CN108831469A - Voice command method for customizing, device and equipment and computer storage medium - Google Patents
Voice command method for customizing, device and equipment and computer storage medium Download PDFInfo
- Publication number
- CN108831469A CN108831469A CN201810887444.XA CN201810887444A CN108831469A CN 108831469 A CN108831469 A CN 108831469A CN 201810887444 A CN201810887444 A CN 201810887444A CN 108831469 A CN108831469 A CN 108831469A
- Authority
- CN
- China
- Prior art keywords
- voice command
- voice
- operational order
- user
- semantics recognition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000011017 operating method Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 26
- 230000006399 behavior Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004378 air conditioning Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of voice command method for customizing, device and equipment and computer storage mediums to promote user experience for realizing the customization of voice control scheme.This method includes：The first voice command is generated according to the voice messaging of acquisition；It exports the first prompt information instruction user and inputs the demonstration operation for realizing at least one function of smart home device, and the first operational order based on demonstration operation generation for the operating procedure during executing the demonstration operation；The incidence relation between first voice command and first operational order is established, and stores the incidence relation, so that executing first operational order when receiving the voice command to match with first voice command.
Description
Technical field
The present invention relates to field of computer technology, in particular to a kind of voice command method for customizing, device and equipment and meter
Calculation machine storage medium.
Background technique
Currently, smart home device provides more conveniences to people's lives, the control for smart home device
Method is also more and more, for example, user can control smart home device by voice, or by installing in terminal
Application program (Application, APP) smart home device is controlled.Wherein, for being controlled by voice
Mode usually just pre-defines the incidence relation of sound bank and function when smart home device dispatches from the factory, and user can root
Corresponding voice control is carried out according to specification or prompt.
Therefore, voice and function command collection all pre-define in existing voice control scheme, but are different
The use habit of user has a certain difference, and the use that the voice control scheme pre-defined may and not meet user is practised
It is used, in this way, usage experience of the user when passing through voice control smart home device is obviously bad, also, language predetermined
The function of including in sound control program is limited, may not be able to satisfy the use demand of user, further reduced making for user
With experience.
Summary of the invention
The embodiment of the present invention provides a kind of voice command method for customizing, device and equipment and computer storage medium, is used for
It realizes the customization of voice control scheme, promotes user experience.
In a first aspect, providing a kind of voice command method for customizing, this method includes：
The first voice command is generated according to the voice messaging of acquisition；
It exports the first prompt information instruction user and inputs the demonstration operation for realizing at least one function of smart home device,
And the first operational order based on demonstration operation generation for the operating procedure during executing the demonstration operation；
The incidence relation between first voice command and first operational order is established, and stores the association and closes
System, so that executing first operational order when receiving the voice command to match with first voice command.
In the embodiment of the present invention, the voice messaging that can acquire user generates voice command, and is grasped according to the demonstration of user
Make to generate corresponding operation instruction, and the two is associated, in this way, voice command is the voice messaging next life according to user
At, and then it can be more in line with the habit of speaking of user, and can not office based on the operational order that user's demonstration operation obtains
It is limited to phonetic control command when smart home device factory, the scope of application is wider.
Optionally, described that first voice command is generated according to the voice messaging of acquisition, including：
It is analyzed according to collected a plurality of voice messaging, to extract the common trait of a plurality of voice messaging；
First voice command is generated based on the common trait.
Optionally, the incidence relation established between first voice command and first operational order, including：
Execute first operational order；
Based on the first feedback information received, determine whether the result for executing first operational order meets user's
It is required that；
When first feedback information shows that the result for executing first operational order meets the requirement of the user,
It is stored after first voice command is associated with first operational order, the user is otherwise prompted to drill again
Show operation.
In the embodiment of the present invention, after generating operational order, execute once-through operation instruction, and then to the operational order into
Whether row verification meets the desired effect of user with the function that confirmation operation instruction is realized.
Optionally, the method also includes：
Semantics recognition is carried out to collected voice messaging, and exports semantics recognition result；
Based on the second feedback information received, determine whether the semantics recognition result is the collected voice letter
The expressed semanteme of breath；
If it is determined that result be it is yes, then first voice command and the semantics recognition result are associated, otherwise, will
The modified semanteme of the user received is associated with first voice command, wherein is closed with same semantics recognition result
Operational order corresponding to all voice commands of connection is identical.
In the embodiment of the present invention, semantics recognition can be carried out to the voice messaging that user inputs, and will believe according to the voice
The voice command that breath generates is associated with semantics recognition result, in this way, with same associated all instructions of semantics recognition result
It can realize identical function, in this way, can be carried out supporting even if user inputs dialect or other languages, improve language
The generalization ability of sound identification.
Optionally, the method also includes：
The second voice command received not with any voice command successful match in stored voice command library,
But when being not less than the first preset threshold with the similarity of at least one voice command in the voice command library, record described second
Voice command；
Prompt user re-starts the input of voice command；
If the voice command successful match re-entered, is updated according to second voice command and re-entered with described
Voice command successful match voice command.
In the embodiment of the present invention, if the voice command that user inputs for the first time is unrecognized, and the voice life inputted again
Order identifies successfully, then can be updated according to the voice command inputted for the first time to voice command library, to promote voice life
Enable the recognition capability in library.
Optionally, the method also includes：
In the voice command that continuous several times receive not with any voice command successful match in voice command library when,
Export the second prompt information for prompting the user whether that associated operational order is arranged；
When the third feedback information received demonstrates the need for that operational order associated with the 4th voice command is arranged,
Export first prompt information.
Second aspect provides a kind of voice command customizing device, including：
Generation unit, for generating the first voice command according to the voice messaging of acquisition；
Output unit inputs at least one function of realization smart home device for exporting the first prompt information instruction user
The demonstration operation of energy；
The generation unit is also used to based on demonstration operation generation for the behaviour during executing the demonstration operation
Make the first operational order of step；
Associative cell, the incidence relation for establishing between first voice command and first operational order, and
The incidence relation is stored, so that when receiving the voice command to match with first voice command, described in execution
First operational order.
Optionally, the generation unit is specifically used for：
It is analyzed according to collected a plurality of voice messaging, to extract the common trait of a plurality of voice messaging；
First voice command is generated based on the common trait.
Optionally, the associative cell is specifically used for：
Execute first operational order；
Based on the first feedback information received, determine whether the result for executing first operational order meets user's
It is required that；
When first feedback information shows that the result for executing first operational order meets the requirement of the user,
It is stored after first voice command is associated with first operational order, the user is otherwise prompted to drill again
Show operation.
Optionally, described device further includes semantics recognition unit, is used for：
Semantics recognition is carried out to collected voice messaging, and exports semantics recognition result；
Based on the second feedback information received, determine whether the semantics recognition result is the collected voice letter
The expressed semanteme of breath；
If it is determined that result be it is yes, then first voice command and the semantics recognition result are associated, otherwise, will
The modified semanteme of the user received is associated with first voice command, wherein is closed with same semantics recognition result
Operational order corresponding to all voice commands of connection is identical.
Optionally, described device further includes updating unit, is used for：
The second voice command received not with any voice command successful match in stored voice command library,
But when being not less than the first preset threshold with the similarity of at least one voice command in the voice command library, record described second
Voice command；
Prompt user re-starts the input of voice command；
If the voice command successful match re-entered, is updated according to second voice command and re-entered with described
Voice command successful match voice command.
Optionally, the output unit is also used to：
In the voice command that continuous several times receive not with any voice command successful match in voice command library when,
Export the second prompt information for prompting the user whether that associated operational order is arranged；
When the third feedback information received demonstrates the need for that operational order associated with the 4th voice command is arranged,
Export first prompt information.
The third aspect provides a kind of voice command equipment for customizing, including：
At least one processor；And
The memory being connect at least one described processor communication；Wherein,
The memory is stored with the instruction that can be executed by least one described processor, and described instruction is by described at least one
A processor executes, so that at least one described processor is able to carry out method as described in relation to the first aspect.
Fourth aspect provides a kind of computer storage medium,
The computer storage medium is stored with computer instruction, when the computer instruction is run on computers,
So that computer executes method as described in relation to the first aspect.
Detailed description of the invention
Fig. 1 is the flow diagram of voice command method for customizing provided in an embodiment of the present invention；
Fig. 2 is the flow diagram provided in an embodiment of the present invention for being associated semantics recognition result and voice command；
Fig. 3 is the flow diagram of speech control process provided in an embodiment of the present invention；
Fig. 4 is a kind of structural schematic diagram of voice command customizing device provided in an embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of voice command equipment for customizing provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.
The technical background of the embodiment of the present invention is described below.
Currently, voice and function command collection all pre-define in voice control scheme, but it is different user's
Use habit has a certain difference, and the voice control scheme pre-defined may and not meet the use habit of user, this
Sample, usage experience of the user when passing through voice control smart home device is obviously bad, also, voice control predetermined
The function of including in scheme is limited, may not be able to satisfy the use demand of user, further reduced the usage experience of user.
In consideration of it, the embodiment of the present invention provides a kind of voice command method for customizing, device and equipment and computer storage is situated between
Matter, in the method, the voice messaging that can acquire user generate voice command, and are generated accordingly according to the demonstration operation of user
Operational order, and the two is associated, in this way, voice command is generated according to the voice messaging of user, in turn
It can be more in line with the habit of speaking of user, and the operational order obtained based on user's demonstration operation can be not limited to intelligent family
Phonetic control command when equipment factory is occupied, the scope of application is wider.
Technical solution provided in an embodiment of the present invention is introduced with reference to the accompanying drawing.
Referring to Figure 1, the embodiment of the present invention provides a kind of voice command method for customizing, and this method can pass through smart home
Equipment or terminal etc. are provided with the equipment (subsequent abbreviation equipment) of speech control module to execute, for example, smart home device
Can be intelligent air condition, intelligent gas-burning stove, smart television, perhaps intelligent refrigerator etc. terminal can be mobile phone or tablet computer
(PAD) etc. the equipment of the APP for controlling smart home device can be installed.The process of this method is described as follows.
Step 101：The first voice command is generated according to the voice messaging of acquisition.
In the embodiment of the present invention, when user wants the new voice control scheme of customization, can in smart home device or
New voice control scheme is created in person APP, smart home device or APP can be supplied to user and visually operate boundary
Face, user operate step by step according to the prompt in operation interface, to complete customization procedure.
When customizing new voice control scheme, need to generate new voice command, then user can be prompted to input language
Message breath, after user's input voice information, it is defeated that the terminal of smart home device or installation APP can collect user
The voice messaging entered.Specifically, being typically provided with microphone in the terminal of smart home device or installation APP, therefore intelligence
Home equipment or the terminal for installing APP can acquire the voice messaging of user's input by microphone.
Wherein, after the voice messaging for collecting user's input, so that it may be generated according to the voice messaging of user's input
First voice command.
In the embodiment of the present invention, the tone or content when being spoken each time due to user more or less all may not
Together, therefore in order to promote the discrimination of the voice command of generation, the voice messaging that can be inputted with multi collect user, and to more
The voice messaging of secondary acquisition is analyzed, to extract the common trait of these voice messagings, and then according to common trait next life
At the first voice command.For example, the voice messaging of collected user 3 times inputs is respectively that " opening air-conditioning " " helps me to open sky
Adjust " " air-conditioning please be open ", then the common trait of 3 inputs is " opening air-conditioning ", thus " can be beaten what user inputted
Turn on the aircondition " this section of voice as common trait, and as the first voice command.Alternatively, in the language for collecting user
After message breath, the vector characteristic in voice messaging, and then the vector that will repeatedly extract are extracted respectively by speech recognition modeling
Feature compares, and obtains common trait, and the first voice command is generated based on the common trait.
In practical applications, after the voice messaging for collecting user input, then user can be prompted to carry out down
The input of voice messaging.Specifically, can be prompted by text information, or can also be mentioned by voice
Show.
Step 102：It exports the first prompt information instruction user and inputs at least one function of realizing smart home device
Demonstration operation.
In the embodiment of the present invention, after generating the first voice command, then the first prompt information can be exported, to prompt to use
Family carries out demonstration operation.Wherein, the first prompt information can be being exported, for example, can be in the form of text information
Display " come in row demonstration operation " printed words on display unit；Alternatively, the first prompt information can also be carried out by voice mode it is defeated
Out, for example, can by smart home device or install APP terminal in include loudspeaker output " come in row demonstration behaviour
Make "；It is exported it is of course also possible to be combined by above two mode.
Step 103：The first operation based on demonstration operation generation for the operating procedure during executing demonstration operation refers to
It enables.
In the embodiment of the present invention, the demonstration operation that user carries out is used to demonstrate at least one function for realizing smart home device
Operating procedure needed for energy, in this way, equipment after collecting the demonstration operation, then includes in the available demonstration operation
Ordinal relation between operating procedure and operating procedure, and then based on the sequence between these operating procedures and operating procedure
Relationship generates the first operational order.
Wherein, for equipment, each operating procedure is to correspond to a function or one for smart home device
A function command.For example, user in demonstration operation, successively performs " opening air-conditioning " " adjusting out monsoon intensity " " adjusting wind direction "
Deng operation, then then available these operate suitable between corresponding function command and function command for equipment
Order relation, then then can successively execute aforesaid operations based on this first operational order generated.Certainly, function command can also be
Other possible function commands, such as the gear of smart home device are adjusted or the page jump of APP etc..
In the specific implementation process, the sequence of step 101 and step 103 also can be converted, that is, first carry out step
Rapid 103, step 101 is then executed again, then step 102 is i.e. for prompting user's recorded speech order.
Step 104：Execute the first operational order.
Step 105：Determine whether the result for executing the first operational order meets the requirement of user.
In the embodiment of the present invention, after generating the first operational order, the first operational order can be verified, with inspection
It tests whether the first operational order can be realized the desired function of realizing of user, therefore first operational order can be executed, so
Afterwards after executing completion, prompt information is exported, user is allowed to be confirmed whether the expection to the user.It carries out feeding back it in user
Afterwards, then it can receive to the first feedback information, and determine whether the result of the first operational order meets based on the first feedback information
The requirement of user.
Step 106：If the definitive result of step 105 be it is yes, establish between the first voice command and the first operational order
Incidence relation, and store incidence relation.
In the embodiment of the present invention, if the first feedback information shows that the result for executing the first operational order meets the requirements, then
First voice command and the first operational order can be associated, to generate new voice control scheme, and to new voice
Control program is stored, in this way, in the use process of smart home device, if receiving user again inputs the first language
Sound order can then find the first operational order being associated, and then execute the first operational order, to realize above-mentioned user
The function that demonstration operation is realized.
Specifically, the incidence relation between voice command and operational order can be stored in what smart home device included
Storage unit, in this way, even if smart home device can also smoothly complete voice control when not having network, alternatively, can also incite somebody to action
Incidence relation between voice command and operational order is stored in server end, in this way, smart home device or APP can be from
Server end obtains and the associated operational order of voice command of user's input.For example, user controls intelligent family by APP
When occupying equipment, then the voice command that user inputs can be sent to server end, server end is matched to associated operation
After instruction, operational order is sent to smart home device, to realize voice control；Alternatively, it is defeated by user to be also possible to APP
The voice command entered is sent to server end, and the operational order that server end will match to feeds back to APP, and APP again refers to operation
Order is sent to smart home device, realizes voice control.
Step 107：If the definitive result of step 105 be it is no, prompt user to carry out demonstration operation again.
In the embodiment of the present invention, if the first feedback information shows that the result for executing the first operational order is undesirable,
It can so prompt user to re-start demonstration operation, then the first new operation is generated based on the demonstration operation re-started and is referred to
It enables.
Fig. 2 is referred to, after the voice messaging for receiving user's input, this method further includes following steps：
Step 201：Semantics recognition is carried out to collected voice messaging, and exports semantics recognition result.
In the embodiment of the present invention, the geographical location where user is different, and the language form being accustomed in daily life is not
Together, such as Shanghai people may more be accustomed to Shanghai native language, and people from Sichuan is more accustomed to saying Sichuan, thus user is customizing new voice control
When scheme processed, it is also possible to dialect can be inputted, and it is identical that different dialects, which is possible to corresponding semanteme, then corresponding
Operational order just ought to be identical.It therefore,, can be with after the voice messaging for receiving user's input in the embodiment of the present invention
Semantics recognition is carried out to voice messaging, and semantics recognition result is exported to user, user can thus be allowed to confirm semantic knowledge
Whether other result is correct.In general, semantics recognition result is generally described using all-purpose language, such as can be using common
Words are described.Specifically, can be shown semantics recognition result on the display unit with written form when being exported,
Or semantics recognition result is played by speaker sound.
Step 202：Determine whether semantics recognition result is semanteme expressed by collected voice messaging.
In the embodiment of the present invention, user can be fed back based on the semantics recognition result of output, and corresponding, equipment is just
Can receive user input the second feedback information, and based on the second feedback information determine above-mentioned semantics recognition result whether be
Semanteme expressed by the voice messaging of user's input.
Step 203：If the definitive result of step 202 be it is yes, the first voice command and semantics recognition result are closed
Connection.
In the embodiment of the present invention, if semantics recognition result is semanteme expressed by the voice messaging of user's input, also
It is to say semantics recognition the result is that correctly, then the first voice command and semantics recognition result can be associated, also,
Operational order corresponding to the same associated all voice commands of semantics recognition result is identical.In this way, even from different sides
Say that the voice command generated is different, as long as but the associated semantics recognition of these voice commands the result is that identical, then pair
The operational order answered is also identical, so that voice control can support dialect, or life spoken language etc. simultaneously.
Step 204：If the definitive result of step 202 is no, the modified semanteme of the user received and described first
Voice command is associated.
In the embodiment of the present invention, if semantics recognition result is not semanteme expressed by the voice messaging of user's input,
It can so prompt user's input correctly semantic.User can modify on the basis of original semantics recognition result,
Or voluntarily input is correctly semantic, then equipment by the user received it is modified it is semantic with first voice command into
Row association.
In the embodiment of the present invention, after storing the incidence relation between voice command and operational order, then it can incite somebody to action
Incidence relation application and voice control.Fig. 3 is referred to, is illustrated for user by the process of voice control smart home device
Figure.
Step 301：Receive the second voice command of user's input.
Step 302：Determining in voice command library whether there is and the matched voice command of the second voice command.
When user wants to control smart home device by voice, such as user wants the function of realizing and needs
The second voice command is inputted, then user can input the second voice command, correspondingly, equipment can receive the second language
Sound order, and the second voice command is matched with voice command library, it whether there is and second with determining in voice command library
The matched voice command of voice command.Specifically, when being matched the second voice command with voice command library, it can be by
All features that two voice commands include are compared with the feature that each voice command includes in voice command library.
Step 303：If the definitive result of step 302 is yes, execution and the matched voice command pass of the second voice command
The operational order of connection.
Specifically, smart home device can be executed directly and the second voice command when equipment is smart home device
The matched associated operational order of voice command；When equipment is to install the terminal of APP, can will be matched with the second voice command
The associated operational order of voice command be sent to smart home device so that smart home device executes the operational order.
Step 304：If the definitive result of step 302 be it is no, prompt user to re-start the input of voice command.
In the embodiment of the present invention, if it fails to match with voice command library for the second voice command of user's input, that is,
The unrecognized success of second voice command, then equipment can prompt equipment to re-start the input of voice command.
Specifically, over time, the voice command that user inputs when may be to customized voice control program is
Forget, but can remember approximate contents, thus the second voice command may have not been able to order with any voice in voice command library
Successful match is enabled, but the similarity of the wherein one or more of voice commands in the second voice command and voice command library is not
Less than the first preset threshold, then equipment can temporarily save the second voice command.Certainly, equipment can also be by above-mentioned one
Or a plurality of associated semantics recognition result of voice command exports and user is allowed to confirm the voice command for needing to input to user,
After user selects and confirms, corresponding operational order is executed.
Step 305：Determine the matched voice command of voice command that whether there is in voice command library and re-enter.
Step 306：If the definitive result of step 305 is language that is yes, updating and re-enter according to the second voice command
The successful voice command of sound commands match.
In the embodiment of the present invention, if the voice command successful match that user re-enters, and inputted for the first time
The similarity of wherein one or more of voice commands in two voice commands and voice command library is not less than the first preset threshold,
So show the second voice command that user inputs for the first time and semanteme expressed by the voice command re-entered should be it is identical,
It can be so updated according to the second voice command pair and the voice command of the voice command re-entered successful match, with
Strengthen the voice command, it can be compatible stronger.Specifically, the second voice command and the voice re-entered can be ordered
It enables the voice command of successful match be compared, extract the common trait of the two and is stored.
In the embodiment of the present invention, if the non-successful match of voice command of user's continuous several times input, then show not
Voice control scheme associated with the voice command, then the second prompt information can be exported, the second prompt information is used for
It prompts the user whether setting and the associated operational order of the voice command, needs to be arranged associated operational order in user feedback
When, the first prompt information is exported, it, will be newly-generated to prompt user to carry out operation demonstration, and after user carries out demonstration operation
Operational order be associated with the common trait in the voice command that is inputted according to continuous several times, to obtain new voice control
Scheme.
In conclusion the voice messaging that can acquire user generates voice command, and generated according to the demonstration operation of user
Corresponding operation instruction, and the two is associated, in this way, voice command is generated according to the voice messaging of user,
And then it can be more in line with the habit of speaking of user, and the operational order obtained based on user's demonstration operation can be not limited to intelligence
Phonetic control command when energy home equipment factory, the scope of application are wider.
Fig. 4 is referred to, based on the same inventive concept, the embodiment of the present invention provides a kind of voice command customizing device, including：
Generation unit 401, for generating the first voice command according to the voice messaging of acquisition；
Output unit 402 inputs at least the one of realization smart home device for exporting the first prompt information instruction user
The demonstration operation of a function；
Generation unit 401 is also used to based on demonstration operation generation for the operating procedure during executing demonstration operation
First operational order；
Associative cell 403, the incidence relation for establishing between the first voice command and the first operational order, and store pass
Connection relationship, so that executing the first operational order when receiving the voice command to match with the first voice command.
Optionally, generation unit 401 is specifically used for：
It is analyzed according to collected a plurality of voice messaging, to extract the common trait of a plurality of voice messaging；
The first voice command is generated based on common trait.
Optionally, associative cell 403 is specifically used for：
Execute the first operational order；
Based on the first feedback information received, determine whether the result for executing the first operational order meets wanting for user
It asks；
When the first feedback information shows that the result for executing the first operational order meets the requirement of user, the first voice is ordered
Order is stored after being associated with the first operational order, otherwise user is prompted to carry out demonstration operation again.
Optionally, which further includes semantics recognition unit 404, is used for：
Semantics recognition is carried out to collected voice messaging, and exports semantics recognition result；
Based on the second feedback information received, determine whether semantics recognition result is expressed by collected voice messaging
Semanteme；
If it is determined that result be it is yes, then the first voice command and semantics recognition result are associated, otherwise, by what is received
The modified semanteme of user is associated with the first voice command, wherein with the associated all voices of same semantics recognition result
The corresponding operational order of order is identical.
Optionally, which further includes updating unit 405, is used for：
The second voice command received not with any voice command successful match in stored voice command library,
But when being not less than the first preset threshold with the similarity of at least one voice command in voice command library, record the second voice life
It enables；
Prompt user re-starts the input of voice command；
If the voice command successful match re-entered, is updated according to the second voice command and ordered with the voice re-entered
Enable the voice command of successful match.
Optionally, output unit 402 is also used to：
In the voice command that continuous several times receive not with any voice command successful match in voice command library when,
Export the second prompt information for prompting the user whether that associated operational order is arranged；
When the third feedback information received demonstrates the need for that operational order associated with the 4th voice command is arranged, output
First prompt information.
The equipment can be used for executing method provided by embodiment shown in Fig. 1-3, therefore, for each function of the equipment
The function etc. that energy module can be realized can refer to the description of embodiment shown in FIG. 1, seldom repeat.Wherein, semantics recognition list
It is not essential functional unit, therefore shown with dotted line although member 404 and updating unit 405 are shown together in Fig. 4
Out.
Fig. 5 is referred to, based on the same inventive concept, the embodiment of the present invention provides a kind of voice command equipment for customizing, including
At least one processor 501, at least one processor 501 is for realizing Fig. 1-when executing the computer program stored in memory
The step of voice command method for customizing that embodiment shown in 3 provides.
Optionally, at least one processor 501 can specifically include central processing unit (CPU), application-specific integrated circuit
(application specific integrated circuit, ASIC) can be one or more and hold for controlling program
Capable integrated circuit can be use site programmable gate array (field programmable gate array, FPGA) and open
The hardware circuit of hair, can be baseband processor.
Optionally, at least one processor 501 may include at least one processing core.
Optionally, which further includes memory 502, and memory 502 may include read-only memory (read only
Memory, ROM), random access memory (random access memory, RAM) and magnetic disk storage.Memory 502 is used
Required data when storing the operation of at least one processor 501.The quantity of memory 502 is one or more.Wherein, it stores
Device 502 is shown together in Fig. 5, but it is understood that memory 502 is not essential functional module, thus in Fig. 5 with
Dotted line is shown.
Based on the same inventive concept, the embodiment of the present invention provides a kind of computer readable storage medium, and the computer can
It reads storage medium and is stored with computer instruction, when the computer instruction is run on computers, so that computer executes such as
Method shown in Fig. 1-3.
In the specific implementation process, computer readable storage medium includes：General serial bus USB
(Universal Serial Bus flash drive, USB), mobile hard disk, read-only memory (Read-Only Memory,
ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. are various can store program
The storage medium of code.
In embodiments of the present invention, it should be understood that disclosed device and method, it can be real by another way
It is existing.For example, apparatus embodiments described above are merely indicative, for example, the division of the unit or unit, only
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of equipment or unit
It connects, can be electrical or other forms.
Each functional unit in embodiments of the present invention can integrate in one processing unit or each unit can also
To be independent physical module.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, the technical solution of the embodiment of the present invention
All or part can be embodied in the form of software products, which is stored in a storage medium
In, including some instructions use so that a computer equipment, such as can be personal computer, server or network are set
Standby etc. or processor (processor) performs all or part of the steps of the method described in the various embodiments of the present invention.And it is above-mentioned
Storage medium includes：General serial bus USB (universal serial bus flash drive), mobile hard disk,
The various media that can store program code such as ROM, RAM, magnetic or disk.
The above, above embodiments are only described in detail to the technical solution to the application, but the above implementation
The method that the explanation of example is merely used to help understand the embodiment of the present invention, should not be construed as the limitation to the embodiment of the present invention.This
Any changes or substitutions that can be easily thought of by those skilled in the art, should all cover the embodiment of the present invention protection scope it
It is interior.
Claims (14)
1. a kind of voice command method for customizing, which is characterized in that including：
The first voice command is generated according to the voice messaging of acquisition；
It exports the first prompt information instruction user and inputs the demonstration operation for realizing at least one function of smart home device, and base
In first operational order of the demonstration operation generation for the operating procedure during executing the demonstration operation；
The incidence relation between first voice command and first operational order is established, and stores the incidence relation,
So that executing first operational order when receiving the voice command to match with first voice command.
2. the method as described in claim 1, which is characterized in that described to generate the first voice life according to the voice messaging of acquisition
It enables, including：
It is analyzed according to collected a plurality of voice messaging, to extract the common trait of a plurality of voice messaging；
First voice command is generated based on the common trait.
3. the method as described in claim 1, which is characterized in that described to establish first voice command and first operation
Incidence relation between instruction, including：
Execute first operational order；
Based on the first feedback information received, determine whether the result for executing first operational order meets wanting for user
It asks；
When first feedback information shows that the result for executing first operational order meets the requirement of the user, by institute
It states after the first voice command is associated with first operational order and is stored, the user is otherwise prompted to carry out demonstration behaviour again
Make.
4. the method as described in claim 1, which is characterized in that the method also includes：
Semantics recognition is carried out to collected voice messaging, and exports semantics recognition result；
Based on the second feedback information received, determine whether the semantics recognition result is the collected voice messaging institute
The semanteme of expression；
If it is determined that result be it is yes, then first voice command and the semantics recognition result are associated, otherwise, will be received
To the modified semanteme of user be associated with first voice command, wherein it is associated with same semantics recognition result
Operational order corresponding to all voice commands is identical.
5. the method as described in claim 1-4 is any, which is characterized in that the method also includes：
The second voice command received not with any voice command successful match in stored voice command library, but with
When the similarity of at least one voice command is not less than the first preset threshold in the voice command library, second voice is recorded
Order；
Prompt user re-starts the input of voice command；
If the voice command successful match re-entered, updated and the language re-entered according to second voice command
The successful voice command of sound commands match.
6. the method as described in claim 1-4 is any, which is characterized in that the method also includes：
In the voice command that continuous several times receive not with any voice command successful match in voice command library when, output
The second prompt information for prompting the user whether that associated operational order is arranged；
When the third feedback information received demonstrates the need for that operational order associated with the 4th voice command is arranged, output
First prompt information.
7. a kind of voice command customizing device, which is characterized in that including：
Generation unit, for generating the first voice command according to the voice messaging of acquisition；
Output unit indicates that user inputs at least one function of realization smart home device for exporting the first prompt information
Demonstration operation；
The generation unit is also used to based on demonstration operation generation for the operation step during executing the demonstration operation
The first rapid operational order；
Associative cell, the incidence relation for establishing between first voice command and first operational order, and store
The incidence relation, so that executing described first when receiving the voice command to match with first voice command
Operational order.
8. device as claimed in claim 7, which is characterized in that the generation unit is specifically used for：
It is analyzed according to collected a plurality of voice messaging, to extract the common trait of a plurality of voice messaging；
First voice command is generated based on the common trait.
9. device as claimed in claim 7, which is characterized in that the associative cell is specifically used for：
Execute first operational order；
Based on the first feedback information received, determine whether the result for executing first operational order meets wanting for user
It asks；
When first feedback information shows that the result for executing first operational order meets the requirement of the user, by institute
It states after the first voice command is associated with first operational order and is stored, the user is otherwise prompted to carry out demonstration behaviour again
Make.
10. device as claimed in claim 7, which is characterized in that described device further includes semantics recognition unit, is used for：
Semantics recognition is carried out to collected voice messaging, and exports semantics recognition result；
Based on the second feedback information received, determine whether the semantics recognition result is the collected voice messaging institute
The semanteme of expression；
If it is determined that result be it is yes, then first voice command and the semantics recognition result are associated, otherwise, will be received
To the modified semanteme of user be associated with first voice command, wherein it is associated with same semantics recognition result
Operational order corresponding to all voice commands is identical.
11. the device as described in claim 7-10 is any, which is characterized in that described device further includes updating unit, is used for：
The second voice command received not with any voice command successful match in stored voice command library, but with
When the similarity of at least one voice command is not less than the first preset threshold in the voice command library, second voice is recorded
Order；
Prompt user re-starts the input of voice command；
If the voice command successful match re-entered, updated and the language re-entered according to second voice command
The successful voice command of sound commands match.
12. the device as described in claim 7-10 is any, which is characterized in that the output unit is also used to：
In the voice command that continuous several times receive not with any voice command successful match in voice command library when, output
The second prompt information for prompting the user whether that associated operational order is arranged；
When the third feedback information received demonstrates the need for that operational order associated with the 4th voice command is arranged, output
First prompt information.
13. a kind of voice command equipment for customizing, which is characterized in that including：
At least one processor；And
The memory being connect at least one described processor communication；Wherein,
The memory is stored with the instruction that can be executed by least one described processor, and described instruction is by described at least one
It manages device to execute, so that at least one described processor is able to carry out the method as described in claim 1~6 any claim.
14. a kind of computer storage medium, it is characterised in that：
The computer storage medium is stored with computer instruction, when the computer instruction is run on computers, so that
Computer executes such as method of any of claims 1-6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810887444.XA CN108831469B (en) | 2018-08-06 | 2018-08-06 | Voice command customizing method, device and equipment and computer storage medium |
| PCT/CN2018/121040 WO2020029500A1 (en) | 2018-08-06 | 2018-12-14 | Voice command customization method, device, apparatus, and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810887444.XA CN108831469B (en) | 2018-08-06 | 2018-08-06 | Voice command customizing method, device and equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108831469A true CN108831469A (en) | 2018-11-16 |
| CN108831469B CN108831469B (en) | 2021-02-12 |
Family
ID=64153673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810887444.XA Active CN108831469B (en) | 2018-08-06 | 2018-08-06 | Voice command customizing method, device and equipment and computer storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108831469B (en) |
| WO (1) | WO2020029500A1 (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584875A (en) * | 2018-12-24 | 2019-04-05 | 珠海格力电器股份有限公司 | A kind of speech ciphering equipment control method, device, storage medium and speech ciphering equipment |
| CN109871119A (en) * | 2018-12-27 | 2019-06-11 | 安徽语讯科技有限公司 | A kind of learning type intellectual voice operating method and system |
| CN109901707A (en) * | 2018-12-27 | 2019-06-18 | 安徽语讯科技有限公司 | A kind of learning-oriented operation module being configured in system |
| CN110570867A (en) * | 2019-09-12 | 2019-12-13 | 安信通科技（澳门）有限公司 | Voice processing method and system for locally added corpus |
| CN110580904A (en) * | 2019-09-29 | 2019-12-17 | 百度在线网络技术（北京）有限公司 | Method and device for controlling small program through voice, electronic equipment and storage medium |
| CN110784384A (en) * | 2019-10-16 | 2020-02-11 | 杭州九阳小家电有限公司 | Household appliance voice technology generation method and intelligent household appliance |
| WO2020029500A1 (en) * | 2018-08-06 | 2020-02-13 | 珠海格力电器股份有限公司 | Voice command customization method, device, apparatus, and computer storage medium |
| CN111063353A (en) * | 2019-12-31 | 2020-04-24 | 苏州思必驰信息科技有限公司 | Client processing method allowing user-defined voice interactive content and user terminal |
| CN111179933A (en) * | 2020-01-23 | 2020-05-19 | 珠海荣邦电子科技有限公司 | Voice control method and device and intelligent terminal |
| CN111261158A (en) * | 2020-01-15 | 2020-06-09 | 上海思依暄机器人科技股份有限公司 | Function menu customization method, voice shortcut control method and robot |
| WO2020237086A1 (en) * | 2019-05-21 | 2020-11-26 | Qualcomm Incorporated | Virtual assistant device |
| WO2021103788A1 (en) * | 2019-11-26 | 2021-06-03 | 北京沃东天骏信息技术有限公司 | Smart sound box setting method and apparatus, smart sound box control method and apparatus, and smart sound box |
| CN113160807A (en) * | 2020-01-22 | 2021-07-23 | 广州汽车集团股份有限公司 | Corpus updating method and system and voice control equipment |
| CN114067792A (en) * | 2020-08-07 | 2022-02-18 | 北京猎户星空科技有限公司 | Control method and device of intelligent equipment |
| CN114246450A (en) * | 2020-09-21 | 2022-03-29 | 佛山市顺德区美的电热电器制造有限公司 | Information processing method and device, cooking equipment and computer readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7027985B2 (en) * | 2000-09-08 | 2006-04-11 | Koninklijke Philips Electronics, N.V. | Speech recognition method with a replace command |
| CN101937693A (en) * | 2010-08-17 | 2011-01-05 | 深圳市子栋科技有限公司 | Video and audio playing method and system based on voice command |
| CN102842306A (en) * | 2012-08-31 | 2012-12-26 | 深圳Tcl新技术有限公司 | Voice control method and device as well as voice response method and device |
| CN105845136A (en) * | 2015-01-13 | 2016-08-10 | 中兴通讯股份有限公司 | Voice control method and device, and terminal |
| CN105931637A (en) * | 2016-04-01 | 2016-09-07 | 金陵科技学院 | User-defined instruction recognition speech photographing system |
| CN105989841A (en) * | 2015-02-17 | 2016-10-05 | 上海汽车集团股份有限公司 | Vehicle-mounted speech control method and device |
| CN108174030A (en) * | 2017-12-26 | 2018-06-15 | 努比亚技术有限公司 | Customize implementation method, mobile terminal and the readable storage medium storing program for executing of voice control |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030110040A1 (en) * | 2001-12-07 | 2003-06-12 | Creative Logic Solutions Inc. | System and method for dynamically changing software programs by voice commands |
| CN103646646B (en) * | 2013-11-27 | 2018-08-31 | 联想(北京)有限公司 | A kind of sound control method and electronic equipment |
| CN103713905A (en) * | 2013-12-29 | 2014-04-09 | 广州视源电子科技股份有限公司 | User-defined method, device and system of operation steps |
| CN106484270A (en) * | 2016-09-12 | 2017-03-08 | 深圳市金立通信设备有限公司 | A kind of voice operating event adding method and terminal |
| CN108831469B (en) * | 2018-08-06 | 2021-02-12 | 珠海格力电器股份有限公司 | Voice command customizing method, device and equipment and computer storage medium |
-
2018
- 2018-08-06 CN CN201810887444.XA patent/CN108831469B/en active Active
- 2018-12-14 WO PCT/CN2018/121040 patent/WO2020029500A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7027985B2 (en) * | 2000-09-08 | 2006-04-11 | Koninklijke Philips Electronics, N.V. | Speech recognition method with a replace command |
| CN101937693A (en) * | 2010-08-17 | 2011-01-05 | 深圳市子栋科技有限公司 | Video and audio playing method and system based on voice command |
| CN102842306A (en) * | 2012-08-31 | 2012-12-26 | 深圳Tcl新技术有限公司 | Voice control method and device as well as voice response method and device |
| CN105845136A (en) * | 2015-01-13 | 2016-08-10 | 中兴通讯股份有限公司 | Voice control method and device, and terminal |
| CN105989841A (en) * | 2015-02-17 | 2016-10-05 | 上海汽车集团股份有限公司 | Vehicle-mounted speech control method and device |
| CN105931637A (en) * | 2016-04-01 | 2016-09-07 | 金陵科技学院 | User-defined instruction recognition speech photographing system |
| CN108174030A (en) * | 2017-12-26 | 2018-06-15 | 努比亚技术有限公司 | Customize implementation method, mobile terminal and the readable storage medium storing program for executing of voice control |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020029500A1 (en) * | 2018-08-06 | 2020-02-13 | 珠海格力电器股份有限公司 | Voice command customization method, device, apparatus, and computer storage medium |
| CN109584875A (en) * | 2018-12-24 | 2019-04-05 | 珠海格力电器股份有限公司 | A kind of speech ciphering equipment control method, device, storage medium and speech ciphering equipment |
| CN109871119A (en) * | 2018-12-27 | 2019-06-11 | 安徽语讯科技有限公司 | A kind of learning type intellectual voice operating method and system |
| CN109901707A (en) * | 2018-12-27 | 2019-06-18 | 安徽语讯科技有限公司 | A kind of learning-oriented operation module being configured in system |
| WO2020237086A1 (en) * | 2019-05-21 | 2020-11-26 | Qualcomm Incorporated | Virtual assistant device |
| US11170774B2 (en) * | 2019-05-21 | 2021-11-09 | Qualcomm Incorproated | Virtual assistant device |
| CN110570867A (en) * | 2019-09-12 | 2019-12-13 | 安信通科技（澳门）有限公司 | Voice processing method and system for locally added corpus |
| CN110580904A (en) * | 2019-09-29 | 2019-12-17 | 百度在线网络技术（北京）有限公司 | Method and device for controlling small program through voice, electronic equipment and storage medium |
| CN110784384A (en) * | 2019-10-16 | 2020-02-11 | 杭州九阳小家电有限公司 | Household appliance voice technology generation method and intelligent household appliance |
| CN110784384B (en) * | 2019-10-16 | 2021-11-02 | 杭州九阳小家电有限公司 | Household appliance voice technology generation method and intelligent household appliance |
| WO2021103788A1 (en) * | 2019-11-26 | 2021-06-03 | 北京沃东天骏信息技术有限公司 | Smart sound box setting method and apparatus, smart sound box control method and apparatus, and smart sound box |
| CN111063353A (en) * | 2019-12-31 | 2020-04-24 | 苏州思必驰信息科技有限公司 | Client processing method allowing user-defined voice interactive content and user terminal |
| CN111261158A (en) * | 2020-01-15 | 2020-06-09 | 上海思依暄机器人科技股份有限公司 | Function menu customization method, voice shortcut control method and robot |
| CN113160807A (en) * | 2020-01-22 | 2021-07-23 | 广州汽车集团股份有限公司 | Corpus updating method and system and voice control equipment |
| CN111179933A (en) * | 2020-01-23 | 2020-05-19 | 珠海荣邦电子科技有限公司 | Voice control method and device and intelligent terminal |
| CN114067792A (en) * | 2020-08-07 | 2022-02-18 | 北京猎户星空科技有限公司 | Control method and device of intelligent equipment |
| CN114246450A (en) * | 2020-09-21 | 2022-03-29 | 佛山市顺德区美的电热电器制造有限公司 | Information processing method and device, cooking equipment and computer readable storage medium |
| CN114246450B (en) * | 2020-09-21 | 2024-02-06 | 佛山市顺德区美的电热电器制造有限公司 | Information processing method, information processing device, cooking equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020029500A1 (en) | 2020-02-13 |
| CN108831469B (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108831469A (en) | Voice command method for customizing, device and equipment and computer storage medium | |
| CN109003624B (en) | Emotion recognition method and device, computer equipment and storage medium | |
| CN101145341B (en) | Method, system and apparatus for improved voice recognition | |
| EP3608906B1 (en) | System for processing user voice utterance and method for operating same | |
| JP2017058673A (en) | Dialog processing apparatus and method, and intelligent dialog processing system | |
| CN107331400A (en) | A kind of Application on Voiceprint Recognition performance improvement method, device, terminal and storage medium | |
| CN107210040A (en) | The operating method of phonetic function and the electronic equipment for supporting this method | |
| CN108172223A (en) | Voice instruction recognition method, device and server and computer readable storage medium | |
| CN109360563B (en) | Voice control method and device, storage medium and air conditioner | |
| CN100524459C (en) | Method and system for speech recognition | |
| CN105551498A (en) | Voice recognition method and device | |
| CN109036406A (en) | A kind of processing method of voice messaging, device, equipment and storage medium | |
| CN108682414A (en) | Sound control method, voice system, equipment and storage medium | |
| CN104795065A (en) | Method for increasing speech recognition rate and electronic device | |
| CN107544272A (en) | terminal control method, device and storage medium | |
| CN109724215A (en) | Air conditioning control method, air conditioning control device, air-conditioning equipment and storage medium | |
| EP3422344B1 (en) | Electronic device for performing operation corresponding to voice input | |
| CN104299623A (en) | Automated confirmation and disambiguation modules in voice applications | |
| CN109584875A (en) | A kind of speech ciphering equipment control method, device, storage medium and speech ciphering equipment | |
| KR20190096308A (en) | electronic device | |
| KR20210020656A (en) | Apparatus for voice recognition using artificial intelligence and apparatus for the same | |
| CN110503962A (en) | Speech recognition and setting method, device, computer equipment and storage medium | |
| US20230223006A1 (en) | Voice conversion method and related device | |
| CN111916088A (en) | Voice corpus generation method and device and computer readable storage medium | |
| CN107742520A (en) | Sound control method, apparatus and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |