 | Method, system and apparatus for switching timbre of air conditioner, electronic device, and storage medium |
CN114023305A (en) * | 2021-11-26 | 2022-02-08 | 北京百度网讯科技有限公司 | Instruction scheduling method and device based on voice and electronic equipment |
CN114120979A (en) * | 2022-01-25 | 2022-03-01 | 荣耀终端有限公司 | Optimization method, training method, device and medium of voice recognition model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109410936A (en) | Air-conditioning equipment sound control method and device based on scene | |
CN107704275A (en) | Smart machine awakening method, device, server and smart machine | |
CN107564518A (en) | Smart machine control method, device and computer equipment | |
US9344815B2 (en) | Method for augmenting hearing | |
US20210280172A1 (en) | Voice Response Method and Device, and Smart Device | |
US9269073B2 (en) | Virtual agenda participant | |
CN107566874A (en) | Far field speech control system based on television equipment | |
CN106847283A (en) | Intelligent electrical appliance control and device | |
CN109036411A (en) | A kind of intelligent terminal interactive voice control method and device | |
CN111161714B (en) | Voice information processing method, electronic equipment and storage medium | |
US11587560B2 (en) | Voice interaction method, device, apparatus and server | |
CN108469966A (en) | Voice broadcast control method and device, intelligent device and medium | |
CN110996477B (en) | Air conditioner lamp control method, computer device and computer readable storage medium | |
CN110347367A (en) | Volume adjusting method, terminal device, storage medium and electronic equipment | |
US20190240588A1 (en) | Communication apparatus and control program thereof | |
CN109036393A (en) | Wake-up word training method, device and the household appliance of household appliance | |
CN106910496A (en) | Intelligent electrical appliance control and device | |
CN109712646A (en) | Voice broadcast method, device and terminal | |
CN109545194A (en) | Wake up word pre-training method, apparatus, equipment and storage medium | |
CN109373518A (en) | Air conditioner and its phonetic controller and sound control method | |
CN109166571A (en) | Wake-up word training method, device and the household appliance of household appliance | |
CN109210703A (en) | The sound control method of air-conditioning and the air-conditioning of voice control | |
CN108733341A (en) | A kind of voice interactive method and device | |
CN109686372A (en) | Resource control method for playing back and device | |
US20200211552A1 (en) | Voice interaction control method and apparatus |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |