CN110534107A - Sound control method, device, system and the electronic equipment of smart machine - Google Patents
Sound control method, device, system and the electronic equipment of smart machine Download PDFInfo
- Publication number
- CN110534107A CN110534107A CN201910859713.6A CN201910859713A CN110534107A CN 110534107 A CN110534107 A CN 110534107A CN 201910859713 A CN201910859713 A CN 201910859713A CN 110534107 A CN110534107 A CN 110534107A
- Authority
- CN
- China
- Prior art keywords
- control command
- identity information
- subscriber identity
- user
- permission
- 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
- 238000000034 method Methods 0.000 title claims abstract description 132
- 230000001755 vocal effect Effects 0.000 claims abstract description 59
- 230000001815 facial effect Effects 0.000 claims abstract description 42
- 230000006399 behavior Effects 0.000 claims description 26
- 230000005540 biological transmission Effects 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 abstract description 45
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 17
- 238000012790 confirmation Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 238000003058 natural language processing Methods 0.000 description 4
- 238000004321 preservation Methods 0.000 description 4
- 238000010408 sweeping Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005406 washing Methods 0.000 description 3
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005755 formation reaction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229910052741 iridium Inorganic materials 0.000 description 1
- GKOZUEZYRPOHIO-UHFFFAOYSA-N iridium atom Chemical compound [Ir] GKOZUEZYRPOHIO-UHFFFAOYSA-N 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000009237 prenatal development Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000003786 sclera Anatomy 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012546 transfer 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
-
- 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
- G10L15/24—Speech recognition using non-acoustical features
- G10L15/25—Speech recognition using non-acoustical features using position of the lips, movement of the lips or face analysis
-
- 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
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
- H04L12/282—Controlling appliance services of a home automation network by calling their functionalities based on user interaction within the home
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Biomedical Technology (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of sound control methods of smart machine, applied to voice control technology field, main purpose is to solve existing smart machine in speech control process, there is a problem of that safety is lower, key step of the present invention includes: reception phonetic control command, and the biological characteristic of the phonetic control command sender is obtained after receiving the phonetic control command, the biological characteristic includes at least one of vocal print feature, iris feature and facial characteristics；According to the biological characteristic, the subscriber identity information of the phonetic control command sender is determined；The subscriber identity information and the phonetic control command are sent to cloud platform.The present invention is suitable for carrying out smart machine the process of voice control.
Description
Technical field
The present invention relates to voice control fields, and in particular to a kind of sound control method of smart machine, device, system and
Electronic equipment.
Background technique
With smart machine, smart home it is universal, people are more and more to the contact of smart machine or smart home.Mesh
It is preceding during controlling smart machine, voice control since its convenience, ease for use are higher, gradually become day
Ordinary persons carry out the major way of smart machine control.
In general, common control process is to issue voice based on user when user carries out voice control to smart machine
After information, the acquisition of voice is carried out by the phonetic inceptings equipment such as intelligent sound box, and by converting voice messaging to control command
Being sent to needs device to be controlled, to carry out the relevant control of equipment, for example, starting or closing by voice control smart machine
It closes.However, in practical applications, due in family smart machine or smart home can pass through intelligent sound box or other intelligence
Terminal carries out freely manipulating for voice, and in fact, environment locating for smart home etc. is to compare secret personal space, current
Speech control process in, smart machine is highly prone to the people except kinsfolk and is controlled, for example, work as non-family members use
It is breakneck when the used voice control in the family electronics kitchen range of family.Therefore, existing smart machine is in voice control mistake
Cheng Zhong has that safety is lower.
Summary of the invention
In view of this, the present invention provides a kind of sound control method of smart machine, device, system and electronic equipment,
Its object is to solve in the speech control process of existing smart machine, the lower problem of safety.
For achieving the above object, according to the first aspect of the invention, a kind of voice control of smart machine is provided
Method includes: applied to mobile terminal
Phonetic control command is received, and obtains the phonetic control command after receiving the phonetic control command and issues
The biological characteristic of person, the biological characteristic include at least one of vocal print feature, iris feature and facial characteristics；
According to the biological characteristic, the subscriber identity information of the phonetic control command sender is determined；
The subscriber identity information and the phonetic control command are sent to cloud platform.
Optionally, described according to the biological characteristic, determine the subscriber identity information of the phonetic control command sender
Include:
According to the vocal print feature extracted in the phonetic control command, the corresponding vocal print is determined in default vocal print relationship
The user identifier of feature, the default vocal print relationship are that prerecords be corresponding with the mapping of different user and its corresponding vocal print
Relationship；
According to the user identifier, the subscriber identity information of the phonetic control command sender is determined.
Optionally, described according to the vocal print feature extracted in the phonetic control command, in default vocal print relationship really
Surely before the user identifier for corresponding to the vocal print feature, the method also includes:
When the biological characteristic for determining the phonetic control command sender is vocal print feature, obtains the default vocal print and close
System.
Optionally, described according to the biological characteristic, determine the subscriber identity information of the phonetic control command sender
Include:
According to the iris feature of acquisition, the user identity letter of the corresponding iris feature is determined in default iris relationship
Breath, the default iris relationship includes the corresponding iris feature of each subscriber identity information；
The reception phonetic control command, and the phonetic control command is obtained after receiving the phonetic control command
The biological characteristic of sender, comprising:
After receiving phonetic control command, by presetting iris collection device, the voice control of predeterminated position is obtained
Instruction sender issues the iris feature when phonetic control command.
Optionally, described according to the biological characteristic, determine the subscriber identity information of the phonetic control command sender
Include:
According to the facial characteristics of acquisition, the user identity letter of the corresponding facial characteristics is determined in default facial relationship
Breath, the face relationship includes each user's face feature and corresponding subscriber identity information；
The reception phonetic control command, and the phonetic control command is obtained after receiving the phonetic control command
The biological characteristic of sender, comprising:
After receiving phonetic control command, by pre-set image acquisition device, the voice of predetermined position is obtained
Control instruction sender issues the facial information when phonetic control command；
Defeated characteristics of image is extracted from the facial information, as the facial characteristics.
Optionally, it is described the subscriber identity information and the phonetic control command are sent to cloud platform before,
The method also includes:
Instruction parsing is carried out to the phonetic control command, obtains the semantic control information of the phonetic control command, institute
Stating instruction parsing includes by default natural language processing operation；
It is described that the subscriber identity information and the phonetic control command are sent to cloud platform, comprising:
The semantic control information and the subscriber identity information are sent to cloud platform.
Optionally, described after receiving phonetic control command, the method also includes:
Determine whether the phonetic control command is provided with encryption requirements；
When determining that described instruction there are when encryption requirements, then adds the phonetic control command and subscriber identity information
Close processing.
Optionally, before receiving phonetic control command, the method also includes:
When receiving voice input instruction, the first prompt information is exported to user, the voice input instruction is default
Be used to indicate the instruction for preparing operator's identity of typing voice control, biological characteristic and its voice operating permission, described the
One prompt information is used to indicate user and inputs subscriber identity information and biological characteristic；
Biological characteristic and subscriber identity information that the user is inputted based on prompt information are received, and establishes user's body
Corresponding relationship between part information and the biological characteristic；
The second prompt information is inputted to user, second prompt information is used to indicate user's typing and corresponds to user's body
The voice operating permission of part information；
The voice operating permission is received, and the voice operating permission and the corresponding relationship are sent to cloud and put down
Platform.
Optionally, after receiving voice input instruction, the method also includes:
The corresponding Permission Levels information of the subscriber identity information is confirmed to user, and the Permission Levels information is sent
To cloud platform, the Permission Levels are administrator or operator.
Optionally, the administrator, which has, to the voice operating permission that operator has modifies, adds and deletes
Permission, the method also includes:
When receiving permission control instruction, the subscriber identity information of the permission control instruction sender is determined, and will
The subscriber identity information of the permission control instruction sender and the permission control instruction are sent to cloud platform, to work as
When stating cloud platform and confirming that the subscriber identity information of the permission control instruction sender has administrator right, according to the power
Limit control instruction carry out permission operation behavior, the permission operation behavior include modify to the voice operating permission of user,
Addition and deletion.
Optionally, the subscriber identity information of the determination permission control instruction sender includes:
Obtain the mobile terminal identification code of user's input, and determine the mobile terminal identification code of user input with it is described
Whether the mobile terminal identification code built in mobile terminal is consistent, and the mobile terminal identification code adds unique when being equipment factory
Identification code；
If consistent, the biological characteristic of the permission control instruction sender is obtained, and according to characteristic identity relationship, is determined
The subscriber identity information of the biological characteristic is corresponded to, includes that each subscriber identity information is corresponding in the characteristic identity relationship
Biological characteristic.
If inconsistent, ignore the permission control instruction.
Optionally, the user identity letter of the phonetic control command sender is determined according to the biological characteristic described
After breath, method further include:
It is compared according to the biological characteristic and default biological characteristic, calculates the offset of user biological feature；
According to the biological characteristic offset, determine whether user's sign is normal；
When user's sign exception, Xiang Yunduan platform sends the prompt information of user's sign exception, and defeated to user
Information warning out.
According to the second aspect of the invention, a kind of sound control method of smart machine is provided, cloud platform is applied to,
Include:
Phonetic control command and subscriber identity information are received from mobile terminal；
According to the subscriber identity information, the voice operating permission of the corresponding subscriber identity information of matching；
According to the voice operating permission and the phonetic control command, to the equipment of the correspondence phonetic control command
Control instruction is sent, so that the equipment executes the operation of the corresponding phonetic control command after receiving the control instruction
Behavior.
Optionally, described according to the subscriber identity information, the voice operating power of the corresponding subscriber identity information of matching
Limit includes:
Identity authority relationship is obtained, it includes subscriber identity information and corresponding voice that the identity authority relationship, which is preset,
The mapping relations of operating right；
According to the identity authority relationship, the voice operating permission of the corresponding subscriber identity information is determined.
Optionally, described to include: from mobile terminal reception phonetic control command and subscriber identity information
Semantic control information and subscriber identity information are received from mobile terminal；
It is described according to the voice operating permission and the phonetic control command, to the correspondence phonetic control command
Equipment sends control instruction, comprising:
According to it is described it is semantic control information, generate the control instruction of the corresponding semantic control information, and by the control
Instruction is sent in the corresponding equipment of the semantic control information.
Optionally, described to include: from mobile terminal reception phonetic control command and subscriber identity information
Encrypted treated phonetic control command and subscriber identity information is received from mobile terminal；
It is described according to the voice operating permission and the phonetic control command, to the correspondence phonetic control command
Equipment sends control instruction, comprising:
According to decryption rule, the phonetic control command after the encryption is decrypted, the voice after being decrypted
Control instruction generates the control instruction based on the phonetic control command after the voice operating permission and the decryption, concurrently
It send into equipment.
Optionally, described before mobile terminal reception phonetic control command and subscriber identity information, the method is also wrapped
It includes:
The voice operating permission and corresponding relationship of user's typing are received from mobile terminal, the corresponding relationship includes user's body
Part information and corresponding biological characteristic；
It by the voice operating permission and the corresponding relationship, is saved according to subscriber identity information, to work as from shifting
Dynamic terminal carries out the matching of voice operating permission when receiving phonetic control command.
Optionally, the voice operating permission and the corresponding relationship are protected according to subscriber identity information described
After depositing, the method also includes:
Level information is limited from mobile-terminated retake the power, and is believed according to the Permission Levels information preservation to corresponding user identity
In the corresponding relationship of breath, the Permission Levels are administrator or operator.
Optionally, the administrator, which has, to the voice operating permission that operator has modifies, adds and deletes
Permission, the method also includes:
When from it is mobile-terminated receive permission control instruction when, determined according to the subscriber identity information and the corresponding relationship
The Permission Levels of the subscriber identity information；
When determining the Permission Levels is the administrator, corresponding permission is executed according to the permission control instruction and is grasped
Make behavior, the permission operation behavior includes that the voice operating permission of user is modified, adds and deleted；
When determining the Permission Levels is the operator, and determine that the permission control instruction is for permission control
When the permission of the sender of system instruction is operated, permission operation behavior is executed according to the permission control instruction, conversely, then neglecting
The slightly described permission control instruction.
Optionally, described according to the voice operating permission and the phonetic control command, to the correspondence voice control
After the equipment of system instruction sends control instruction, the method also includes:
According to the subscriber identity information, user identity feature is determined,
Based on the user identity feature, determine that the corresponding user group of the subscriber identity information, the user group are bases
It is pre-set according to classification in variety classes user identity feature；
According to the corresponding user group of subscriber identity information, Xiang Suoshu mobile terminal feeds back the pushed information of corresponding user group.
Optionally, described according to the voice operating permission and the phonetic control command, to the correspondence voice control
After the equipment of system instruction sends control instruction, the method also includes:
Prompt information is received from mobile terminal, the prompt information is used to indicate user's sign and there is exception；
According to the prompt information, user's sign extremely corresponding reason and solution are obtained, it is different as sign
Often processing information, and the sign exception handling information is fed back into mobile terminal.
According to the present invention in terms of third, a kind of phonetic controller of smart machine is provided, is applied to mobile terminal,
Include:
Acquiring unit for receiving phonetic control command, and obtains institute's predicate after receiving the phonetic control command
The biological characteristic of sound control instruction sender, the biological characteristic include at least in vocal print feature, iris feature and facial characteristics
One kind；
First determination unit, for determining user's body of the phonetic control command sender according to the biological characteristic
Part information；
Transmission unit, for the subscriber identity information and the phonetic control command to be sent to cloud platform.
Optionally, first determination unit includes:
First determining module, for according to the vocal print feature extracted in the phonetic control command, in default vocal print relationship
The user identifier of the middle determining corresponding vocal print feature, the default vocal print relationship be prerecord be corresponding with different user and
The mapping relations of its corresponding vocal print；
Second determining module, for determining user's body of the phonetic control command sender according to the user identifier
Part information.
Optionally, first determination unit further include:
Module is obtained, for obtaining when the biological characteristic for determining the phonetic control command sender is vocal print feature
The default vocal print relationship.
Optionally, first determination unit includes:
Third determining module determines the corresponding iris for the iris feature according to acquisition in default iris relationship
The subscriber identity information of feature, the default iris relationship include the corresponding iris feature of each subscriber identity information；
The acquiring unit, comprising:
Iris obtains module, for by presetting iris collection device, obtaining default position after receiving phonetic control command
The phonetic control command sender set issues the iris feature when phonetic control command.
Optionally, first determination unit includes:
4th determining module determines the corresponding face in default facial relationship for the facial characteristics according to acquisition
The subscriber identity information of feature, the face relationship includes each user's face feature and corresponding subscriber identity information；
The acquiring unit, comprising:
Image collection module, for by pre-set image acquisition device, obtaining default after receiving phonetic control command
The phonetic control command sender at position issues the facial information when phonetic control command；
Extraction module, for extracting defeated characteristics of image from the facial information, as the facial characteristics.
Optionally, described device further include:
Resolution unit obtains the language of the phonetic control command for carrying out instruction parsing to the phonetic control command
Justice control information, described instruction parsing include by default natural language processing operation；
The transmission unit, specifically for the semantic control information and the subscriber identity information to be sent to cloud and put down
Platform.
Optionally, described device further include:
Second determination unit, for determining whether the phonetic control command is provided with encryption requirements；
Encryption unit, for when determining described instruction there are when encryption requirements, then to the phonetic control command and user
Identity information is encrypted.
Optionally, described device further include:
First output unit, for exporting the first prompt information, institute's predicate to user when receiving voice input instruction
Sound typing instruction is that the preset operator's identity for preparing typing voice control, biological characteristic and its voice operating of being used to indicate is weighed
The instruction of limit, first prompt information are used to indicate user and input subscriber identity information and biological characteristic；
Unit is established, the biological characteristic and subscriber identity information inputted for receiving the user based on prompt information, and
Establish the corresponding relationship between the subscriber identity information and the biological characteristic；
Second output unit, for inputting the second prompt information to user, second prompt information is used to indicate user
Typing corresponds to the voice operating permission of the subscriber identity information；
The transmission unit, is also used to receive the voice operating permission, and by the voice operating permission and described right
It should be related to and be sent to cloud platform.
Optionally, described device further include:
Confirmation unit, for confirming the corresponding Permission Levels information of the subscriber identity information to user, and by the power
Limit level information is sent to cloud platform, and the Permission Levels are administrator or operator.
Optionally, the administrator, which has, to the voice operating permission that operator has modifies, adds and deletes
Permission, described device further include:
Permission control unit, for when receiving permission control instruction, determining the permission control instruction sender
Subscriber identity information, and the subscriber identity information of the permission control instruction sender and the permission control instruction are sent to
Cloud platform, to confirm that the subscriber identity information of the permission control instruction sender has administrator when the cloud platform
When permission, permission operation behavior is carried out according to the permission control instruction, the permission operation behavior includes the voice to user
Operating right is modified, adds and is deleted.
Optionally, the true permission control unit includes:
Determining module for obtaining the mobile terminal identification code of user's input, and determines the mobile end of user's input
Hold identification code and the mobile terminal identification code built in the mobile terminal whether consistent, the mobile terminal identification code goes out for equipment
The exclusive identification code added when factory；
First processing module, for if it is determined that built in the mobile terminal identification code and the mobile terminal of user input
Mobile terminal identification code it is consistent, then obtain the biological characteristic of the permission control instruction sender, and close according to characteristic identity
System, determines the subscriber identity information of the corresponding biological characteristic, includes each user identity letter in the characteristic identity relationship
Cease corresponding biological characteristic.
Second processing module, for if it is determined that built in the mobile terminal identification code and the mobile terminal of user input
Mobile terminal identification code it is inconsistent, then ignore the permission control instruction.
Optionally, described device further include:
Computing unit calculates the inclined of user biological feature for comparing according to the biological characteristic and default biological characteristic
Shifting amount；
Third determination unit, for determining whether user's sign is normal according to the biological characteristic offset；
Third output unit, for when user's sign exception, Xiang Yunduan platform to send mentioning for user's sign exception
Show information, and exports information warning to user.
4th aspect according to the present invention, provides a kind of phonetic controller of smart machine, is applied to cloud platform,
Include:
First receiving unit, for receiving phonetic control command and subscriber identity information from mobile terminal；
Matching unit, for according to the subscriber identity information, the voice operating of the corresponding subscriber identity information of matching
Permission；
Transmission unit is used for according to the voice operating permission and the phonetic control command, to the correspondence voice control
The equipment of system instruction sends control instruction, so that the equipment executes the corresponding voice control after receiving the control instruction
Make the operation behavior of instruction.
Optionally, the matching unit includes:
Module is obtained, for obtaining identity authority relationship, it includes user identity that the identity authority relationship, which is preset,
The mapping relations of information and corresponding voice operating permission；
Determining module, for determining the voice operating of the corresponding subscriber identity information according to the identity authority relationship
Permission.
Optionally, first receiving unit includes:
First receiving module, for receiving semantic control information and subscriber identity information from mobile terminal；
The transmission unit, comprising:
First sending module, for generating the control of the corresponding semantic control information according to the semantic control information
Instruction, and send the control instruction in the corresponding equipment of the semantic control information.
Optionally, first receiving unit includes:
Second receiving module, for receiving encrypted treated phonetic control command and user identity letter from mobile terminal
Breath；
The transmission unit, comprising:
Second sending module, for according to decryption rule, the phonetic control command after the encryption to be decrypted,
Phonetic control command after being decrypted generates institute based on the phonetic control command after the voice operating permission and the decryption
Control instruction is stated, and is sent in equipment.
Optionally, described device further include:
Second receiving unit, it is described right for receiving the voice operating permission and corresponding relationship of user's typing from mobile terminal
Should be related to include subscriber identity information and corresponding biological characteristic；
Storage unit, for being protected according to subscriber identity information by the voice operating permission and the corresponding relationship
It deposits, to carry out the matching of voice operating permission when receiving phonetic control command from mobile terminal.
Optionally, described device further include:
Third receiving unit, for limiting level information from mobile-terminated retake the power, and according to the Permission Levels information preservation
Into the corresponding relationship of corresponding subscriber identity information, the Permission Levels are administrator or operator.
Optionally, the administrator, which has, to the voice operating permission that operator has modifies, adds and deletes
Permission, described device further include:
First determination unit, for when from it is mobile-terminated receive permission control instruction when, according to the subscriber identity information
And the corresponding relationship determines the Permission Levels of the subscriber identity information；
First execution unit, for being referred to according to permission control when determining the Permission Levels is the administrator
It enables and executes corresponding permission operation behavior, the permission operation behavior includes modifying, adding to the voice operating permission of user
Add and deletes；
Second execution unit for when determining the Permission Levels is the operator, and determines permission control
When instruction operates for the permission for the sender to permission control instruction, permission is executed according to the permission control instruction
Operation behavior, conversely, then ignoring the permission control instruction.
Optionally, described device further include:
Second determination unit, for determining user identity feature according to the subscriber identity information,
Third determination unit determines the corresponding user of the subscriber identity information for being based on the user identity feature
Group, the user group are pre-set according to classification based on variety classes user identity feature；
First feedback unit, for according to the corresponding user group of subscriber identity information, Xiang Suoshu mobile terminal feedback to be corresponded to
The pushed information of user group.
Optionally, described device further include:
4th receiving unit, for receiving prompt information from mobile terminal, the prompt information is used to indicate user's sign
There are exceptions；
Second feedback unit, for obtaining user's sign extremely corresponding reason and solution according to the prompt information
Certainly scheme feeds back to mobile terminal as sign exception handling information, and by the sign exception handling information.
5th aspect according to the present invention, provides a kind of speech control system of smart machine, comprising:
Mobile terminal for receiving phonetic control command, and obtains institute's predicate after receiving the phonetic control command
The biological characteristic of sound control instruction sender determines the user of the phonetic control command sender according to the biological characteristic
The subscriber identity information and the phonetic control command are sent to cloud platform by identity information；
The cloud platform end, for receiving phonetic control command and subscriber identity information from the mobile terminal, according to institute
Subscriber identity information is stated, matching corresponds to the voice operating permission of the subscriber identity information, according to the voice operating permission, and
The phonetic control command sends control instruction to the equipment of the correspondence phonetic control command.
6th aspect according to the present invention, provides a kind of electronic equipment, including memory, processor and communication bus；
The memory and the processor pass through the communication bus communication connection；
Computer executable instructions are stored in the memory, the processor is executable for executing the computer
Instruction, for realizing the sound control method for the smart machine that first aspect of the present invention or the second invention provide.
7th aspect according to the present invention, provides a kind of computer readable storage medium, the computer-readable storage
Media storage has a computer executable instructions, the computer executable instructions when executed, for realizing the present invention first
The sound control method for the smart machine that a aspect or second aspect provide.
Sound control method, device, system and the electronic equipment of a kind of smart machine provided by the invention, with the prior art
In by voice can to smart machine carry out voice control compare, the present invention mobile terminal by first receive voice control
It instructs, and obtains the biological characteristic of the phonetic control command sender, then, root after receiving the phonetic control command
According to the biological characteristic, the subscriber identity information of the phonetic control command sender is determined, finally, the user identity is believed
Breath and the phonetic control command are sent to cloud platform；Platform is referred to by receiving voice control from mobile terminal first beyond the clouds
It enables and then subscriber identity information according to the subscriber identity information, matches the voice operating of the corresponding subscriber identity information
Permission is sent according to the voice operating permission and the phonetic control command to the equipment of the correspondence phonetic control command
Control instruction.So as to according to the interaction between mobile terminal and cloud platform, biological characteristic when using phonetic order come into
The confirmation of row user identity, and the phonetic control command is executed according to the corresponding voice operating permission of the identities match of user,
Realize a kind of smart machine sound control method based on user identity come confirmation operation permission thereby executing phonetic control command,
It avoids and works as the problem of non-permission personnel carry out smart machine control, then ensure when extraneous non-family safe user is in family
Smart machine carries out voice control and existing safety problem, improves the voice control of the smart machine including smart home
The safety of process processed.In addition, can be made in this way by carrying out the confirmation process setting of subscriber identity information in mobile terminal
When interacting during proper sound control method there are multiple mobile terminal executions with cloud platform, user can will confirm that
The process of identity is executed in mobile terminal side, so that data processing pressure of the cloud platform when carrying out this method has been shared,
Reduce the data processing pressure of cloud platform.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.
Fig. 1 is a kind of voice control side of the smart machine applied to mobile terminal provided according to one embodiment of the application
The implementation flow chart of method；
Fig. 2 is a kind of voice control side of the smart machine applied to cloud platform provided according to one embodiment of the application
The implementation flow chart of method；
Fig. 3 be provided according to one embodiment of the application it is a kind of applied to mobile terminal and the smart machine of cloud platform
The implementation flow chart of sound control method；
Fig. 4 is a kind of voice control dress of the smart machine applied to mobile terminal provided according to one embodiment of the application
The structural schematic diagram set；
Fig. 5 is the voice control for being applied to the smart machine of mobile terminal according to the another kind that one embodiment of the application provides
The structural schematic diagram of device；
Fig. 6 is a kind of voice control dress of the smart machine applied to cloud platform provided according to one embodiment of the application
The structural schematic diagram set；
Fig. 7 is the voice control for being applied to the smart machine of cloud platform according to the another kind that one embodiment of the application provides
The structural schematic diagram of device；
Fig. 8 is a kind of structural schematic diagram of the speech control system of the smart machine provided according to one embodiment of the application；
Fig. 9 is the structural schematic diagram of the electronic equipment provided according to one embodiment of the application.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below with reference to accompanying drawings in more detail
The exemplary embodiment of the disclosure is described.Although showing the exemplary embodiment of the disclosure in attached drawing, it being understood, however, that can
It should not be limited by the embodiments set forth herein with realizing the disclosure in a variety of manners.On the contrary, provide these embodiments be for
It can thoroughly understand the disclosure, and the scope of the present disclosure can be fully disclosed to those skilled in the art.
The embodiment of the invention provides a kind of sound control methods of smart machine, are applied to mobile terminal, the method
For improving the safety for carrying out voice control to smart machine, as shown in Figure 1, which comprises
101, phonetic control command is received, and obtains the phonetic control command after receiving the phonetic control command
The biological characteristic of sender.
Wherein, the biological characteristic includes at least one of vocal print feature, iris feature and facial characteristics.
In embodiments of the present invention, after receiving phonetic control command, then explanation currently needs to carry out voice control, base
When the existing voice control to smart machine, there is a problem of that safety is lower, phonetic control command is received in this step
Afterwards, then also need to carry out the sender to current speech control instruction the acquisition of biological characteristic.Wherein, which can be with
Being interpreted as can be to distinguish the related indication of the organism of user.
Here, the biological characteristic can be vocal print feature, wherein vocal print refers to the carrying speech that electricity consumption acoustic instrument is shown
The sound wave spectrum of language information.Modern scientific research shows that vocal print not only has specificity, but also has the characteristics of relative stability.
After adult, the sound of people can keep stablizing relatively for a long time constant.It is demonstrated experimentally that no matter talker is deliberately to imitate other people sound
And the tone, or whisper and softly talk, even if imitating remarkably true to life, vocal print is but constant always.Therefore, based on the tool of vocal print
There is the characteristics of uniqueness, the biological characteristic that can be used as the identity of confirmation user obtains.In addition, the biological characteristic can also be with
For iris feature, wherein iris is the annular formations in human eye between black pupil and white sclera, and it includes have very
The minutia of multiphase mutually staggered spot, filament, coronal, striped, crypts etc..Iris is after prenatal development stage is formed, In
It will be to maintain constant in its entire life course, the uniqueness of iris feature determined based on features described above, while also determining
The uniqueness of identification.It therefore, can be using the iris feature of eye as everyone identification object.Meanwhile institute
Stating biological characteristic can be facial characteristics, wherein facial characteristics identification is to carry out identification based on facial feature information of people
A kind of biological identification technology, image or video flowing containing face can be usually acquired with video camera or camera, and automatic
Detection and tracking face in the picture.In general a series of the relevant technologies that face recognition is carried out to the face detected, lead to
Often it is also referred to as Identification of Images or face recognition.
Therefore in embodiments of the present invention may be used based on the uniqueness that facial characteristics, vocal print feature, iris feature have
Choose above-mentioned any one or a variety of foundations being combined as user identification confirmation.Therefore, it can choose in this step
Any one of the above a variety of is obtained.
102, according to the biological characteristic, the subscriber identity information of the phonetic control command sender is determined.
After getting the biological characteristic of user, it is based on biological characteristic feature with uniqueness, therefore, used can be somebody's turn to do
Biological characteristic determines the identity of the sender of current speech control instruction, then obtains the relevant information of the user, specifically,
The identity information of active user can be determined based on the biological characteristic.Here, for determining user identity based on biological characteristic
The process of information can be compared by preset biological characteristic and the biological characteristic currently got, so that it is determined that currently
Biological characteristic it is consistent with which default biological characteristic, so that it is determined that the identity information of current phonetic order sender.Specifically
, the characteristics of based on different biological characteristics, it can include but is not limited to mode as the example shows for method of determination herein
It carries out, for example, when biological characteristic is vocal print feature, then it in this step can be each pre- by being obtained from preset audio library
The user of first typing and its corresponding audio-frequency information, and determine current vocal print feature and the audio-frequency information phase of which user
Match, so that it is determined which user is current phonetic control command sender correspond to, then determines the user identity of active user
Information.
103, the subscriber identity information and the phonetic control command are sent to cloud platform.
It, then can used step after the identity information that step 102 has determined the sender of current speech control instruction
The subscriber identity information and phonetic control command are sent to cloud platform by rapid method.Specifically, its sending method can be with base
It is carried out in existing any instruction transmission mode, certainly, safety when in order to ensure instruction transmission avoids intercepted steal
The problems such as, here, can also the subscriber identity information be packaged and be encrypted together with phonetic control command, so that it is guaranteed that hair
Pass through the safety of journey.
The embodiment of the invention also provides a kind of sound control methods of smart machine, are applied to cloud platform, the side
Method is used to improve the safety for carrying out smart machine voice control, as shown in Figure 2, which comprises
201, phonetic control command and subscriber identity information are received from mobile terminal.
After mobile terminal has sent subscriber identity information and phonetic control command, then can by the method for this step,
Carry out the reception of the phonetic control command and subscriber identity information.Specific reception mode can choose any mode and carry out,
But ensure that receive process described in the embodiment of the present invention will send subscriber identity information with the mobile terminal in previous embodiment
And the process of phonetic control command is corresponding.For example, when it is aforementioned be in embodiment mobile terminal send when also to voice control
When instruction and subscriber identity information carry out packaging ciphering, then this step also needs the decryption according to corresponding cipher mode when receiving
Operation is decrypted to received phonetic control command and subscriber identity information in mode.
202, according to the subscriber identity information, the voice operating permission of the corresponding subscriber identity information of matching.
It in embodiments of the present invention, include corresponding different user identity information and voice operating power in the cloud platform
The corresponding relationship of limit, therefore, when receiving phonetic control command, it is also necessary to carry out the language to whether the user of the instruction has
The permission of sound control is judged, specifically, can match the subscriber identity information institute according to the subscriber identity information for it
The voice operating permission having.For example, when the subscriber identity information for receiving mobile terminal transmission is " user A ", then from cloud
The operating right that the corresponding user A is found in the user right saved in platform, when user A has control washing machine, control
It is then that it matches the corresponding voice operating power of user A after finding user A when the permission of sweeping robot and control electronics kitchen range
Limit.
203, according to the voice operating permission and the phonetic control command, to the correspondence phonetic control command
Equipment sends control instruction, so that the equipment executes the corresponding phonetic control command after receiving the control instruction
Operation behavior.
After the corresponding voice operating permission of subscriber identity information has been determined, current speech instruction is in fact had determined
Sender is therefore can be based on the voice control for the smart machine that it has with the permission for controlling which kind of smart machine
The smart machine that permission and its phonetic control command can control it sends corresponding control instruction, to carry out smart machine
Voice control.
For example, when user A has control washing machine, control sweeping robot and the voice control permission for controlling electronics kitchen range
When, and the phonetic control command is when opening electronics kitchen range, since user A has the voice control permission of electronics kitchen range, then
The open command of electronics kitchen range can be generated and be sent to electronic range tool, to realize that the electronics kitchen range based on voice control are opened
Operation.
A kind of sound control method of smart machine provided in this embodiment, can be to intelligence with voice is passed through in the prior art
Energy equipment carries out voice control and compares, and the present invention passes through in mobile terminal receives phonetic control command first, and receiving
The biological characteristic that the phonetic control command sender is obtained after phonetic control command is stated, then, according to the biological characteristic, really
The subscriber identity information of the fixed phonetic control command sender, finally, by the subscriber identity information and the voice control
Instruction is sent to cloud platform；Platform is by receiving phonetic control command and user identity letter from mobile terminal first beyond the clouds
Breath, then, according to the subscriber identity information, the voice operating permission of the corresponding subscriber identity information of matching, according to described
Voice operating permission and the phonetic control command send control instruction to the equipment of the correspondence phonetic control command.To
Can be according to the interaction between mobile terminal and cloud platform, biological characteristic when using phonetic order carries out user identity really
Recognize, and execute the phonetic control command according to the corresponding voice operating permission of the identities match of user, realizes a kind of based on use
Family identity carrys out confirmation operation permission thereby executing the smart machine sound control method of phonetic control command, avoids when non-permission
Personnel carry out the problem of smart machine control, then ensure when extraneous non-family safe user carries out language to the smart machine in family
Sound control system and existing safety problem, improve the safety of the speech control process of the smart machine including smart home
Property.In addition, can be made in this way by carrying out the confirmation process setting of subscriber identity information in mobile terminal when there are multiple
When interacting during the mobile terminal execution sound control method with cloud platform, it can will confirm that the process of user identity exists
Mobile terminal side executes, to share data processing pressure of the cloud platform when carrying out this method, it is flat to reduce cloud
The data processing pressure of platform.
Further, according to method shown in Fig. 1 and 2, another embodiment of the invention additionally provides a kind of intelligence and sets
Standby sound control method is applied in mobile terminal and cloud platform, to the further refinement to aforementioned exemplary and illustrates,
Specifically, as shown in Figure 3, wherein based in the speech control process of smart machine, actually can also including original state
The process of lower typing user speech control information, is managed voice control based on Permission Levels the process of voice control
Many processes of process, the feedback that recommendation information is carried out based on user related information and the detection of user's sign, here, for upper
Stating implementation process can be as described in the following Examples, and wherein this method specifically includes that
301, mobile terminal exports the first prompt information to user when receiving voice input instruction.
Wherein, the voice input instruction is the preset operator's identity for being used to indicate preparation typing voice control, life
The instruction of object feature and its voice operating permission, first prompt information are used to indicate user and input subscriber identity information and life
Object feature.This step needs to carry out the Input Process that voice control carries out relevant information before it is to be understood that working as user,
In, the voice input instruction can be pre-set voice, in this way, when user issues the pre-set voice, then
The execution system of the present embodiment the method can be made when receiving the voice, determine that user currently needs to carry out voice input
Operation.In addition, the way of output can include but is not limited to when to user's input for indicative first prompt information
Voice, can any mode such as interaction figure picture carry out.Purpose based on the method described in the embodiment of the present invention is solution pair
Smart machine carries out the safety issue in speech control process, therefore, when mobile terminal receives voice input instruction,
Need to prompt the user with its typing for needing to carry out relevant information, specifically, the information of suggested user's input in this step
Including at least the biological characteristic of active user and the identity information of the user.
302, mobile terminal receives the biological characteristic and subscriber identity information that the user is inputted based on prompt information, and builds
Found the corresponding relationship between the subscriber identity information and the biological characteristic.
Wherein the biological characteristic includes following one or more features, wherein can for vocal print feature, iris feature and
Facial characteristics, it is consistent with the description in step 101 in previous embodiment for the description of above-mentioned several features at this, herein no longer
It repeats.Meanwhile after receiving the biological characteristic and subscriber identity information of user's input, based on being the presence of corresponding close therebetween
System, therefore, it is also desirable to carry out the foundation of corresponding relationship to the two according to the method for this step.Specifically, the corresponding relationship can
A kind of mapping relations are thought, wherein the biological characteristic of subscriber identity information and its typing comprising each user.Also, in order to
Safety and convenience are further ensured that in practical application, each user is in the corresponding biological characteristic of typing subscriber identity information
It can be not limited to a kind of biological characteristic, or the combination of a variety of biological characteristics.For example, user A is in its user identity of typing
When information a, the iris feature X and facial characteristics F in its biological characteristic can be inputted simultaneously, in this way, subsequent special based on biology
Sign carry out subscriber identity information identification when, can choose in both biological characteristics any one progress, thus improve it is convenient
Property, certainly, in order to ensure safety, it can also be arranged to when needing to confirm subscriber identity information while carry out two kinds of biology spies
The identification of sign.Here, can be configured based on any of the above-described kind of mode, it is not limited here, can be arranged according to actual needs.
But it should be recognized that in the identity information and biological characteristic for being actually typing user, the biological characteristic of input
Type and quantity need with it is subsequent carry out identification process in setting it is consistent.For example, working as method described in the embodiment of the present invention
Execution system carry out subscriber identity information determination process in need two kinds of biological characteristics of vocal print feature and iris feature when, then
This step needs both biological characteristics of typing simultaneously, to ensure the realization of subsequent determining function.
303, mobile terminal inputs the second prompt information to user.
Wherein, second prompt information is used to indicate the voice operating power that user's typing corresponds to the subscriber identity information
Limit.After the subscriber identity information and its biological characteristic of user's typing, it is also necessary to carry out it and be able to carry out voice operating permission
It determines, therefore, the second prompt information can be exported to user by mobile terminal in this step, so that user being capable of basis
The input and setting of second prompt information progress voice operating permission.
304, mobile terminal receives the voice operating permission, and the voice operating permission and the corresponding relationship are sent out
It send to cloud platform.
After user has input the voice operating permission that it needs to carry out, then it can will be received by current mobile terminal
The voice operating permission and the corresponding relationship established of abovementioned steps 302 be sent to cloud platform.Wherein, the present invention is implemented
Voice operating permission in example can be multiple permissions of multiple equipment, for example, the voice operating permission may include to intelligence
TV is opened and closed, and the operating rights such as is opened, closed and suspended to sweeping robot.Here, for institute
The permission quantity and type for including in predicate sound operating right do not do specific restriction, can be according to the actually required progress of user
It is corresponding to choose.In addition, can be carried out according to any mode for the sending method chosen when the transmission, for example, optional
Take wireless transfer channel to be sent the voice operating permission and the corresponding relationship,
305, cloud platform receives the voice operating permission and corresponding relationship of user's typing from mobile terminal.
After being sent the voice operating permission and corresponding relationship of user based on 304 mobile terminal of abovementioned steps, then
Platform needs to receive voice operating permission and corresponding relationship beyond the clouds, specifically, the mode of reception and abovementioned steps 304
Sending method is consistent.
306, cloud platform is protected the voice operating permission and the corresponding relationship according to subscriber identity information
It deposits.
After when cloud, platform receives voice operating permission and corresponding relationship, based on including user identity in corresponding relationship
Information, and when the above- mentioned information sent in the platform of cloud there are multiple users, it, then can be according in order to avoid obscuring
The method of this step saves above-mentioned voice operating permission, biological characteristic, subscriber identity information according to user.Specifically,
User's operation permission table can be constructed, wherein include the mark (ID or name) of each user, it is each to identify corresponding user
Identity information, biological characteristic and its voice operating permission having.For example, its table can be as shown in table 1 below:
Table 1
In this way, by saving above-mentioned subscriber identity information, biological characteristic and voice operating permission according to user, energy
Enough ensure the accuracy of saved information, carries out voice operating power when receiving phonetic control command from mobile terminal to be subsequent
The matching of limit, lays a good foundation.
In addition, in embodiments of the present invention, after when cloud, platform receives the voice operating permission, can also pass through
Mobile terminal carries out the confirmation of Permission Levels belonging to user, so as to the subsequent progress for needing to carry out voice operating permission as user
The modification that can carry out permission when adjustment based on the Permission Levels of user, specifically can be as shown in following step 307.
307, mobile terminal confirms the corresponding Permission Levels information of the subscriber identity information to user, and by the permission
Level information is sent to cloud platform.
Based in the actual operation process, it is understood that there may be the case where modifying to the voice operating permission of user is needed,
And accuracy when in order to ensure modification, while certain user being avoided to modify the permission that it did not had originally.For example, child user
Do not have the voice operatings permissions such as control electronics kitchen range, washing machine.It therefore in embodiments of the present invention, can also be according to mobile whole
It holds to user and confirms the corresponding Permission Levels information of current user identities information, wherein the Permission Levels can be divided into management
Member or operator.It may insure that Administrator Level can carry out the control of voice operating permission to the user of other operation ranks in this way
System, to make subsequent authority modification that there is certain safety.
308, cloud platform limits level information from mobile-terminated retake the power, and according to the Permission Levels information preservation to correspondence
Subscriber identity information corresponding relationship in.
, then can be by under the Permission Levels information preservation to corresponding user identifier after being connected to Permission Levels information, this
Sample can make the Permission Levels that user is also saved in saved corresponding relationship, specifically, showing according to abovementioned steps
Example, in this step, specific operating result can be as described in Table 2:
Table 2
309, mobile terminal receives phonetic control command, and the voice is obtained after receiving the phonetic control command
The biological characteristic of control instruction sender.
In actual speech control process, when being connected to phonetic control command, the identity based on each user is different,
And there may be different operating rights by the user of different identity, therefore, need to refer to receiving voice control in this step
After order, the biological characteristic of the sender of present instruction is received by mobile terminal.Wherein, biological characteristic can be facial characteristics, sound
Therefore any one or more of combination such as line feature and iris feature is based on different biological features, during acquisition,
Mode also with its biological characteristic difference and change, can specifically carry out in the following manner:
When the biological characteristic is iris, then acquisition modes can be with are as follows: after receiving phonetic control command, by presetting
Iris collection device obtains the iris when phonetic control command sender of predeterminated position issues the phonetic control command
Feature.
When the biological characteristic is for facial characteristics, then acquisition modes can be with are as follows: first after receiving phonetic control command
First, by pre-set image acquisition device, the phonetic control command sender for obtaining predetermined position issues the voice control
Facial information when system instruction.Then, defeated characteristics of image is extracted from the facial information, as the facial characteristics.
When the biological characteristic is for vocal print feature, then acquisition modes can be through the voice messaging in phonetic order,
Voiceprint extraction is carried out, to obtain the vocal print feature of current speech control instruction sender.
It is carried out here, any existing way can be chosen for the practical manner for obtaining above-mentioned biological characteristic,
In the type of acquired biological characteristic, quantity can with system when actually confirming subscriber identity information required type,
Quantity is corresponding.
310, mobile terminal determines the user identity letter of the phonetic control command sender according to the biological characteristic
Breath.
It, can be according to when determining the user identity of phonetic control command sender specifically, based on different biological characteristics
Different biological characteristics carries out:
On the one hand, it when the biological characteristic for determining the phonetic control command sender is vocal print feature, then obtains first
The default vocal print relationship, the default vocal print relationship be prerecord be corresponding with reflecting for different user and its corresponding vocal print
Penetrate relationship.Then, it according to the vocal print feature extracted in the phonetic control command, is determined in default vocal print relationship described in corresponding to
The user identifier of vocal print feature.Finally, determining the user identity of the phonetic control command sender according to the user identifier
Information.
On the other hand, it when determining biological characteristic is iris feature, then according to the iris feature of acquisition, is closed in default iris
The subscriber identity information of the corresponding iris feature is determined in system, the default iris relationship includes each subscriber identity information
Corresponding iris feature.
Another aspect, then according to the facial characteristics of acquisition, is closed when determining biological characteristic is facial characteristics in default face
Determine the subscriber identity information of the corresponding facial characteristics in system, the face relationship includes each user's face feature and right
The subscriber identity information answered.
311, mobile terminal carries out instruction parsing to the phonetic control command, obtains the semanteme of the phonetic control command
Control information.
Based in practical operation, corresponding a word of phonetic control command of user's input, and in not whole word entirely
Portion's text is all useful, wherein may only have part of semantic is for carrying out voice control, other may be modal particle etc.
At this moment meaningless vocabulary can entirely be instructed by the method for this step by parsing to phonetic control command
In semantic component, i.e., the described semantic control information.Wherein, when parsing to instruction, mode can be based on preset
Natural language processing technique is operated.In this way, parsing by this step to phonetic control command, semantic control information, energy are obtained
Enough ensure to reject meaningless vocabulary in phonetic control command, so that data volume is less when subsequent transmission, when reducing data transmission
Pressure.In addition, can then skip this step when without carrying out instruction parsing operation and directly execute step 312.
312, mobile terminal determines whether the phonetic control command is provided with encryption requirements.
In the actual operation process, some users are in the considerations of data privacy, it is also possible to need in voice control
It is encrypted in the transmission process of instruction, for this, whether can determine current speech control instruction according to the setting of user preset
It is provided with encryption requirements.When determining the not set encryption requirements of user, then step 314 can be directly executed.
It should be noted that in the actual operation process, when the not set encryption requirements option of user, then can skip this step
Rapid and step 313, directly execution step 314.
313, mobile terminal is when determining described instruction there are when encryption requirements, then to the phonetic control command and user's body
Part information is encrypted；
When pre-setting encryption requirements with book, then illustrate instruction that user needs to assign it and subsequent operation into
Therefore the relevant encryption of row can encrypt subscriber identity information and phonetic control command together in this step
Processing, to ensure the privacy of user data.
314, the subscriber identity information and the phonetic control command are sent to cloud platform by mobile terminal.
Based on the difference of abovementioned steps mode of operation, there is also parts to distinguish for specific executive mode in this step, tool
Body, after abovementioned steps perform the operation of parsing described in step 311, then this step specifically: by the semantic control letter
Breath and the subscriber identity information are sent to cloud platform.
In addition, after abovementioned steps perform encryption described in step 312-313, then this step specifically: by institute
It states encrypted subscriber identity information and phonetic control command is sent to cloud platform.
315, cloud platform receives phonetic control command and subscriber identity information from mobile terminal.
After mobile terminal has sent phonetic control command and subscriber identity information, it can be put down by this step by cloud
Platform is received, wherein received mode is without limitation, but is needed corresponding with the mode that abovementioned steps mobile terminal is sent.Example
Such as, when mobile platform is when sending phonetic control command and when subscriber identity information has carried out encryption to above- mentioned information, then this step
It needs to be decrypted using manner of decryption corresponding with mobile terminal cipher mode after rapid reception.
It is semantic control transmitted by the mobile terminal in addition, the difference based on mobile terminal mode of operation in abovementioned steps
It, then can be in this step receive process when information processed specifically: receive semantic control information and user identity letter from mobile terminal
Breath.
When being encrypted treated phonetic control command and subscriber identity information transmitted by the mobile terminal, then this step
It can be in rapid receive process specifically: receive encrypted treated phonetic control command and user identity letter from mobile terminal
Breath.
316, cloud platform is according to the subscriber identity information, the voice operating power of the corresponding subscriber identity information of matching
Limit.
When receiving subscriber identity information and phonetic control command, then illustrate that active user needs to carry out smart machine
Voice control, but based on some users, there is no the permissions of voice control, therefore, before cloud platform carries out execution operation, also
The permission for whether having operation to the user of currently received phonetic control command according to the method for this step is needed to carry out
Confirmation, specifically, its corresponding voice operating permission of the subscriber identity information unique match can be based on.
Specifically, this step may include: firstly, obtaining identity authority relationship, the identity authority relationship when being executed
For it is preset include subscriber identity information and corresponding voice operating permission mapping relations.Then, according to the identity authority
Relationship determines the voice operating permission of the corresponding subscriber identity information.
Based on example described in abovementioned steps, when preserving identity authority relationship as shown in Table 2 in the cloud platform
When table, then when being " subscriber identity information a " with identity information, then it can be based on table 2, determine the language that active user A has
Sound operating right are as follows: unlatching/closing smart television；Unlatching/closing sweeping robot；Unlatching/closing electronics kitchen range.
317, cloud platform is according to the voice operating permission and the phonetic control command, to the correspondence voice control
The equipment of system instruction sends control instruction, so that the equipment executes the corresponding voice control after receiving the control instruction
Make the operation behavior of instruction.
Specifically, corresponding to phonetic control command when determining that user exists based on the matched voice operating permission of step 316 institute
Operating right when, then illustrate that the voice operating of active user can execute, therefore, can be according to the method base of this step
Control instruction is sent to current smart machine in the phonetic control command, to be controlled.
Practical operation based on abovementioned steps, when the phonetic control command is semantic control information, then this step can
With are as follows: according to it is described it is semantic control information, generate the control instruction of the corresponding semantic control information, and by the control instruction
It is sent in the corresponding equipment of the semantic control information.
When the phonetic control command is by encrypted instruction obtained by encryption, then this step can be with are as follows: root
According to decryption rule, the phonetic control command after the encryption is decrypted, the phonetic control command after being decrypted, base
Phonetic control command after the voice operating permission and the decryption generates the control instruction, and is sent in equipment.
318, mobile terminal determines user's body of the permission control instruction sender when receiving permission control instruction
Part information, and the subscriber identity information of the permission control instruction sender and the permission control instruction are sent to cloud and put down
Platform.
In the actual operation process, there is likely to be the needs for needing to be configured permission and modify sometimes, at this time
It can be carried out based on permission control instruction.Specifically, the method as described in this step, when mobile terminal receives permission control
When instruction, then illustrate that user needs to be adjusted voice operating permission.As such, it is desirable to determine the user of present instruction sender
Identity information, and the permission control instruction and subscriber identity information are sent to cloud platform together to carry out subsequent operation.
In this way when the cloud platform confirms that the subscriber identity information of the permission control instruction sender has administrator right, root
Carry out permission operation behavior according to the permission control instruction, the permission operation behavior include to the voice operating permission of user into
Row modification, addition and deletion.
In order to during carrying out permission modification, it is ensured that the accuracy of operation avoids the possibility of maloperation, in the present invention
Determining that the detailed process of the subscriber identity information of the permission control instruction sender may include: in embodiment
Obtain the mobile terminal identification code of user's input, and determine the mobile terminal identification code of user input with it is described
Whether the mobile terminal identification code built in mobile terminal is consistent, wherein the mobile terminal identification code is that equipment is added when dispatching from the factory
Exclusive identification code.For example, the exclusive identification code can be IMEI (International Mobile Equipment
Identity, international mobile equipment identification number abbreviation IMEI) be international mobile equipment identification number abbreviation, be commonly called as " mobile phone string
Number ", " mobile phone string code ", " handset serial ", the code in GSM mobile network for identifying each independent mobile phone, quite
In the ID card No. of mobile phone.IMEI code is suitable for the mobile phone and iridium satellite satellite phone of GSM and WCDMA standard.
If consistent, the biological characteristic of the permission control instruction sender is obtained, and according to characteristic identity relationship, is determined
The subscriber identity information of the biological characteristic is corresponded to, includes that each subscriber identity information is corresponding in the characteristic identity relationship
Biological characteristic.If inconsistent, ignore the permission control instruction.In this way, the uniqueness based on the IMEI code, is determining user
When whether being that voice control permission to be carried out is modified, the input and judgement of the mobile terminal unique identification, energy can be passed through
Enough ensure modify operation really for equipment owner actual needs, and not false triggering the case where, meanwhile, also can be avoided hacker
Or malicious attack is to the modification bring risk of the voice operating permission of user.
319, cloud platform when from it is mobile-terminated receive permission control instruction when, according to the subscriber identity information and described
Corresponding relationship determines the Permission Levels of the subscriber identity information.
When cloud, platform has received permission control instruction, whens Permission Levels being had based on different users, is different
, for example administrator can modify and control to all users, and operator is only capable of controlling the operating right of itself
System.Or there is corresponding permission operating function by the user that the Permission Levels of different levels are arranged in preset rules.For example, institute
It states administrator and has the permission that the voice operating permission that operator has is modified, adds and deleted.
It wherein, can be according to different during the operation of subsequent execution permission based on different user right ranks
Permission Levels take corresponding step respectively: when the corresponding Permission Levels of subscriber identity information for determining the permission control instruction
When for administrator, step 320 is executed；When determining the corresponding Permission Levels of subscriber identity information is operator, then follow the steps
321。
320, cloud platform end is executed when determining the Permission Levels is the administrator according to the permission control instruction
Corresponding permission operation behavior；
Have the highest Permission Levels of system based on administrator, therefore, in embodiments of the present invention, when cloud platform determines
When the sender of current permission control instruction is administrator, have to any user carry out voice operating permission modify,
Therefore addition and the permission deleted can operate according to its permission and execute corresponding permission operation behavior.
321, cloud platform end is when determining the Permission Levels is the operator, and determines that the permission control instruction is
When permission for the sender to permission control instruction operates, permission operation row is executed according to the permission control instruction
For conversely, then ignoring the permission control instruction.
When determining user is operator, then illustrates that user only possesses and the permission of itself is controlled, it at this moment can basis
When the method for this step determines the operational order of active user for itself, then according to the corresponding permission operation row of the instruction execution
When determining present instruction is the permission operation for other people, then to ignore its instruction.To according to the sender to instruction
Whether instruction purposes is used to itself be judged, can be avoided the user for not having permission and carry out permission control to other users
Behavior, it is ensured that the safety that permission is modified in speech control process.
322, mobile terminal is compared according to the biological characteristic and default biological characteristic, calculates the offset of user biological feature
Amount.
In actual application, it after user has input relevant phonetic control command, is inputted every time based on user
There may be subtle differences for biological characteristic, and biology character can reflect the physical condition of user to a certain extent, in this way,
Comparison based on biological characteristic Yu default biology character can find the abnormal conditions of user identity, in time so that user is timely
Processing.Specifically, in this step, can be carried out by calculating the offset of biological characteristic.For example, when the life of user's input
When object feature is facial characteristics, then it can be based on user preset facial characteristics and currently compare, so that it is determined that therebetween
Offset.
323, mobile terminal determines whether user's sign is normal according to the biological characteristic offset.
Based on the size of biological characteristic offset, it is able to carry out whether user's sign normally judges, such as when determining face
The facial color of user is more than certain threshold than color displacement amount between the facial color of user in default facial characteristics in portion's feature
When value, then it can illustrate user's problem gloomy there is currently complexion, it is understood that there may be certain illnesss on body therefore can be with
Determine that user's sign is abnormal.
324, for mobile terminal when user's sign exception, Xiang Yunduan platform sends the prompt letter of user's sign exception
Breath, and information warning is exported to user.
Based on the judgement of abovementioned steps 323, when it is abnormal for determining user's sign, then illustrate the body of user there may be
The prompt information of active user's sign exception then can be sent to cloud platform according to the method for this step to this by problem, with
Just corresponding solution countermeasure is obtained.And information warning is inputted to user simultaneously.Wherein, it may include reflection in the prompt information
Offset between the biological characteristic and current biological feature and default biological characteristic of user's sign exception, it is, of course, also possible to
The information of the preparatory typing of the users such as the relevant information comprising other users, such as age, work.Here, believing for the prompt
The contents of the data for including in breath, type, quantity without limitation, can be chosen and setting according to actual needs.
325, cloud platform end receives prompt information from mobile terminal.
, can be consistent with the sending method of aforementioned mobile terminal in receive process, it is not limited here.
326, according to the prompt information, user's sign extremely corresponding reason and solution are obtained, as body
Exception handling information is levied, and the sign exception handling information is fed back into mobile terminal.
Based on prompt information to determine that it is abnormal that user's sign exists, therefore, when cloud, platform receives the prompt information
Afterwards, then the reason and solution of corresponding current sign exception can be obtained based on the prompt information, and by reason and solution party
Case is fed back as exception handling information to mobile terminal, so that user can learn that current sign is of the presence of an anomaly with reason and solution
Certainly scheme, it is ensured that the health of user identity.
For example, can then determine that there may be throat or throats by user when determining user's sign extremely is cacophonia
The problem of, at this moment, the available solution and reason to solve the above problems, wherein solution can be with are as follows: uses when determining
There are when unlatching/closing air cleaner permission in the voice control permission at family, then it is net air can be opened to user feedback
Change machine is to purify the suggestion of air as solution.
327, cloud platform end determines user identity feature according to the subscriber identity information.
In addition, based in speech control process, can also by carrying out the determination of identity to subscriber identity information, so as to
So as to provide corresponding recommendation information simultaneously during carrying out voice control for it.Specifically, in the process for determining identity
In, user identity feature can be determined based on the method for this step first.
328, cloud platform end group determines the corresponding user group of the subscriber identity information in the user identity feature.
Wherein, the user group is pre-set according to classification based on variety classes user identity feature.
After determining the identity characteristic of user, it can be formed by user group based on the user of different identity feature, determined
User group belonging to active user.For example, when determining subscriber identity information determines that the identity characteristic of user is male, 45 weeks
Year, it is married when, and in advance typing user group's middle-aged male group feature are as follows: 40-50 one full year of life；It is married；When male, then may be used
To determine that active user belongs to middle-aged male group.
329, according to the corresponding user group of subscriber identity information, Xiang Suoshu mobile terminal feeds back corresponding user group at cloud platform end
Pushed information.
Be based on different user groups there is different hobbies, for example, middle-aged male more concerned with football, house property,
Automobile and politics when, then can based on to user group determined by active user be middle-aged male when, be active user feedback
Related PUSH message about football, house property, automobile and politics.
In this way, corresponding recommendation information is fed back for it based on subscriber identity information by speech control process, it can
Ensure when user carries out voice control, while the associated recommendation information interested to it can also be got, so that being set to intelligence
When standby progress voice control, other information can be understood simultaneously, it is more convenient.
The sound control method of another kind smart machine provided by the invention, can be to intelligence with voice is passed through in the prior art
Energy equipment carries out voice control and compares, and the present invention passes through in mobile terminal receives phonetic control command first, and receiving
The biological characteristic that the phonetic control command sender is obtained after phonetic control command is stated, then, according to the biological characteristic, really
The subscriber identity information of the fixed phonetic control command sender, finally, by the subscriber identity information and the voice control
Instruction is sent to cloud platform；Platform is by receiving phonetic control command and user identity letter from mobile terminal first beyond the clouds
Breath, then, according to the subscriber identity information, the voice operating permission of the corresponding subscriber identity information of matching, according to described
Voice operating permission and the phonetic control command send control instruction to the equipment of the correspondence phonetic control command.To
Can be according to the interaction between mobile terminal and cloud platform, biological characteristic when using phonetic order carries out user identity really
Recognize, and execute the phonetic control command according to the corresponding voice operating permission of the identities match of user, realizes a kind of based on use
Family identity carrys out confirmation operation permission thereby executing the smart machine sound control method of phonetic control command, avoids when non-permission
Personnel carry out the problem of smart machine control, then ensure when extraneous non-family safe user carries out language to the smart machine in family
Sound control system and existing safety problem, improve the safety of the speech control process of the smart machine including smart home
Property.In addition, can be made in this way by carrying out the confirmation process setting of subscriber identity information in mobile terminal when there are multiple
When interacting during the mobile terminal execution sound control method with cloud platform, it can will confirm that the process of user identity exists
Mobile terminal side executes, to share data processing pressure of the cloud platform when carrying out this method, it is flat to reduce cloud
The data processing pressure of platform.
Further, according to above-mentioned Fig. 1 and Fig. 3 the method embodiment, another embodiment of the invention is additionally provided
A kind of phonetic controller of smart machine is applied to mobile terminal, as shown in figure 4, described device includes:
Acquiring unit 401 can be used for receiving phonetic control command, and obtain after receiving the phonetic control command
The biological characteristic of the phonetic control command sender, the biological characteristic include at least vocal print feature, iris feature and face
One of feature；
First determination unit 402 can be used for the biological characteristic obtained according to the acquiring unit 401, determine institute's predicate
The subscriber identity information of sound control instruction sender；
Transmission unit 403 can be used for the subscriber identity information and the voice for determining first determination unit 402
Control instruction is sent to cloud platform.
Optionally, as shown in figure 5, first determination unit 402 includes:
First determining module 4021 can be used for according to the vocal print feature extracted in the phonetic control command, default
Determine the user identifier of the corresponding vocal print feature in vocal print relationship, the default vocal print relationship is being corresponding with not of prerecording
With the mapping relations of user and its corresponding vocal print；
Second determining module 4022 can be used for the user identifier determined according to first determining module 4021, determine
The subscriber identity information of the phonetic control command sender.
Optionally, as shown in figure 5, first determination unit 402 further include:
Obtain module 4023, for when determine the phonetic control command sender biological characteristic be vocal print feature when,
The default vocal print relationship is obtained, so that first determining module 4021 determines user identifier.
Optionally, as shown in figure 5, first determination unit 402 includes:
Third determining module 4024 can be used for the iris feature according to acquisition, determines and corresponds in default iris relationship
The subscriber identity information of the iris feature, the default iris relationship include that the corresponding iris of each subscriber identity information is special
Sign；
The acquiring unit 401, comprising:
Iris obtains module 4011, can be used for after receiving phonetic control command, by presetting iris collection device, obtains
Iris feature when the phonetic control command sender of predeterminated position being taken to issue the phonetic control command.
Optionally, as shown in figure 5, first determination unit 402 includes:
4th determining module 4025 can be used for the facial characteristics according to acquisition, determines and corresponds in default facial relationship
The subscriber identity information of the facial characteristics, the face relationship includes each user's face feature and corresponding user identity
Information；
The acquiring unit 401, comprising:
Image collection module 4012, can be used for after receiving phonetic control command, by pre-set image acquisition device,
The phonetic control command sender of acquisition predetermined position issues the facial information when phonetic control command；
Extraction module 4013 can be used for obtaining in the facial information that module 4012 obtains from described image and extract defeated image
Feature, as the facial characteristics.
Optionally, as shown in figure 5, described device further include:
Resolution unit 404 can be used for carrying out instruction parsing to the phonetic control command, obtains the voice control and refers to
The semantic control information of order, described instruction parsing include by default natural language processing operation；
The transmission unit 403, can be specifically used for the semantic control information for obtaining the resolution unit 404 parsing and
The subscriber identity information is sent to cloud platform.
Optionally, as shown in figure 5, described device further include:
Second determination unit 405, is determined for whether the phonetic control command is provided with encryption requirements；
Encryption unit 406 can be used for determining described instruction there are when encryption requirements, then to institute when the second determination unit 45
It states phonetic control command and subscriber identity information is encrypted.
Optionally, as shown in figure 5, described device further include:
First output unit 407 can be used for when receiving voice input instruction, to user's output the first prompt letter
Breath, voice input instruction be it is preset be used to indicate the operator's identity for preparing typing voice control, biological characteristic and its
The instruction of voice operating permission, first prompt information are used to indicate user and input subscriber identity information and biological characteristic；
Unit 408 is established, can be used for receiving biological characteristic and user identity that the user is inputted based on prompt information
Information, and establish the corresponding relationship between the subscriber identity information and the biological characteristic；
Second output unit 409 can be used for inputting the second prompt information to user, and second prompt information is for referring to
Show that user's typing corresponds to the voice operating permission of the subscriber identity information；
The transmission unit 403, is also used to receive the voice operating permission, and by the voice operating permission and described
Corresponding relationship is sent to cloud platform.
Optionally, as shown in figure 5, the device, described device further include:
Confirmation unit 410 can be used for confirming to user the corresponding Permission Levels information of the subscriber identity information, and will
The Permission Levels information is sent to cloud platform, and the Permission Levels are administrator or operator.
Optionally, it modifies, add to the voice operating permission that operator has as shown in figure 5, stating administrator and having
And the permission deleted, described device further include:
Permission control unit 411 can be used for when receiving permission control instruction, determine the permission control instruction hair
Subscriber identity information out, and by the subscriber identity information of the permission control instruction sender and the permission control instruction
It is sent to cloud platform, to confirm that the subscriber identity information of the permission control instruction sender has when the cloud platform
When administrator right, permission operation behavior is carried out according to the permission control instruction, the permission operation behavior includes to user
Voice operating permission modify, add and delete.
Optionally, as shown in figure 5, the true permission control unit 411 includes:
Determining module 4111 can be used for obtaining the mobile terminal identification code of user's input, and determine user's input
Mobile terminal identification code and the mobile terminal identification code built in the mobile terminal it is whether consistent, the mobile terminal identification code
For the exclusive identification code added when equipment factory；
First processing module 4112 can be used for if it is determined that module 4111 determines the mobile terminal identification of user's input
Code is consistent with the mobile terminal identification code built in the mobile terminal, then the biology for obtaining the permission control instruction sender is special
Sign, and according to characteristic identity relationship, it determines the subscriber identity information of the corresponding biological characteristic, is wrapped in the characteristic identity relationship
Contain the corresponding biological characteristic of each subscriber identity information.
Second processing module 4113 can be used for if it is determined that module 4111 determines the mobile terminal identification of user's input
Code is inconsistent with the mobile terminal identification code built in the mobile terminal, then ignores the permission control instruction.
Optionally, as shown in figure 5, described device further include:
Computing unit 412 can be used for being compared according to the biological characteristic and default biological characteristic, it is special to calculate user biological
The offset of sign；
Third determination unit 413 can be used for the biological characteristic offset obtained according to the computing unit 412, determine
Whether user's sign is normal；
Third output unit 414 can be used for when the third determination unit 413 determines user's sign exception, Xiang Yun
It holds platform to send the prompt information of user's sign exception, and exports information warning to user.
Further, according to above-mentioned Fig. 2 and Fig. 3 the method embodiment, another embodiment of the invention is additionally provided
A kind of phonetic controller of smart machine is applied to cloud platform, as shown in fig. 6, described device includes:
First receiving unit 601 can be used for receiving phonetic control command and subscriber identity information from mobile terminal；
Matching unit 602 can be used for according to the received subscriber identity information of first receiving unit 601, matching pair
Answer the voice operating permission of the subscriber identity information；
Transmission unit 603 can be used for the voice operating permission and described first determined according to the matching unit 602
The received phonetic control command of receiving unit 601 sends control instruction to the equipment of the correspondence phonetic control command, with toilet
State the operation behavior that equipment executes the corresponding phonetic control command after receiving the control instruction.
Optionally, as shown in fig. 7, the matching unit 602 includes:
Module 6021 is obtained, can be used for obtaining identity authority relationship, the identity authority relationship, which is preset, includes
The mapping relations of subscriber identity information and corresponding voice operating permission；
Determining module 6022 can be used for determining what corresponding acquisition module 6021 obtained according to the identity authority relationship
The voice operating permission of the subscriber identity information.
Optionally, as shown in fig. 7, first receiving unit 601 includes:
First receiving module 6011 can be used for receiving semantic control information and subscriber identity information from mobile terminal；
The transmission unit 603, comprising:
First sending module 6031 can be used for generating the corresponding semantic control according to the semantic control information and believing
The control instruction of breath, and send the control instruction in the corresponding equipment of the semantic control information.
Optionally, as shown in fig. 7, first receiving unit 601 includes:
Second receiving module 6012 can be used for receiving encrypted treated phonetic control command and use from mobile terminal
Family identity information；
The transmission unit 603, comprising:
Second sending module 6032 can be used for according to decryption rule, to the phonetic control command after the encryption
It is decrypted, the phonetic control command after being decrypted, based on the voice control after the voice operating permission and the decryption
Instruction generates the control instruction, and is sent in equipment.
Optionally, as shown in fig. 7, described device further include:
Second receiving unit 604 can be used for receiving the voice operating permission and corresponding relationship of user's typing from mobile terminal,
The corresponding relationship includes subscriber identity information and corresponding biological characteristic；
Storage unit 605 can be used for the received voice operating permission of second receiving unit 604 and the correspondence
Relationship is saved according to subscriber identity information, to carry out voice operating when receiving phonetic control command from mobile terminal
The matching of permission.
Optionally, as shown in fig. 7, described device further include:
Third receiving unit 606 can be used for limiting level information from mobile-terminated retake the power, and be believed according to the Permission Levels
Breath is saved in the corresponding relationship of corresponding subscriber identity information, and the Permission Levels are administrator or operator.
Optionally, as shown in fig. 7, the administrator has modifies, adds to the voice operating permission that operator has
The permission for adding and deleting, described device further include:
First determination unit 607, can be used for when from it is mobile-terminated receive permission control instruction when, according to user's body
Part information and the corresponding relationship determine the Permission Levels of the subscriber identity information；
First execution unit 608 can be used for determining that the Permission Levels are the administrator when the first determination unit 607
When, corresponding permission operation behavior is executed according to the permission control instruction, the permission operation behavior includes the language to user
Sound operating right is modified, adds and is deleted；
Second execution unit 609 can be used for determining that the Permission Levels are the operator when the first determination unit 607
When, and determine that the permission control instruction is when operating for the permission of the sender to permission control instruction, according to institute
It states permission control instruction and executes permission operation behavior, conversely, then ignoring the permission control instruction.
Optionally, as shown in fig. 7, described device further include:
Second determination unit 610 can be used for determining user identity feature according to the subscriber identity information,
Third determination unit 611 can be used for the user identity feature determined based on second determination unit 610, really
Determine the corresponding user group of the subscriber identity information, the user group is pre- according to classification based on variety classes user identity feature
First it is arranged；
First feedback unit 612 can be used for the corresponding use of subscriber identity information determined according to third determination unit 611
Family group, Xiang Suoshu mobile terminal feed back the pushed information of corresponding user group.
Optionally, as shown in fig. 7, described device further include:
4th receiving unit 613 can be used for receiving prompt information from mobile terminal, and the prompt information is used to indicate use
Family sign exists abnormal；
Second feedback unit 614 can be used for obtaining institute according to the received prompt information of the 4th receiving unit 613
User's sign extremely corresponding reason and solution are stated, as sign exception handling information, and by the sign abnormality processing
Information feeds back to mobile terminal.
Further, it is also provided according to above-mentioned Fig. 1,2 and Fig. 3 the method embodiment, another embodiment of the invention
A kind of speech control system of smart machine, as shown in figure 8, described device includes:
Mobile terminal 81, for receiving phonetic control command, and after receiving the phonetic control command described in acquisition
The biological characteristic of phonetic control command sender determines the use of the phonetic control command sender according to the biological characteristic
The subscriber identity information and the phonetic control command are sent to cloud platform 82 by family identity information；
The cloud platform end 82, for receiving phonetic control command and subscriber identity information, root from the mobile terminal 81
According to the subscriber identity information, the voice operating permission of the corresponding subscriber identity information of matching is weighed according to the voice operating
Limit and the phonetic control command send control instruction to the equipment of the correspondence phonetic control command.
The method, apparatus and system of a kind of voice control of smart machine provided in an embodiment of the present invention, with the prior art
In by voice can to smart machine carry out voice control compare, the present invention mobile terminal by first receive voice control
It instructs, and obtains the biological characteristic of the phonetic control command sender, then, root after receiving the phonetic control command
According to the biological characteristic, the subscriber identity information of the phonetic control command sender is determined, finally, the user identity is believed
Breath and the phonetic control command are sent to cloud platform；Platform is referred to by receiving voice control from mobile terminal first beyond the clouds
It enables and then subscriber identity information according to the subscriber identity information, matches the voice operating of the corresponding subscriber identity information
Permission is sent according to the voice operating permission and the phonetic control command to the equipment of the correspondence phonetic control command
Control instruction.So as to according to the interaction between mobile terminal and cloud platform, biological characteristic when using phonetic order come into
The confirmation of row user identity, and the phonetic control command is executed according to the corresponding voice operating permission of the identities match of user,
Realize a kind of smart machine sound control method based on user identity come confirmation operation permission thereby executing phonetic control command,
It avoids and works as the problem of non-permission personnel carry out smart machine control, then ensure when extraneous non-family safe user is in family
Smart machine carries out voice control and existing safety problem, improves the voice control of the smart machine including smart home
The safety of process processed.
Further, according to above-described embodiment, another embodiment of the invention additionally provides a kind of storage medium, described
Storage medium includes the program of storage, wherein equipment where controlling the storage medium in described program operation executes as above
The method of the voice control of the smart machine.
Further, according to above-described embodiment, another embodiment of the invention additionally provides a kind of electronic equipment 90 such as
Shown in Fig. 9, including: memory 91, processor 92 and communication bus 93；
Processor 92 may include central processing unit (Central Processing Unit, CPU), at digital signal
It manages device (digital signal processor, DSP), microcontroller (MicrocontrollerUnit, MCU), dedicated integrated
Circuit (Application Specific Integrated Circuit, ASIC) or field programmable gate array
At least one of (Field-Programmable Gate Array, FPGA).
Memory 91 and processor 92 pass through 93 communication connection of communication bus；
Computer executable instructions are stored in memory 91, processor 92 is used to execute computer executable instructions, with
Realize the sound control method for the smart machine that any optional embodiment of the embodiment of the present application provides.
Computer executable instructions can be realized in the form of SFU software functional unit and can sell as independent product
Or use, memory 91 can be any form of computer-readable storage medium.Based on this understanding, the skill of the application
The all or part of art scheme can be embodied in the form of software products, including some instructions are used so that a computer
Equipment specifically can be processor, all or part of the steps of terminal in each embodiment of Lai Zhihang the application.And meter above-mentioned
Calculation machine readable storage medium storing program for executing includes: that USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), arbitrary access are deposited
The various media that can store program code such as reservoir (Random Access Memory, RAM), magnetic or disk.
It should be noted that the voice control of mobile terminal embodiment provided by the present application and smart machine provided by the present application
Embodiment of the method processed has same or similar effect, and this embodiment is not repeated.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of equipment and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can use various
Programming language realizes summary of the invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects, In
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments in this include institute in other embodiments
Including certain features rather than other feature, but the combination of the feature of different embodiment means in the scope of the present invention
Within and form different embodiments.For example, in the following claims, embodiment claimed it is any it
One can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize the voice control of smart machine according to an embodiment of the present invention a kind of
The some or all functions of some or all components in method, apparatus, system and electronic equipment.The present invention can also be real
Now for for executing method as described herein some or all equipment or device program (for example, computer journey
Sequence and computer program product).It is such to realize that program of the invention can store on a computer-readable medium, or can be with
In the form of one or more signals.Such signal can be downloaded from an internet website to obtain, or believe in carrier
It provides, or is provided in any other form on number.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claim for listing several equipment, several in these equipment be can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
Claims (10)
1. a kind of sound control method of smart machine is applied to mobile terminal characterized by comprising
Phonetic control command is received, and obtains the phonetic control command sender after receiving the phonetic control command
Biological characteristic, the biological characteristic include at least one of vocal print feature, iris feature and facial characteristics；
According to the biological characteristic, the subscriber identity information of the phonetic control command sender is determined；
The subscriber identity information and the phonetic control command are sent to cloud platform.
2. determining the voice control the method according to claim 1, wherein described according to the biological characteristic
System instruction sender subscriber identity information include:
According to the vocal print feature extracted in the phonetic control command, the corresponding vocal print feature is determined in default vocal print relationship
User identifier, the default vocal print relationship is that the mapping for being corresponding with different user and its corresponding vocal print prerecorded is closed
System；
According to the user identifier, the subscriber identity information of the phonetic control command sender is determined.
3. according to the method described in claim 2, it is characterized in that, described according to the sound extracted in the phonetic control command
Line feature, before the user identifier for corresponding to the vocal print feature is determined in default vocal print relationship, the method also includes:
When the biological characteristic for determining the phonetic control command sender is vocal print feature, the default vocal print relationship is obtained.
4. a kind of sound control method of smart machine is applied to cloud platform characterized by comprising
Phonetic control command and subscriber identity information are received from mobile terminal；
According to the subscriber identity information, the voice operating permission of the corresponding subscriber identity information of matching；
According to the voice operating permission and the phonetic control command, sent to the equipment of the correspondence phonetic control command
Control instruction, so that the equipment executes the operation row of the corresponding phonetic control command after receiving the control instruction
For.
5. according to the method described in claim 4, it is characterized in that, described according to the subscriber identity information, the corresponding institute of matching
The voice operating permission for stating subscriber identity information includes:
Identity authority relationship is obtained, it includes subscriber identity information and corresponding voice operating that the identity authority relationship, which is preset,
The mapping relations of permission；
According to the identity authority relationship, the voice operating permission of the corresponding subscriber identity information is determined.
6. a kind of phonetic controller of smart machine is applied to mobile terminal characterized by comprising
Acquiring unit for receiving phonetic control command, and obtains the voice control after receiving the phonetic control command
The biological characteristic of system instruction sender, the biological characteristic include at least one in vocal print feature, iris feature and facial characteristics
Kind；
First determination unit, for determining the user identity letter of the phonetic control command sender according to the biological characteristic
Breath；
Transmission unit, for the subscriber identity information and the phonetic control command to be sent to cloud platform.
7. a kind of phonetic controller of smart machine is applied to cloud platform characterized by comprising
First receiving unit, for receiving phonetic control command and subscriber identity information from mobile terminal；
Matching unit, for according to the subscriber identity information, the voice operating permission of the corresponding subscriber identity information of matching；
Transmission unit, for referring to the correspondence voice control according to the voice operating permission and the phonetic control command
The equipment of order sends control instruction, refers to so that the equipment executes the corresponding voice control after receiving the control instruction
The operation behavior of order.
8. a kind of speech control system of smart machine characterized by comprising
Mobile terminal for receiving phonetic control command, and obtains the voice control after receiving the phonetic control command
The biological characteristic of system instruction sender determines the user identity of the phonetic control command sender according to the biological characteristic
The subscriber identity information and the phonetic control command are sent to cloud platform by information；
The cloud platform end, for receiving phonetic control command and subscriber identity information from the mobile terminal, according to the use
Family identity information, the voice operating permission of the corresponding subscriber identity information of matching, according to the voice operating permission and described
Phonetic control command sends control instruction to the equipment of the correspondence phonetic control command.
9. a kind of electronic equipment, which is characterized in that including memory, processor and communication bus；
The memory and the processor pass through the communication bus communication connection；
Computer executable instructions are stored in the memory, the computer is executable to be referred to the processor for executing
It enables, to realize method described in any one of claim 1-3 or 4-5.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer can
Execute instruction, the computer executable instructions when executed, for realizing described in any one of claim 1-3 or 4-5
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910859713.6A CN110534107A (en) | 2019-09-11 | 2019-09-11 | Sound control method, device, system and the electronic equipment of smart machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910859713.6A CN110534107A (en) | 2019-09-11 | 2019-09-11 | Sound control method, device, system and the electronic equipment of smart machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110534107A true CN110534107A (en) | 2019-12-03 |
Family
ID=68668381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910859713.6A Pending CN110534107A (en) | 2019-09-11 | 2019-09-11 | Sound control method, device, system and the electronic equipment of smart machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110534107A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111276144A (en) * | 2020-02-21 | 2020-06-12 | 北京声智科技有限公司 | Platform matching method, device, equipment and medium |
| CN111464489A (en) * | 2020-02-21 | 2020-07-28 | 中国电子技术标准化研究院 | Privacy protection method and system for Internet of things equipment |
| CN111583921A (en) * | 2020-04-22 | 2020-08-25 | 珠海格力电器股份有限公司 | Voice control method, device, computer equipment and storage medium |
| CN111600782A (en) * | 2020-04-28 | 2020-08-28 | 百度在线网络技术（北京）有限公司 | Control method and device of intelligent voice equipment, electronic equipment and storage medium |
| CN112540544A (en) * | 2020-12-29 | 2021-03-23 | 宜宾凯翼汽车有限公司 | System and method for remotely controlling household intelligent equipment by vehicle |
| CN113053381A (en) * | 2021-03-30 | 2021-06-29 | 三一汽车制造有限公司 | Control system, control method, control device and electronic equipment of fire fighting truck |
| CN113934299A (en) * | 2021-10-18 | 2022-01-14 | 珠海格力电器股份有限公司 | Equipment interaction method and device, smart home equipment and processor |
| CN114489317A (en) * | 2020-11-13 | 2022-05-13 | 上海擎感智能科技有限公司 | Interaction method, interaction device, terminal and computer readable storage medium |
| CN114613368A (en) * | 2022-03-08 | 2022-06-10 | 广州国音智能科技有限公司 | Cloud server, identity authentication method and system based on multiple devices |
| CN116079720A (en) * | 2022-12-23 | 2023-05-09 | 深圳优地科技有限公司 | Robot control method, robot, and storage medium |
| CN118366443A (en) * | 2024-03-27 | 2024-07-19 | 镁佳(北京)科技有限公司 | Multi-mode voice awakening method, device, equipment and medium |
Citations (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101658412A (en) * | 2009-06-19 | 2010-03-03 | 中卫莱康科技发展（北京）有限公司 | Mobile communicator, remote medical system and control method for mobile communicator |
| CN102429637A (en) * | 2011-08-17 | 2012-05-02 | 北京百纳威尔科技有限公司 | Mobile terminal iris detection method and mobile terminal |
| CN104036778A (en) * | 2014-05-20 | 2014-09-10 | 安徽科大讯飞信息科技股份有限公司 | Equipment control method, device and system |
| CN104102801A (en) * | 2013-04-07 | 2014-10-15 | 甘肃百合物联科技信息有限公司 | Elderly health monitoring and management system based on mobile Internet |
| CN105391730A (en) * | 2015-12-02 | 2016-03-09 | 北京云知声信息技术有限公司 | Information feedback method, device and system |
| CN105608407A (en) * | 2015-06-29 | 2016-05-25 | 宇龙计算机通信科技(深圳)有限公司 | Method, device and terminal for information processing |
| CN205261811U (en) * | 2015-12-02 | 2016-05-25 | 王海军 | Vital sign monitors air purifier unusually |
| CN105808903A (en) * | 2014-12-29 | 2016-07-27 | 中兴通讯股份有限公司 | Health report generation method and apparatus |
| CN105962895A (en) * | 2016-04-26 | 2016-09-28 | 广东小天才科技有限公司 | User state reminding method and system |
| CN106506442A (en) * | 2016-09-14 | 2017-03-15 | 上海百芝龙网络科技有限公司 | A kind of smart home multi-user identification and its Rights Management System |
| CN106530165A (en) * | 2015-09-10 | 2017-03-22 | 李冠瑢 | Health management device, health management method and health management system |
| CN106550095A (en) * | 2015-09-18 | 2017-03-29 | 中兴通讯股份有限公司 | The yellow page system of the method, device and mobile terminal of health data management |
| CN107209857A (en) * | 2015-02-10 | 2017-09-26 | 三星电子株式会社 | User terminal and its offer method |
| CN107311002A (en) * | 2017-06-26 | 2017-11-03 | 广东工匠特种设备有限公司 | A kind of elevator |
| CN107358179A (en) * | 2017-06-27 | 2017-11-17 | 上海爱优威软件开发有限公司 | A kind of living management system, medium and method based on iris verification |
| CN107358025A (en) * | 2017-06-12 | 2017-11-17 | 美的集团股份有限公司 | Control method, control device, Intelligent mirror and computer-readable recording medium |
| CN206696852U (en) * | 2017-01-18 | 2017-12-01 | 北京释码大华科技有限公司 | A kind of iris authentication annex |
| CN107463124A (en) * | 2017-07-07 | 2017-12-12 | 广东美的制冷设备有限公司 | Intelligent air equipment and its control method, device, server, storage medium |
| CN107562868A (en) * | 2017-08-30 | 2018-01-09 | 努比亚技术有限公司 | A kind of information recommendation method, terminal and computer-readable recording medium |
| CN108389578A (en) * | 2018-02-09 | 2018-08-10 | 深圳市鹰硕技术有限公司 | Smart classroom speech control system |
| CN208027537U (en) * | 2018-03-30 | 2018-10-30 | 比亚迪股份有限公司 | Intelligent wearable device and vehicle DAS (Driver Assistant System) |
| CN108847288A (en) * | 2018-07-13 | 2018-11-20 | 武汉久乐科技有限公司 | A kind of healthy early warning method and apparatus |
| CN108926331A (en) * | 2017-05-22 | 2018-12-04 | 深圳大森智能科技有限公司 | Healthy monitoring and managing method and system based on wearable device |
| CN109448716A (en) * | 2018-12-06 | 2019-03-08 | 珠海格力电器股份有限公司 | Voice control method and device, storage medium and air conditioner |
| CN109493577A (en) * | 2018-12-19 | 2019-03-19 | 重庆奇甫机械有限责任公司 | Mounted remote intelligent alarm system |
| CN109584860A (en) * | 2017-09-27 | 2019-04-05 | 九阳股份有限公司 | A kind of voice wakes up word and defines method and system |
| CN109631252A (en) * | 2018-12-03 | 2019-04-16 | 珠海格力电器股份有限公司 | Air conditioner control method and device and air conditioner |
| CN109979443A (en) * | 2017-12-27 | 2019-07-05 | 深圳市优必选科技有限公司 | Authority management control method and device for robot |
| CN209059162U (en) * | 2017-11-15 | 2019-07-05 | 北京汽车集团有限公司 | Vehicle-mounted health detection system |
| CN110008870A (en) * | 2019-03-25 | 2019-07-12 | 秒针信息技术有限公司 | Obj State alarm method and device |
| CN110048916A (en) * | 2018-01-17 | 2019-07-23 | 佛山市顺德区美的电热电器制造有限公司 | A kind of control method of equipment, device and storage medium |
-
2019
- 2019-09-11 CN CN201910859713.6A patent/CN110534107A/en active Pending
Patent Citations (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101658412A (en) * | 2009-06-19 | 2010-03-03 | 中卫莱康科技发展（北京）有限公司 | Mobile communicator, remote medical system and control method for mobile communicator |
| CN102429637A (en) * | 2011-08-17 | 2012-05-02 | 北京百纳威尔科技有限公司 | Mobile terminal iris detection method and mobile terminal |
| CN104102801A (en) * | 2013-04-07 | 2014-10-15 | 甘肃百合物联科技信息有限公司 | Elderly health monitoring and management system based on mobile Internet |
| CN104036778A (en) * | 2014-05-20 | 2014-09-10 | 安徽科大讯飞信息科技股份有限公司 | Equipment control method, device and system |
| CN105808903A (en) * | 2014-12-29 | 2016-07-27 | 中兴通讯股份有限公司 | Health report generation method and apparatus |
| CN107209857A (en) * | 2015-02-10 | 2017-09-26 | 三星电子株式会社 | User terminal and its offer method |
| CN105608407A (en) * | 2015-06-29 | 2016-05-25 | 宇龙计算机通信科技(深圳)有限公司 | Method, device and terminal for information processing |
| CN106530165A (en) * | 2015-09-10 | 2017-03-22 | 李冠瑢 | Health management device, health management method and health management system |
| CN106550095A (en) * | 2015-09-18 | 2017-03-29 | 中兴通讯股份有限公司 | The yellow page system of the method, device and mobile terminal of health data management |
| CN105391730A (en) * | 2015-12-02 | 2016-03-09 | 北京云知声信息技术有限公司 | Information feedback method, device and system |
| CN205261811U (en) * | 2015-12-02 | 2016-05-25 | 王海军 | Vital sign monitors air purifier unusually |
| CN105962895A (en) * | 2016-04-26 | 2016-09-28 | 广东小天才科技有限公司 | User state reminding method and system |
| CN106506442A (en) * | 2016-09-14 | 2017-03-15 | 上海百芝龙网络科技有限公司 | A kind of smart home multi-user identification and its Rights Management System |
| CN206696852U (en) * | 2017-01-18 | 2017-12-01 | 北京释码大华科技有限公司 | A kind of iris authentication annex |
| CN108926331A (en) * | 2017-05-22 | 2018-12-04 | 深圳大森智能科技有限公司 | Healthy monitoring and managing method and system based on wearable device |
| CN107358025A (en) * | 2017-06-12 | 2017-11-17 | 美的集团股份有限公司 | Control method, control device, Intelligent mirror and computer-readable recording medium |
| CN107311002A (en) * | 2017-06-26 | 2017-11-03 | 广东工匠特种设备有限公司 | A kind of elevator |
| CN107358179A (en) * | 2017-06-27 | 2017-11-17 | 上海爱优威软件开发有限公司 | A kind of living management system, medium and method based on iris verification |
| CN107463124A (en) * | 2017-07-07 | 2017-12-12 | 广东美的制冷设备有限公司 | Intelligent air equipment and its control method, device, server, storage medium |
| CN107562868A (en) * | 2017-08-30 | 2018-01-09 | 努比亚技术有限公司 | A kind of information recommendation method, terminal and computer-readable recording medium |
| CN109584860A (en) * | 2017-09-27 | 2019-04-05 | 九阳股份有限公司 | A kind of voice wakes up word and defines method and system |
| CN209059162U (en) * | 2017-11-15 | 2019-07-05 | 北京汽车集团有限公司 | Vehicle-mounted health detection system |
| CN109979443A (en) * | 2017-12-27 | 2019-07-05 | 深圳市优必选科技有限公司 | Authority management control method and device for robot |
| CN110048916A (en) * | 2018-01-17 | 2019-07-23 | 佛山市顺德区美的电热电器制造有限公司 | A kind of control method of equipment, device and storage medium |
| CN108389578A (en) * | 2018-02-09 | 2018-08-10 | 深圳市鹰硕技术有限公司 | Smart classroom speech control system |
| CN208027537U (en) * | 2018-03-30 | 2018-10-30 | 比亚迪股份有限公司 | Intelligent wearable device and vehicle DAS (Driver Assistant System) |
| CN108847288A (en) * | 2018-07-13 | 2018-11-20 | 武汉久乐科技有限公司 | A kind of healthy early warning method and apparatus |
| CN109631252A (en) * | 2018-12-03 | 2019-04-16 | 珠海格力电器股份有限公司 | Air conditioner control method and device and air conditioner |
| CN109448716A (en) * | 2018-12-06 | 2019-03-08 | 珠海格力电器股份有限公司 | Voice control method and device, storage medium and air conditioner |
| CN109493577A (en) * | 2018-12-19 | 2019-03-19 | 重庆奇甫机械有限责任公司 | Mounted remote intelligent alarm system |
| CN110008870A (en) * | 2019-03-25 | 2019-07-12 | 秒针信息技术有限公司 | Obj State alarm method and device |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111464489A (en) * | 2020-02-21 | 2020-07-28 | 中国电子技术标准化研究院 | Privacy protection method and system for Internet of things equipment |
| CN111276144A (en) * | 2020-02-21 | 2020-06-12 | 北京声智科技有限公司 | Platform matching method, device, equipment and medium |
| CN111583921A (en) * | 2020-04-22 | 2020-08-25 | 珠海格力电器股份有限公司 | Voice control method, device, computer equipment and storage medium |
| CN111600782A (en) * | 2020-04-28 | 2020-08-28 | 百度在线网络技术（北京）有限公司 | Control method and device of intelligent voice equipment, electronic equipment and storage medium |
| CN114489317B (en) * | 2020-11-13 | 2023-11-03 | 上海擎感智能科技有限公司 | Interaction method, interaction device, terminal and computer readable storage medium |
| CN114489317A (en) * | 2020-11-13 | 2022-05-13 | 上海擎感智能科技有限公司 | Interaction method, interaction device, terminal and computer readable storage medium |
| CN112540544A (en) * | 2020-12-29 | 2021-03-23 | 宜宾凯翼汽车有限公司 | System and method for remotely controlling household intelligent equipment by vehicle |
| CN113053381A (en) * | 2021-03-30 | 2021-06-29 | 三一汽车制造有限公司 | Control system, control method, control device and electronic equipment of fire fighting truck |
| CN113934299A (en) * | 2021-10-18 | 2022-01-14 | 珠海格力电器股份有限公司 | Equipment interaction method and device, smart home equipment and processor |
| CN113934299B (en) * | 2021-10-18 | 2024-01-30 | 珠海格力电器股份有限公司 | Equipment interaction method and device, intelligent household equipment and processor |
| CN114613368A (en) * | 2022-03-08 | 2022-06-10 | 广州国音智能科技有限公司 | Cloud server, identity authentication method and system based on multiple devices |
| CN116079720A (en) * | 2022-12-23 | 2023-05-09 | 深圳优地科技有限公司 | Robot control method, robot, and storage medium |
| CN118366443A (en) * | 2024-03-27 | 2024-07-19 | 镁佳(北京)科技有限公司 | Multi-mode voice awakening method, device, equipment and medium |
| CN118366443B (en) * | 2024-03-27 | 2024-09-20 | 镁佳(北京)科技有限公司 | Multi-mode voice awakening method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110534107A (en) | Sound control method, device, system and the electronic equipment of smart machine | |
| CN105429761B (en) | A kind of key generation method and device | |
| US9286455B2 (en) | Real identity authentication | |
| US20220028200A1 (en) | Roaming user password based on human identity analytic data | |
| US20220092161A1 (en) | Document signing and digital signatures with human as the password | |
| US11831784B2 (en) | Systems and methods for secure data transmission | |
| CN105096420A (en) | Access control system and data processing method for same | |
| CN105335643B (en) | The processing method and processing system of file | |
| Jo et al. | Security analysis and improvement of fingerprint authentication for smartphones | |
| CN108809659A (en) | Generation, verification method and system, the dynamic password system of dynamic password | |
| WO2013055970A2 (en) | Authenticating device users | |
| CN103617382A (en) | Privacy protection method and device | |
| CN106778208A (en) | The access processing method and device of application program | |
| US10630630B1 (en) | Intelligent lock screen notifications | |
| US10375088B2 (en) | Routing systems and methods | |
| CN107733636A (en) | Authentication method and Verification System | |
| US20140082367A1 (en) | Verifying passwords on a mobile device | |
| CN103699223A (en) | Control method and equipment based on gestures | |
| WO2020073916A1 (en) | Encryption method and apparatus for storage device, and storage medium | |
| CN105426727B (en) | Fingerprint decryption method and mobile terminal | |
| CN110262908A (en) | Shear plate data processing method and device | |
| CN205140028U (en) | Gate inhibition system | |
| CN105162804A (en) | Communication information protection method and apparatus | |
| CN106709310A (en) | Virtual reality system interface login method and device | |
| CN108009411A (en) | Method, apparatus and computing device based on recognition of face control automobile |
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: 20191203 |