CN109817211A - A kind of electric control method, device, storage medium and electric appliance - Google Patents
A kind of electric control method, device, storage medium and electric appliance Download PDFInfo
- Publication number
- CN109817211A CN109817211A CN201910114386.1A CN201910114386A CN109817211A CN 109817211 A CN109817211 A CN 109817211A CN 201910114386 A CN201910114386 A CN 201910114386A CN 109817211 A CN109817211 A CN 109817211A
- Authority
- CN
- China
- Prior art keywords
- user
- image
- command
- voice
- electric appliance
- 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.)
- Granted
Links
Landscapes
- Selective Calling Equipment (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present invention provides a kind of electric control method, device, storage medium and electric appliance, which comprises when receiving preset voice wake-up command, obtains the first image of the user when the voice wake-up command issues in the electric appliance local environment；The first image is identified, to identify the target user for issuing the default voice wake-up command；Identify the voice control command that the target user issues；The electric appliance, which is controlled, according to the voice control command executes corresponding operation.Scheme provided by the invention can combine image recognition and speech recognition, improve the accuracy rate of speech recognition.
Description
Technical field
The present invention relates to control field more particularly to a kind of electric control method, device, storage medium and electric appliances.
Background technique
With reaching its maturity for voice and image technique, the electric equipment products about voice and image are more and more.For example, taking
The intelligent air condition of voice or image is carried, or carries the intelligent air condition of voice and image.Currently, when only single user is opposite
When air-conditioning issues phonetic order, air-conditioning can quickly be identified and accordingly be made and more accurately act.But when user is more and more
When, intelligent air condition is just less fully up to expectations to receiving and recognizing of instructing of user speech.For example, group is in room
The inside party, more people are speaking simultaneously, have a user to want to operate air-conditioning by voice, at this point, simple dependence is returned
Sound the technologies such as eliminates and carries out noise reduction process, and the accuracy of possible speech recognition will reduction, it is likely that will lead to cannot identify or
The phenomenon of identification mistake occurs.
Summary of the invention
It is a primary object of the present invention to overcome the defect of the above-mentioned prior art, provide a kind of electric control method, device,
Storage medium and electric appliance, to solve under the scene that multiple users speak simultaneously in the prior art, when carrying out voice control to electric appliance
The problem of accuracy of speech recognition will reduce.
One aspect of the present invention provides a kind of electric control method, comprising: when receiving preset voice wake-up command,
Obtain the first image of the user when the voice wake-up command issues in the electric appliance local environment；To the first image
It is identified, to identify the target user for issuing the default voice wake-up command；Identify the language that the target user issues
Sound control command；The electric appliance, which is controlled, according to the voice control command executes corresponding operation.
Optionally, further includes: when receiving the preset voice wake-up command, judge in the electric appliance local environment
Whether multiple users are had；In the case where there are multiple users, obtain when the voice wake-up command issues locating for the electric appliance
The first image of user in environment.
Optionally, the first image is identified, to identify the target for issuing the default voice wake-up command
User, comprising: whether spoken using each user in preset image recognition model identification the first image；It will know
Not Chu the first image in the user to speak be determined as the target user.
Optionally, whether said using each user in preset image recognition model identification the first image
Words, comprising: using the lip state of each user in preset image recognition model identification the first image, to determine
Whether each user stated in the first image is speaking；Wherein, the lip state, comprising: whether lip is closed and/or mouth
Whether lip acts；When identifying that the lip state of any user within a preset time is closed state, it is identified as not saying
Words；And/or it when identifying that the lip state of any user within a preset time is action state, is identified as speaking.
Optionally, the voice control command that the target user issues is identified, comprising: acquire the second of the target user
Voice in image and current environment；Second image is identified, to identify that the target user spoke rises
Stop；According to the start-stop point identified, the voice control command of target user's sending is extracted.
Optionally, the electric appliance is controlled according to the voice control command and executes corresponding operation, comprising: to the voice
Control command carries out speech recognition, to identify the corresponding electrical equipment control order of the voice control command；According to what is identified
The electrical equipment control order controls the electric appliance and executes corresponding operation.
Another aspect of the present invention provides a kind of electric apparatus control apparatus, comprising: acquiring unit, for preset when receiving
When voice wake-up command, the first figure of the user when the voice wake-up command issues in the electric appliance local environment is obtained
Picture；User identification unit issues the default voice wake-up command for identifying to the first image to identify
Target user；Command recognition unit, the voice control command that the target user issues for identification；Control unit is used for root
The electric appliance, which is controlled, according to the voice control command executes corresponding operation.
Optionally, further includes: judging unit, for when receiving the preset voice wake-up command, described in judgement
Whether multiple users are had in electric appliance local environment；The acquiring unit is obtained in the case where there is multiple users in the voice
The first image of user of wake-up command when issuing in the electric appliance local environment.
Optionally, the user identification unit, comprising: identification subelement, for being known using preset image recognition model
Whether each user in other the first image is speaking；Determine subelement, the first image for will identify that
In the user to speak be determined as the target user.
Optionally, the identification subelement is identified each in the first image using preset image recognition model
Whether user is speaking, comprising: utilizes the mouth of each user in preset image recognition model identification the first image
Whether lip-like state is being spoken with each user determined in the first image；Wherein, the lip state, comprising: lip
Whether it is closed and/or whether lip acts；When identifying that the lip state of any user within a preset time is closed state
When, it is identified as not speaking；And/or when identifying that the lip state of any user within a preset time is action state,
It is identified as speaking.
Optionally, the command recognition unit, comprising: Image Acquisition subelement, for acquiring the of the target user
Voice in two images and current environment；Image recognition subelement, for being identified to second image, to identify
The start-stop point that the target user speaks；Subelement is extracted in order, for extracting target according to the start-stop point identified
The voice control command that user issues.
Optionally, described control unit controls the electric appliance according to the voice control command and executes corresponding operation, packet
It includes: speech recognition being carried out to the voice control command, to identify the corresponding electrical equipment control order of the voice control command；
According to the electrical equipment control order identified, controls the electric appliance and execute corresponding operation.
Another aspect of the invention provides a kind of storage medium, is stored thereon with computer program, and described program is processed
The step of device realizes aforementioned any the method when executing.
Further aspect of the present invention provides a kind of electric appliance, including processor, memory and storage on a memory can be
The step of computer program run on processor, the processor realizes aforementioned any the method when executing described program.
Further aspect of the present invention provides a kind of electric appliance, including aforementioned any electric apparatus control apparatus.
According to the technique and scheme of the present invention, the figure of user when voice wake-up command issues in electric appliance local environment is obtained
Picture goes out to issue the target user of voice wake-up command by image recognition, to identify the voice control that target user issues
Image recognition and speech recognition are combined to control electric appliance according to the voice control command, improve speech recognition by order
Accuracy rate can identify the user for issuing voice control command in multiple users, improve user especially under multi-user scene
Experience, and voice control life is carried out by the start-stop point that image recognition is carrying out the user of voice control and user speaks
The extraction of order further improves the accuracy rate of speech recognition.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the method schematic diagram of an embodiment of electric control method provided by the invention；
Fig. 2 is identified to the first image, to identify that the target for issuing the default voice wake-up command is used
A kind of flow diagram of specific embodiment of the step of family；
The one kind for the step of Fig. 3 is the voice control command of identification according to an embodiment of the present invention target user's sending
The flow diagram of specific embodiment；
Fig. 4 is the method schematic diagram of another embodiment of electric control method provided by the invention；
Fig. 5 is the structural schematic diagram of an embodiment of electric apparatus control apparatus provided by the invention；
Fig. 6 is a kind of structural schematic diagram of specific embodiment of user identification unit according to an embodiment of the present invention；
Fig. 7 is a kind of structural schematic diagram of specific embodiment of command recognition unit according to an embodiment of the present invention；
Fig. 8 is the structural schematic diagram of another embodiment of electric apparatus control apparatus provided by the invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the specific embodiment of the invention and
Technical solution of the present invention is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
Fig. 1 is the method schematic diagram of an embodiment of electric control method provided by the invention.
As shown in Figure 1, according to one embodiment of present invention, the electric control method includes at least step S110, step
Rapid S120, step S130 and step S140.
Step S110 is obtained when receiving preset voice wake-up command and is issued when institute in the voice wake-up command
State the first image of the user in electric appliance local environment.
Specifically, the first figure of the user in the electric appliance local environment can be acquired by the camera on the electric appliance
Picture.For example, the electric appliance is intelligent air condition, the camera of intelligent air condition can be constantly in open state, in real time acquisition intelligence
User images in air-conditioning local environment.When receiving preset voice wake-up command, obtain in the voice wake-up command
The first image of user when sending in the electric appliance local environment identifies that issuing voice calls out will pass through the first image
Wake up the user ordered.
Step S120, identifies the first image, to identify the mesh for issuing the default voice wake-up command
Mark user.
Fig. 2 be it is according to an embodiment of the present invention the first image is identified, issue the default language to identify
A kind of flow diagram of specific embodiment of the step of target user of sound wake-up command.As shown in Fig. 2, a kind of specific
In embodiment, step S120 includes step S121 and step S122.
Whether step S121 is being spoken using the user in preset image recognition model identification the first image.
Step S122, the user to speak in the first image that will identify that are determined as the target user.
Specifically, using the lip state of each user in preset image recognition model identification described image, with true
Whether each user determined in described image is speaking.Described image identification model can be for example convolution mind trained in advance
Through network model, the lip state includes: whether lip is closed and/or whether lip acts；When identifying that any user exists
When lip state in preset time is closed state, it is identified as not speaking；And/or works as and identify any user default
When lip state in time is action state, it is identified as speaking.That is, in a period of time, a certain user's
Lip thinks that the user is not speaking at this time all in closed state；In a period of time, the lip of a certain user is all in dynamic
Make state, for example, the regular opening and closing of lip), then it is assumed that the user is speaking at this time.It is waken up if identifying in the voice
A certain user is speaking when order sending, then the user to speak that will identify that is determined as target user, i.e. sending language
The user of sound wake-up command.
Step S130 identifies the voice control command that the target user issues.
The one kind for the step of Fig. 3 is the voice control command of identification according to an embodiment of the present invention target user's sending
The flow diagram of specific embodiment.As shown in figure 3, in a specific embodiment, step S130 include step S131,
Step S132 and step S133.
Step S131 acquires the voice in the second image and current environment of the target user.
Step S132 identifies second image, to identify start-stop point that the target user speaks.
Step S133 extracts the voice control command of target user's sending according to the start-stop point identified.
Specifically, after identifying the target user for issuing voice wake-up command, image (the second figure of the target user is acquired
Picture) and current environment in voice, and the image of acquisition is identified, to identify start-stop that the target user speaks
Point, user subconscious can generally make a short pause when finishing a word, user face detection to the phenomenon that be exactly
Lip closure, in a period of time, the second image (preferably, acquiring the face-image of target user) of collected target user
In, the lip of user is at closed state, that is, thinks that user is not speaking at this time.In a period of time, collected mesh
In the second image for marking user, the regular opening and closing of the lip of user, then it is assumed that user is speaking at this time, uses for the previous period
Family state is to speak state, and user's lip does not have opening and closing after a period of time, that is, thinks that user speaks ends, according to identified
Stop, extract in the environment acquired between start-stop point voice (for example, according to rise, the period between stop, extracting should
Voice in period environment), as the target user user issue voice control command.Optionally, it can be combined with language
Voice endpoint detection technique identifies the forward terminal (i.e. starting point) and aft terminal (i.e. end point) of the voice in collected environment, from
And the efficient voice section in the voice in collected environment (voice control command of the i.e. described target user) is extracted, thus
Improve the accuracy of identification punctuate.
Step S140 controls the electric appliance according to the voice control command and executes corresponding operation.
Specifically, speech recognition is carried out to the voice control command, to identify that the voice control command is corresponding
Electrical equipment control order；According to the electrical equipment control order identified, controls the electric appliance and execute corresponding operation.More specifically
Ground carries out speech recognition to the voice control command, to identify the semanteme of the voice control command, according to what is identified
Semanteme determines the corresponding electrical equipment control order of the voice control command.If being capable of determining that according to the semanteme identified corresponding
Electrical equipment control order, then the voice control command is effective phonetic control command, then can be according to the electric appliance identified
Control command controls the electric appliance and executes corresponding operation.
In practical application scene, there are multiple users inside room, multiple users may chat together, useful at this time
Voice control air-conditioning is wanted at family, needs first to issue voice wake-up command against intelligent air condition, when intelligent air condition receives user's
When voice wake-up command, the image when voice wake-up command issues in local environment is obtained, identifies and is being said in described image
The user of words identifies the voice control command of user, when identify the voice control command be effective voice control command
When, control intelligent air condition executes corresponding operation.
Fig. 4 is the method schematic diagram of another embodiment of electric control method provided by the invention.As shown in figure 4, according to
Another embodiment of the invention, the electric control method further include step S102.
Step S102, when receiving the preset voice wake-up command, judge in the electric appliance local environment whether
There are multiple users.
In the case where there are multiple users, obtain when the voice wake-up command issues in the electric appliance local environment
The first image (step S110) of user.
In a specific embodiment, multiple use are determined whether by acquiring the sound in the electric appliance local environment
Family.For example, carry out Application on Voiceprint Recognition to the sound in the electric appliance local environment of acquisition, when identifying more than two different vocal print,
Determining has multiple users in electric appliance local environment.In another embodiment, the image in the electric appliance local environment is acquired,
By whether having multiple users in image recognition electric appliance local environment.In the case where determining there are multiple users, obtain described
The first image of user of voice wake-up command when issuing in the electric appliance local environment.
Fig. 5 is the structural schematic diagram of an embodiment of electric apparatus control apparatus provided by the invention.As shown in figure 5, the electricity
Device control device 100 includes acquiring unit 110, user identification unit 120, command recognition unit 130 and control unit 140.
Acquiring unit 110 is used for when receiving preset voice wake-up command, is obtained and is sent out in the voice wake-up command
The first image of user when out in the electric appliance local environment；User identification unit 120 is used to carry out the first image
Identification, to identify the target user for issuing the default voice wake-up command；The mesh for identification of command recognition unit 130
Mark the voice control command that user issues；Control unit 140 is used to control the electric appliance according to the voice control command and execute
Corresponding operation.
When receiving preset voice wake-up command, acquiring unit 110 is obtained when the voice wake-up command issues
The first image of user in the electric appliance local environment.
Specifically, acquiring unit 110 can be acquired in the electric appliance local environment by the camera on the electric appliance
The first image of user.For example, the electric appliance is intelligent air condition, the camera of intelligent air condition can be constantly in open state,
User images in acquisition intelligent air condition local environment in real time.When intelligent air condition receives preset voice wake-up command, obtain
The first image for the user for taking unit 110 to obtain when the voice wake-up command issues in the electric appliance local environment, so as to
The user for issuing voice wake-up command is identified by the first image.
User identification unit 120 identifies the first image, to identify that issuing the default voice wakes up life
The target user of order.
Fig. 6 is a kind of structural schematic diagram of specific embodiment of user identification unit according to an embodiment of the present invention.Such as
Shown in Fig. 6, in a specific embodiment, user identification unit 120 includes identification subelement 121 and determining subelement 122.
Identification subelement 121 is used for
It is no to speak.Determine that the user to speak in the first image of the subelement 122 for will identify that is determined as institute
State target user.
Specifically, identification subelement 121 utilizes each user's in preset image recognition model identification described image
Whether lip state is being spoken with each user determined in described image.Described image identification model for example can be pre-
First trained convolutional neural networks model, the lip state include: whether lip is closed and/or whether lip acts；Work as knowledge
Not Chu the lip state of any user within a preset time when being closed state, be identified as not speaking；And/or works as and identify
When the lip state of any user within a preset time is action state, it is identified as speaking.That is, a period of time
Interior, the lip of a certain user thinks that the user is not speaking at this time all in closed state；In a period of time, a certain user
Lip all in action state, for example, the regular opening and closing of lip), then it is assumed that the user is speaking at this time.If identification
Unit 121 identifies that a certain user is speaking when the voice wake-up command issues, it is determined that subelement 122 will identify that
The user to speak be determined as target user, that is, issue the user of voice wake-up command.
Command recognition unit 130 identifies the voice control command that the target user issues.
Fig. 7 is a kind of structural schematic diagram of specific embodiment of command recognition unit according to an embodiment of the present invention.Such as
Shown in Fig. 7, in a specific embodiment, command recognition unit 130 includes Image Acquisition subelement 131, image recognition
Subelement 133 is extracted in unit 132 and order.
Image Acquisition subelement 131 is used to acquire the voice in the second image and current environment of the target user；
Image recognition subelement 132 is used to identify second image that described image acquisition subelement 131 acquires, with identification
The start-stop point that the target user speaks out；Order extracts what subelement 133 was used to identify according to image recognition subelement 132
The start-stop point extracts the voice control command of target user's sending.
Specifically, after user identification unit 120 identifies the target user for issuing voice wake-up command, Image Acquisition is single
The image (the second image) and the voice in current environment that member 131 acquires the target user, 132 pairs of image recognition subelement figures
As the image that acquisition subelement 131 acquires is identified that identify the start-stop point that the target user speaks, user is finishing one
When word, subconscious can generally make a short pause, user face detection to the phenomenon that be exactly lip closure, at one section
In, in the second image (preferably, acquiring the face-image of target user) of collected target user, the lip of user is all
It is to think that user is not speaking at this time in closed state.In a period of time, the second image of collected target user
In, the regular opening and closing of the lip of user, then it is assumed that user is speaking at this time, and User Status is shape of speaking for the previous period
State, user's lip does not have opening and closing after a period of time, that is, thinks that user speaks end, and order is extracted subelement 133 and known according to image
The start-stop point that small pin for the case unit 132 identifies extracts the voice in the environment acquired between start-stop point (for example, according to rising, stopping
Period between point, extract the voice in the period environment), the voice control that as the target user user issues is ordered
It enables.Optionally, order, which extracts subelement 133 and can be combined with speech terminals detection technology, identifies voice in collected environment
Forward terminal (i.e. starting point) and aft terminal (i.e. end point), to extract effective language in the voice in collected environment
Segment (voice control command of the i.e. described target user), to improve the accuracy of identification punctuate.
Control unit 140 controls the electric appliance according to the voice control command and executes corresponding operation.
Specifically, control unit 140 carries out speech recognition to the voice control command, to identify the voice control
Order corresponding electrical equipment control order；According to the electrical equipment control order identified, controls the electric appliance and execute corresponding behaviour
Make.More specifically, control unit 140 carries out speech recognition to the voice control command, to identify the voice control life
The semanteme of order determines the corresponding electrical equipment control order of the voice control command according to the semanteme identified.If according to identifying
Semanteme be capable of determining that corresponding electrical equipment control order, then the voice control command be effective phonetic control command, then control
Unit 140 processed can control the electric appliance and execute corresponding operation according to the electrical equipment control order identified.
Fig. 8 is the structural schematic diagram of another embodiment of electric apparatus control apparatus provided by the invention.As shown in figure 8, according to
Another embodiment of the invention, the electric apparatus control apparatus further include judging unit 102.
Judging unit 102 is used for when receiving the preset voice wake-up command, judges the electric appliance local environment
In whether have multiple users；The acquiring unit 110 is obtained and is sent out in the voice wake-up command in the case where there is multiple users
The first image of user when out in the electric appliance local environment.
In a specific embodiment, judging unit 102 can be by acquiring the sound in the electric appliance local environment
Determine whether multiple users.For example, in the electric appliance local environment of acquisition sound carry out Application on Voiceprint Recognition, identify two with
When upper different vocal print, determining has multiple users in electric appliance local environment.In another embodiment, the electric appliance institute is acquired
Whether there are multiple users in image recognition electric appliance local environment of the image by acquisition in place's environment.It is true in judging unit 102
Surely in the case where having multiple users, acquiring unit 110 obtains the electric appliance local environment when the voice wake-up command issues
In user the first image.
The present invention also provides a kind of storage mediums for corresponding to the electric control method, are stored thereon with computer journey
Sequence, the step of aforementioned any the method is realized when described program is executed by processor.
The present invention also provides a kind of electric appliances for corresponding to the electric control method, including processor, memory and deposit
The computer program that can be run on a processor on a memory is stored up, the processor is realized aforementioned any when executing described program
The step of the method.
The present invention also provides a kind of electric appliances for corresponding to the electric apparatus control apparatus, including aforementioned any electric appliance control
Device processed.
Accordingly, scheme provided by the invention obtains the figure of user when voice wake-up command issues in electric appliance local environment
Picture goes out to issue the target user of voice wake-up command by image recognition, to identify the voice control that target user issues
Order, image recognition and speech recognition are combined, the accuracy rate of speech recognition is improved, especially under multi-user scene, energy
Enough identify in multiple users issue voice control command user, the user experience is improved, and by image recognition into
The start-stop point that the user and user of row voice control speak carries out the extraction of voice control command, further improves voice knowledge
Other accuracy rate.
Function described herein can be implemented in hardware, the software executed by processor, firmware or any combination thereof.
If implemented in the software executed by processor, computer can be stored in using function as one or more instructions or codes
It is transmitted on readable media or via computer-readable media.Other examples and embodiment are wanted in the present invention and appended right
It asks in the scope and spirit of book.For example, due to the property of software, function described above can be used by processor,
Hardware, firmware, hardwired or the software implementation for appointing the combination of whichever to execute in these.In addition, each functional unit can integrate
In one processing unit, it is also possible to each unit to physically exist alone, can also be integrated in two or more units
In one unit.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, and fill as control
The component set may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
The above description is only an embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should be included within scope of the presently claimed invention.
Claims (15)
1. a kind of electric control method characterized by comprising
When receiving preset voice wake-up command, the electric appliance local environment when the voice wake-up command issues is obtained
In user the first image；
The first image is identified, to identify the target user for issuing the default voice wake-up command；
Identify the voice control command that the target user issues；
The electric appliance, which is controlled, according to the voice control command executes corresponding operation.
2. the method according to claim 1, wherein further include:
When receiving the preset voice wake-up command, judge whether there are multiple users in the electric appliance local environment；
In the case where there are multiple users, the user when the voice wake-up command issues in the electric appliance local environment is obtained
The first image.
3. method according to claim 1 or 2, which is characterized in that identify to the first image, set out with identification
The target user of the default voice wake-up command out, comprising:
Whether spoken using each user in preset image recognition model identification the first image；
The user to speak in the first image that will identify that is determined as the target user.
4. according to the method described in claim 3, it is characterized in that, identifying first figure using preset image recognition model
Whether each user as in is speaking, comprising:
Using the lip state of each user in preset image recognition model identification the first image, with determination described the
Whether each user in one image is speaking；Wherein, the lip state, comprising: whether lip is closed and/or lip is
No movement；
When identifying that the lip state of any user within a preset time is closed state, it is identified as not speaking；
And/or
When identifying that the lip state of any user within a preset time is action state, it is identified as speaking.
5. method according to claim 1-4, which is characterized in that identify the voice control that the target user issues
System order, comprising:
Acquire the voice in the second image and current environment of the target user；
Second image is identified, to identify start-stop point that the target user speaks；
According to the start-stop point identified, the voice control command of target user's sending is extracted.
6. method according to claim 1-5, which is characterized in that according to voice control command control
Electric appliance executes corresponding operation, comprising:
Speech recognition is carried out to the voice control command, to identify corresponding electrical equipment control order；
According to the electrical equipment control order identified, controls the electric appliance and execute corresponding operation.
7. a kind of electric apparatus control apparatus characterized by comprising
Acquiring unit, for obtaining and issuing when institute in the voice wake-up command when receiving preset voice wake-up command
State the first image of the user in electric appliance local environment；
User identification unit issues the default voice wake-up command for identifying to the first image to identify
Target user；
Command recognition unit, the voice control command that the target user issues for identification；
Control unit executes corresponding operation for controlling the electric appliance according to the voice control command.
8. device according to claim 7, which is characterized in that further include:
Judging unit, for when receiving the preset voice wake-up command, judge in the electric appliance local environment whether
There are multiple users；
The acquiring unit obtains the electric appliance institute when the voice wake-up command issues in the case where there is multiple users
Locate the first image of the user in environment.
9. device according to claim 7 or 8, which is characterized in that the user identification unit, comprising:
Subelement is identified, for whether to identify each user in the first image using preset image recognition model
It speaks；
Determine subelement, the user to speak in the first image for will identify that is determined as the target and uses
Family.
10. device according to claim 9, which is characterized in that the identification subelement utilizes preset image recognition mould
Whether each user in type identification the first image is speaking, comprising:
Using the lip state of each user in preset image recognition model identification the first image, with determination described the
Whether each user in one image is speaking；Wherein, the lip state, comprising: whether lip is closed and/or lip is
No movement；
When identifying that the lip state of any user within a preset time is closed state, it is identified as not speaking；
And/or
When identifying that the lip state of any user within a preset time is action state, it is identified as speaking.
11. according to the described in any item devices of claim 7-10, which is characterized in that the command recognition unit, comprising:
Image Acquisition subelement, the voice in the second image and current environment for acquiring the target user；
Image recognition subelement, for being identified to second image, to identify start-stop that the target user speaks
Point；
Subelement is extracted in order, for extracting the voice control life of target user's sending according to the start-stop point identified
It enables.
12. according to the described in any item devices of claim 7-11, which is characterized in that described control unit, according to the voice
Control command controls the electric appliance and executes corresponding operation, comprising:
Speech recognition is carried out to the voice control command, to identify the corresponding electrical equipment control life of the voice control command
It enables；
According to the electrical equipment control order identified, controls the electric appliance and execute corresponding operation.
13. a kind of storage medium, which is characterized in that it is stored thereon with computer program, it is real when described program is executed by processor
The step of existing claim 1-6 any the method.
14. a kind of electric appliance, which is characterized in that can be transported on a processor on a memory including processor, memory and storage
The step of capable computer program, the processor realizes claim 1-6 any the method when executing described program.
15. a kind of electric appliance, which is characterized in that including the electric apparatus control apparatus as described in claim 7-12 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910114386.1A CN109817211B (en) | 2019-02-14 | 2019-02-14 | Electric appliance control method and device, storage medium and electric appliance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910114386.1A CN109817211B (en) | 2019-02-14 | 2019-02-14 | Electric appliance control method and device, storage medium and electric appliance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109817211A true CN109817211A (en) | 2019-05-28 |
| CN109817211B CN109817211B (en) | 2021-04-02 |
Family
ID=66606549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910114386.1A Active CN109817211B (en) | 2019-02-14 | 2019-02-14 | Electric appliance control method and device, storage medium and electric appliance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109817211B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517685A (en) * | 2019-09-25 | 2019-11-29 | 深圳追一科技有限公司 | Audio recognition method, device, electronic equipment and storage medium |
| CN110910887A (en) * | 2019-12-30 | 2020-03-24 | 苏州思必驰信息科技有限公司 | Voice wake-up method and device |
| CN111276140A (en) * | 2020-01-19 | 2020-06-12 | 珠海格力电器股份有限公司 | Voice command recognition method, device, system and storage medium |
| CN111294706A (en) * | 2020-01-16 | 2020-06-16 | 珠海格力电器股份有限公司 | Voice electrical appliance control method and device, storage medium and voice electrical appliance |
| CN112002316A (en) * | 2020-07-30 | 2020-11-27 | 珠海格力电器股份有限公司 | Electric appliance control method and device, storage medium and terminal |
| CN112567457A (en) * | 2019-12-13 | 2021-03-26 | 华为技术有限公司 | Voice detection method, prediction model training method, device, equipment and 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 |
| WO2023005844A1 (en) * | 2021-07-26 | 2023-02-02 | 华为技术有限公司 | Device wake-up method, related apparatus, and communication system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682273A (en) * | 2011-03-18 | 2012-09-19 | 夏普株式会社 | Device and method for detecting lip movement |
| CN104049721A (en) * | 2013-03-11 | 2014-09-17 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN104166831A (en) * | 2013-05-15 | 2014-11-26 | 五邑大学 | ALBP and SRC algorithm-based fatigue detection method and system |
| CN104409075A (en) * | 2014-11-28 | 2015-03-11 | 深圳创维－Rgb电子有限公司 | Voice identification method and system |
| US20150373774A1 (en) * | 2014-06-20 | 2015-12-24 | Apple Inc. | End-to-End Delay Adaptation with Connected DRX in a Cellular Voice Call |
| CN106257355A (en) * | 2015-06-18 | 2016-12-28 | 松下电器（美国）知识产权公司 | Apparatus control method and controller |
| CN107346661A (en) * | 2017-06-01 | 2017-11-14 | 李昕 | A kind of distant range iris tracking and acquisition method based on microphone array |
| CN107679506A (en) * | 2017-10-12 | 2018-02-09 | Tcl通力电子（惠州）有限公司 | Awakening method, intelligent artifact and the computer-readable recording medium of intelligent artifact |
-
2019
- 2019-02-14 CN CN201910114386.1A patent/CN109817211B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682273A (en) * | 2011-03-18 | 2012-09-19 | 夏普株式会社 | Device and method for detecting lip movement |
| CN104049721A (en) * | 2013-03-11 | 2014-09-17 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN104166831A (en) * | 2013-05-15 | 2014-11-26 | 五邑大学 | ALBP and SRC algorithm-based fatigue detection method and system |
| US20150373774A1 (en) * | 2014-06-20 | 2015-12-24 | Apple Inc. | End-to-End Delay Adaptation with Connected DRX in a Cellular Voice Call |
| CN104409075A (en) * | 2014-11-28 | 2015-03-11 | 深圳创维－Rgb电子有限公司 | Voice identification method and system |
| CN106257355A (en) * | 2015-06-18 | 2016-12-28 | 松下电器（美国）知识产权公司 | Apparatus control method and controller |
| CN107346661A (en) * | 2017-06-01 | 2017-11-14 | 李昕 | A kind of distant range iris tracking and acquisition method based on microphone array |
| CN107679506A (en) * | 2017-10-12 | 2018-02-09 | Tcl通力电子（惠州）有限公司 | Awakening method, intelligent artifact and the computer-readable recording medium of intelligent artifact |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517685A (en) * | 2019-09-25 | 2019-11-29 | 深圳追一科技有限公司 | Audio recognition method, device, electronic equipment and storage medium |
| CN110517685B (en) * | 2019-09-25 | 2021-10-08 | 深圳追一科技有限公司 | Voice recognition method and device, electronic equipment and storage medium |
| CN112567457A (en) * | 2019-12-13 | 2021-03-26 | 华为技术有限公司 | Voice detection method, prediction model training method, device, equipment and medium |
| WO2021114224A1 (en) * | 2019-12-13 | 2021-06-17 | 华为技术有限公司 | Voice detection method, prediction model training method, apparatus, device, and medium |
| CN112567457B (en) * | 2019-12-13 | 2021-12-10 | 华为技术有限公司 | Voice detection method, prediction model training method, device, equipment and medium |
| CN110910887A (en) * | 2019-12-30 | 2020-03-24 | 苏州思必驰信息科技有限公司 | Voice wake-up method and device |
| CN111294706A (en) * | 2020-01-16 | 2020-06-16 | 珠海格力电器股份有限公司 | Voice electrical appliance control method and device, storage medium and voice electrical appliance |
| CN111276140A (en) * | 2020-01-19 | 2020-06-12 | 珠海格力电器股份有限公司 | Voice command recognition method, device, system and storage medium |
| CN111276140B (en) * | 2020-01-19 | 2023-05-12 | 珠海格力电器股份有限公司 | Voice command recognition method, device, system and storage medium |
| CN112002316A (en) * | 2020-07-30 | 2020-11-27 | 珠海格力电器股份有限公司 | Electric appliance control method and device, storage medium and terminal |
| 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 |
| WO2023005844A1 (en) * | 2021-07-26 | 2023-02-02 | 华为技术有限公司 | Device wake-up method, related apparatus, and communication system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109817211B (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109817211A (en) | A kind of electric control method, device, storage medium and electric appliance | |
| CN105723450B (en) | The method and system that envelope for language detection compares | |
| CN107480622A (en) | Micro- expression recognition method, device and storage medium | |
| CN104540290A (en) | Control method for intelligent table lamp and intelligent table lamp | |
| CN108305623A (en) | Electric control method and device | |
| CN108920639A (en) | Context acquisition methods and equipment based on interactive voice | |
| CN109377995B (en) | Method and device for controlling equipment | |
| CN107360157A (en) | A kind of user registering method, device and intelligent air conditioner | |
| KR102203720B1 (en) | Method and apparatus for speech recognition | |
| CN110970018A (en) | Speech recognition method and device | |
| US20170185827A1 (en) | Emotion estimation apparatus using facial images of target individual, emotion estimation method, and non-transitory computer readable medium | |
| CN109979474A (en) | Speech ciphering equipment and its user speed modification method, device and storage medium | |
| CN110569344B (en) | Method and device for determining standard question corresponding to dialogue text | |
| CN112489648A (en) | Wake-up processing threshold adjustment method, voice home appliance, and storage medium | |
| CN108986825A (en) | Context acquisition methods and equipment based on interactive voice | |
| CN108681390A (en) | Information interacting method and device, storage medium and electronic device | |
| CN108897517B (en) | Information processing method and electronic equipment | |
| CN108122557A (en) | Vehicle multimedia navigation terminal based on Application on Voiceprint Recognition | |
| CN109286706A (en) | display device | |
| CN107808085A (en) | the fingerprint control method and system of intelligent terminal | |
| CN112200556A (en) | Transfer processing method and device of automatic teller machine | |
| CN111428666A (en) | Intelligent family accompanying robot system and method based on rapid face detection | |
| CN108318042A (en) | Navigation mode-switching method, device, terminal and storage medium | |
| CN109635625A (en) | Smart identity checking method, equipment, storage medium and device | |
| CN109903522A (en) | A kind of monitoring method, device, storage medium and household electrical appliance |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200409 Address after: 519070 Guangdong city of Zhuhai Province Qianshan Applicant after: GREE ELECTRIC APPLIANCES Inc. OF ZHUHAI Applicant after: GREE GREEN REFRIGERATION TECHNOLOGY CENTER CO., LTD. OF ZHUHAI Address before: Xiangzhou District of Guangdong city in Zhuhai province 519070 Qianshan No. 789 Applicant before: GREE ELECTRIC APPLIANCES Inc. OF ZHUHAI |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |