CN111105795B - Method and device for training offline voice firmware of smart home - Google Patents
Method and device for training offline voice firmware of smart home Download PDFInfo
- Publication number
- CN111105795B CN111105795B CN201911295463.4A CN201911295463A CN111105795B CN 111105795 B CN111105795 B CN 111105795B CN 201911295463 A CN201911295463 A CN 201911295463A CN 111105795 B CN111105795 B CN 111105795B
- Authority
- CN
- China
- Prior art keywords
- voice
- user
- firmware
- training
- offline
- 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.)
- Active
Links
- 238000012549 training Methods 0.000 title claims abstract description 138
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims description 20
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000006399 behavior Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 241001672694 Citrus reticulata Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0631—Creating reference templates; Clustering
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Automation & Control Theory (AREA)
- Artificial Intelligence (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Telephonic Communication Services (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The embodiment of the invention provides a method and a device for training off-line voice firmware of an intelligent home, wherein the method comprises the steps that a terminal device obtains a training request of the off-line voice firmware, the training request comprises a voice instruction file to be trained, a voice training scheme corresponding to the voice instruction to be trained is determined according to the voice instruction file to be trained, the voice training scheme is displayed to a user, so that the user inputs voice information according to the voice training scheme, after the voice information input by the user is received, off-line voice firmware corresponding to the voice instruction file is generated according to the voice information input by the user, and the off-line voice firmware is sent to the off-line voice device, so that the off-line voice device stores the off-line voice firmware and recognizes a voice control instruction sent by the user according to the off-line voice firmware, the problems of low voice recognition degree and fixed and limited voice semantic definition of the existing off-line voice device can be solved, the practical function of the off-line voice device is enriched, and the user experience is improved.
Description
Technical Field
The embodiment of the invention relates to the field of intelligent home, in particular to a method and a device for training off-line voice firmware of an intelligent home.
Background
The intelligent home is a hot spot industry which develops rapidly in recent years, various home devices emerge endlessly, particularly in the aspect of ZigBee wireless communication, along with the gradual access of various multifunctional products to a gateway system, a voice interaction function is an ecological entrance of an intelligent home product, and the intelligent home product occupies an extremely important position in the system and is a trend of future intelligent development.
At present, most voice interaction products on the market are networking voice interaction, the equipment price is high, the occupied resources are more, the voice recognition set of the 'voice' has defects, and the phenomena of question answering, recognition error, reaction delay and the like are easy to occur in the voice interaction; in a few off-line voice products, the phenomena of voice mode rigidity, single function and insufficient practicability generally exist, so that the existing voice products, no matter the networking voice products or the local voice products, have the problems of high price, overlong communication link, low voice recognition degree, single mode available for users, fixed voice semantic recognition standard and the like.
In summary, there is a need for a method for training an offline voice firmware of an intelligent home to solve the problems of low voice recognition and fixed and limited voice semantic definitions of the existing offline voice devices.
Disclosure of Invention
The embodiment of the invention provides a method and a device for training off-line voice firmware of an intelligent home, which are used for solving the problems of low voice recognition degree and fixed and limited voice semantic definition of the existing off-line voice equipment.
In a first aspect, an embodiment of the present invention provides a method for training an offline voice firmware in an intelligent home, including:
the method comprises the steps that terminal equipment obtains a training request of off-line voice firmware, wherein the training request comprises a voice instruction file to be trained;
the terminal equipment determines a voice training scheme corresponding to the voice instruction to be trained according to the voice instruction pattern to be trained;
the terminal equipment displays the voice training scheme to a user so that the user inputs voice information according to the voice training scheme;
after receiving the voice information input by the user, the terminal equipment generates an offline voice firmware corresponding to the voice instruction file according to the voice information input by the user;
and the terminal equipment sends the offline voice firmware to offline voice equipment so that the offline voice equipment stores the offline voice firmware and identifies a voice control instruction sent by the user according to the offline voice firmware.
According to the technical scheme, the off-line voice firmware is stored and the voice control instruction sent by the user is recognized according to the off-line voice firmware by the off-line voice equipment, so that the problems of low voice recognition degree and fixed and limited voice semantic definition of the existing off-line voice equipment can be solved, more stable and convenient high-quality off-line voice equipment is provided for the user, the practical function of the off-line voice equipment is enriched, and the user experience is improved.
Optionally, the speech training scheme comprises a plurality of training steps;
the terminal device displays the voice training scheme to a user, and the method comprises the following steps:
and the terminal equipment displays the current training step to the user, and continues to display the training steps after the current training step to the user after receiving the voice information corresponding to the current training step input by the user until the training steps in the voice training scheme are completely displayed.
In the technical scheme, the current training step is displayed to the user, and the training steps after the voice information corresponding to the current training step input by the user is received continue to be displayed to the user until all the training steps in the voice training scheme are finished, so that the voice information of the user is trained in a full voice angle through the series of training steps, and the user is facilitated to self-define the voice control instruction of the off-line voice equipment according to the self-requirement.
Optionally, after the terminal device receives the voice instruction file to be trained, the method further includes:
and the terminal equipment stores the voice instruction file in a file list so that the user can check the trained voice instruction file.
In the technical scheme, the voice instruction file is stored in the file list, so that a user can conveniently inquire the voice instruction file in the later period.
Optionally, after the terminal device generates the offline voice firmware corresponding to the voice instruction pattern, the method further includes:
the terminal equipment caches the off-line voice firmware corresponding to the voice instruction file;
the terminal equipment receives an add-delete instruction of the user, wherein the add-delete instruction comprises off-line voice firmware to be added or off-line voice firmware to be deleted;
and the terminal equipment adds or deletes the offline voice firmware to be added or deleted in the cache, and synchronously adds or deletes the corresponding voice instruction file in the file list.
In the technical scheme, the off-line voice firmware corresponding to the voice instruction file is cached, the off-line voice firmware to be added or deleted is added or deleted in the cache according to the add-delete instruction of the user, and the corresponding voice instruction file in the file list is synchronously updated, so that the user can add or delete the trained off-line voice firmware according to the self requirement, and the user experience is improved.
Optionally, the sending, by the terminal device, the offline voice firmware to the offline voice device includes:
and the terminal equipment sends the off-line voice firmware to the off-line voice equipment through a wireless module.
In the technical scheme, the wireless module is used for carrying out wireless pairing connection on the off-line voice equipment and the terminal equipment so that the terminal equipment can send the off-line voice firmware to the off-line voice equipment, and a communication basis can be provided for transmission of the off-line voice firmware.
In a second aspect, an embodiment of the present invention further provides an apparatus for training an offline voice firmware in an intelligent home, where the apparatus includes:
the device comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring a training request of an off-line voice firmware, and the training request comprises a voice instruction file to be trained;
the processing unit is used for determining a voice training scheme corresponding to the voice instruction to be trained according to the voice instruction file to be trained; displaying the voice training scheme to a user so that the user inputs voice information according to the voice training scheme; after receiving the voice information input by the user, generating an off-line voice firmware corresponding to the voice command file according to the voice information input by the user; and sending the offline voice firmware to offline voice equipment so that the offline voice equipment stores the offline voice firmware and identifies a voice control instruction sent by the user according to the offline voice firmware.
Optionally, the speech training scheme comprises a plurality of training steps;
the processing unit is specifically configured to:
and displaying the current training step to the user, and continuing to display the training steps after the current training step to the user after receiving the voice information corresponding to the current training step input by the user until the training steps in the voice training scheme are completely displayed.
Optionally, the processing unit is further configured to:
after receiving the voice instruction pattern to be trained, storing the voice instruction pattern in a pattern list so that the user views the trained voice instruction pattern.
Optionally, the processing unit is further configured to:
after the offline voice firmware corresponding to the voice instruction file is generated, caching the offline voice firmware corresponding to the voice instruction file;
receiving an add-delete instruction of the user, wherein the add-delete instruction comprises an offline voice firmware to be added or an offline voice firmware to be deleted;
and adding or deleting the offline voice firmware to be added or deleted in the cache, and synchronously adding or deleting the corresponding voice instruction file in the file list.
Optionally, the processing unit is specifically configured to:
and sending the off-line voice firmware to the off-line voice equipment through a wireless module.
In a third aspect, an embodiment of the present invention provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instruction stored in the memory and executing the method for training the offline voice firmware of the intelligent home according to the obtained program.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer-executable instructions are stored, and the computer-executable instructions are configured to enable a computer to execute a method for training an offline voice firmware of an intelligent home.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of a system architecture according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a method for training an offline voice firmware for an intelligent home according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of another method for training an offline voice firmware for a smart home according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of speech training according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus for training offline voice firmware in an intelligent home according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Fig. 1 illustrates a system architecture to which an embodiment of the present invention is applicable, which may include a mobile terminal 110, a cloud server 120, a router/switch 130, a gateway 140, an offline voice device 150, an infrared device 160, and an intelligent device 170.
Wherein, install wisdom house cell-phone APP on mobile terminal 110, the user can train off-line pronunciation firmware on this wisdom house cell-phone APP. The mobile terminal 110 may be wirelessly coupled to the offline voice device 150 through a bluetooth or WiFi network, may communicate with the cloud server 120 through the internet, and may communicate with the router/switch 130 through the WiFi network.
The cloud server 120 is configured to provide cloud services, store information such as a pre-control device configuration file and a voice instruction file, and provide data support for the gateway 140.
The gateway 140 may communicate with the cloud server 120 via the router/switch 130 to download a corresponding set of instructions from the cloud server 120 to control the corresponding smart device 170.
The offline speech device 150 may receive the offline speech firmware sent by the mobile terminal 110, recognize the speech sent by the user according to the offline speech firmware, and convert the speech into a speech control instruction to send to the gateway 140 to control the corresponding intelligent device 170 or to control the corresponding infrared device 160 through the infrared control module. The off-line voice device 150 is provided with an infrared control module, an off-line voice module and a ZigBee module, wherein the off-line voice device 150 communicates with the gateway 140 through the ZigBee module.
The infrared device 160 may be a conventional home device controlled by an infrared remote controller, such as a television, an air conditioner, and so on.
The smart device 170 may be a light, a curtain, an air conditioner, a door lock, a switch, etc. having a ZigBee protocol.
It should be noted that the structure shown in fig. 1 is only an example, and the embodiment of the present invention is not limited thereto.
Based on the above description, fig. 2 exemplarily shows a flow of a method for training an offline voice firmware by a smart home according to an embodiment of the present invention, where the flow may be executed by an apparatus for training an offline voice firmware by a smart home, and the apparatus may be located in the mobile terminal 110 shown in fig. 1, or may be the mobile terminal 110.
As shown in fig. 2, the process specifically includes:
In the embodiment of the present invention, the training request may include a voice command document to be trained, and since the user is in a "blank" voice state in a stage of taking the offline voice device, that is, does not recognize any voice behavior, the user may send a request for training the offline voice firmware to the terminal device (such as the mobile phone APP end) according to the home device that the user wants to control.
In the embodiment of the invention, the terminal equipment determines the voice training scheme corresponding to the voice instruction to be trained according to the voice instruction pattern to be trained. Specifically, the user defines the voice command for the home equipment to be controlled by using the terminal equipment, the definition can be personalized, for example, "turn on the television backlight", and the user can determine the corresponding voice training scheme according to the voice control command, wherein all control command documents customized by the user form a list and are stored in the document list for later query and configuration by the user.
And 203, the terminal device displays the voice training scheme to a user so that the user inputs voice information according to the voice training scheme.
In the embodiment of the invention, the voice training scheme comprises a plurality of training steps, the terminal equipment displays the current training step for the user, and continues to display the training steps after the current training step for the user after receiving the voice information corresponding to the current training step input by the user until the training steps in the voice training scheme are displayed completely.
Specifically, for a voice instruction of a user, for example, "turn on a television backlight", a full voice angle training is performed, by taking a reference of a fingerprint multi-angle training method at a mobile phone APP end, the mobile phone APP end automatically prompts "please say this command at a high voice", "please say this command at a low voice", "please say this command at a high speed", and "please say this command at a low speed", the user executes this voice behavior in sequence according to the voice prompt at the mobile phone APP end, and a receiver at the mobile phone APP end performs voice reception until a training flow of this voice behavior is finished.
And 204, after receiving the voice information input by the user, the terminal equipment generates an offline voice firmware corresponding to the voice instruction file according to the voice information input by the user.
In the embodiment of the invention, after receiving voice information input by a user, terminal equipment generates offline voice firmware corresponding to a voice instruction pattern according to the voice information input by the user, caches the offline voice firmware corresponding to the voice instruction pattern after the offline voice firmware corresponding to the voice instruction pattern is generated, receives an add-delete instruction of the user, the add-delete instruction comprises offline voice firmware to be added or offline voice firmware to be deleted, adds or deletes the offline voice firmware to be added or offline voice firmware to be deleted in the cache, and synchronously adds or deletes the voice instruction pattern corresponding to the offline voice firmware to be added or offline voice firmware to be deleted in a pattern list.
Specifically, the mobile phone APP end voice training module forms offline voice firmware according to the 4 trained voice behaviors and temporarily stores the offline voice firmware in the mobile phone APP end voice library, at this time, the user can customize the 2 nd to the multiple voice instruction patterns and train the offline voice firmware according to the mobile phone APP end voice prompt, and the user can add or delete the offline voice firmware formed in the cache. The user-defined file of the offline voice firmware selected by the user to be added or deleted can be synchronously stored in a file list, and the file list is updated, so that the user can check which instructions are finished after training.
In the embodiment of the invention, the terminal equipment sends the off-line voice firmware to the off-line voice equipment through the wireless module, so that the off-line voice equipment stores the off-line voice firmware and identifies the voice control instruction sent by the user according to the off-line voice firmware.
Specifically, increase pronunciation firmware function and wireless transmission link access at cell-phone APP end, be equipped with bluetooth or wiFi module in off-line speech equipment, carry out wireless pairing connection from cell-phone APP end to off-line speech equipment, can search for the only identification code that off-line speech equipment has in the cell-phone APP end, the pairing process adopts bluetooth or wiFi's exclusive pairing characteristic, the cell-phone APP end appears corresponding suggestion after the pairing is accomplished, then sends off-line speech firmware for off-line speech equipment. The speech recognition module of the mobile phone APP end only accurately recognizes the current training speech content, and whether speech semantics are correct or not can not be analyzed, and the speech training recognition model can be used for storing various timbres, tones, high speeds, low speeds and even foreign languages sent by a user in a lossless manner and is matched with the user-defined special documents one by one. After the voice training firmware is led into the off-line voice equipment, when the user uses the off-line voice equipment, the user only needs to send out the tone similar to that during training, no matter whether the user is an old person with nonstandard pronunciation or a child with fuzzy pronunciation, or the user is a tone with dialect property or a foreign language, the voice product model only carries out acoustic matching of artificial audio information and a voice module which completes internal training, after the acoustic matching is completed, a control instruction code is output to a wireless module of the off-line voice equipment, the wireless module transmits the control instruction code to a gateway, and the gateway executes the action expected by the user. The personalized training model design of the artificial audio information is considered from the practicability of user use, a large amount of work is put at the APP end and the equipment end of the mobile phone for processing, and the multifunctional, simple and convenient operation mode is presented to the user, so that the user can be identified only by using standard Mandarin without being limited to offline voice equipment, and the user population with different pronunciations is greatly enriched. To the zigBee wireless product of wisdom house majority, the user can all carry out control behind the speech training, makes off-line speech equipment's practicality strengthen greatly. In addition, aiming at the off-line voice device development stage, a voice instruction set which is possibly used by a user is embedded into hardware storage resources required by the off-line voice device, in actual use, the user can only use a small part of the voice instruction set, so that other voice instructions are wasted, the hardware storage has higher requirements, but considering that the off-line voice device is used by a relatively fixed crowd, only one person or the crowd in the same department in a company possibly exists, the crowd base number used by the off-line voice device is not high in change degree, the crowd can be used for voice set training, the obtained instruction set used for use is in tens of orders of magnitude, the requirements on hardware storage are reduced, and the cost performance of the product is improved.
In order to better explain the embodiment of the present invention, a flow of a method for training an offline voice firmware for an intelligent home provided by the embodiment of the present invention is described below through a specific implementation scenario.
As shown in fig. 3, the process includes the following steps:
The user can self-define the Nth voice instruction file according to the self requirement, and the Nth voice instruction file can be stored in the file list.
For example, as shown in fig. 4, the mobile phone APP end automatically prompts "please say the command at high voice", "please say the command at low voice", "please say the command at high speed", and "please say the command at low speed", the user executes the voice behavior in sequence according to the voice prompt of the mobile phone APP end, and a receiver of the mobile phone APP end receives voice until the training process of the voice behavior is finished, so as to obtain a plurality of voice behaviors.
After the matching speech training is finished, the APP end of the mobile phone may form an nth offline speech firmware according to the plurality of speech behaviors trained in step 302, and temporarily store the nth offline speech firmware in the APP speech library.
After the nth off-line voice firmware is temporarily stored in the APP voice library, the user can add or delete the off-line voice firmware formed in the cache, and synchronously update the document list, that is, add or delete the corresponding voice instruction document in the document list. And judging whether to edit the (N + 1) th voice command file according to the user requirement, if so, executing the step 301, and if not, executing the step 305.
The APP end of the mobile phone is in wireless pairing connection with the offline voice equipment through a Bluetooth or WiFi module, and the offline voice firmware is transmitted to the offline voice equipment; the offline voice equipment stores the offline voice firmware after receiving the offline voice firmware, and can recognize a voice control instruction sent by a user according to the offline voice firmware when being used.
The embodiment shows that by obtaining a training request of an offline voice firmware, the training request includes a voice instruction case to be trained, determining a voice training scheme corresponding to the voice instruction to be trained according to the voice instruction case to be trained, displaying the voice training scheme to a user, so that the user inputs voice information according to the voice training scheme, after receiving the voice information input by the user, generating an offline voice firmware corresponding to the voice instruction case according to the voice information input by the user, and sending the offline voice firmware to the offline voice device, so that the offline voice device stores the offline voice firmware and recognizes a voice control instruction sent by the user according to the offline voice firmware, the problems of low voice recognition degree and fixed and limited voice semantic definition of the existing offline voice device can be solved, thereby enriching practical functions of the offline voice device and improving user experience.
Based on the same technical concept, fig. 5 exemplarily shows an apparatus for training an offline voice firmware for a smart home according to an embodiment of the present invention, where the apparatus can execute a flow of a method for training an offline voice firmware for a smart home.
As shown in fig. 5, the apparatus includes:
an obtaining unit 501, configured to obtain a training request of an offline voice firmware, where the training request includes a voice instruction pattern to be trained;
a processing unit 502, configured to determine, according to the voice instruction pattern to be trained, a voice training scheme corresponding to the voice instruction to be trained; displaying the voice training scheme to a user so that the user inputs voice information according to the voice training scheme; after receiving the voice information input by the user, generating an offline voice firmware corresponding to the voice instruction file according to the voice information input by the user; and sending the offline voice firmware to offline voice equipment so that the offline voice equipment stores the offline voice firmware and identifies a voice control instruction sent by the user according to the offline voice firmware.
Optionally, the speech training scheme comprises a plurality of training steps;
the processing unit 502 is specifically configured to:
and displaying the current training step to the user, and continuing to display the training steps after the current training step to the user after receiving the voice information corresponding to the current training step input by the user until the training steps in the voice training scheme are displayed completely.
Optionally, the processing unit 502 is further configured to:
after receiving the voice instruction pattern to be trained, storing the voice instruction pattern in a pattern list so that the user views the trained voice instruction pattern.
Optionally, the processing unit 502 is further configured to:
after the offline voice firmware corresponding to the voice instruction file is generated, caching the offline voice firmware corresponding to the voice instruction file;
receiving an add-delete instruction of the user, wherein the add-delete instruction comprises offline voice firmware to be added or offline voice firmware to be deleted;
and adding or deleting the offline voice firmware to be added or deleted in the cache, and synchronously adding or deleting the corresponding voice instruction file in the file list.
Optionally, the processing unit 502 is specifically configured to:
and sending the off-line voice firmware to the off-line voice equipment through a wireless module.
Based on the same technical concept, an embodiment of the present invention provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instruction stored in the memory and executing the method for training the off-line voice firmware of the intelligent home according to the obtained program.
Based on the same technical concept, embodiments of the present invention provide a computer-readable storage medium, where computer-executable instructions are stored, and the computer-executable instructions are used to enable a computer to execute a method for training an offline voice firmware of an intelligent home.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present application and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for training offline voice firmware of smart home is characterized by comprising the following steps:
the method comprises the steps that terminal equipment obtains a training request of an offline voice firmware, wherein the training request comprises a voice instruction pattern to be trained; the voice instruction file to be trained is a file customized by a user for the off-line voice equipment according to the self-demand;
the terminal equipment determines a voice training scheme corresponding to the voice instruction to be trained according to the voice instruction pattern to be trained;
the terminal equipment displays the voice training scheme to a user so that the user inputs voice information according to the voice training scheme;
after receiving the different pieces of voice information input by the user, the terminal equipment generates an offline voice firmware corresponding to the voice command file according to the different pieces of voice information input by the user;
and the terminal equipment sends the offline voice firmware to offline voice equipment so that the offline voice equipment stores the offline voice firmware and identifies a voice control instruction sent by the user according to the offline voice firmware.
2. The method of claim 1, wherein the speech training scheme comprises a plurality of training steps;
the terminal device displays the voice training scheme to a user, and the method comprises the following steps:
and the terminal equipment displays the current training step to the user, and continues to display the training steps after the current training step to the user after receiving the voice information corresponding to the current training step input by the user until the training steps in the voice training scheme are completely displayed.
3. The method of claim 1, wherein after the terminal device receives the voice instruction document to be trained, further comprising:
and the terminal equipment stores the voice instruction file in a file list so that the user can check the trained voice instruction file.
4. The method of claim 1, wherein after the terminal device generates the offline voice firmware corresponding to the voice command pattern, the method further comprises:
the terminal equipment caches the off-line voice firmware corresponding to the voice instruction file;
the terminal equipment receives an add-delete instruction of the user, wherein the add-delete instruction comprises an offline voice firmware to be added or an offline voice firmware to be deleted;
and the terminal equipment adds or deletes the offline voice firmware to be added or deleted in the cache, and synchronously adds or deletes the corresponding voice instruction file in the file list.
5. The method of any one of claims 1 to 4, wherein the terminal device sending the offline voice firmware to an offline voice device comprises:
and the terminal equipment sends the offline voice firmware to the offline voice equipment through a wireless module.
6. The utility model provides a device of intelligence house training off-line pronunciation firmware which characterized in that includes:
the device comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring a training request of the off-line voice firmware, and the training request comprises a voice instruction file to be trained; the voice instruction file to be trained is a file customized by a user for the off-line voice equipment according to the self-demand;
the processing unit is used for determining a voice training scheme corresponding to the voice instruction to be trained according to the voice instruction pattern to be trained; displaying the voice training scheme to a user so that the user inputs voice information according to the voice training scheme; after receiving a plurality of pieces of different voice information input by the user, generating an offline voice firmware corresponding to the voice instruction file according to the plurality of pieces of different voice information input by the user; and sending the offline voice firmware to offline voice equipment so that the offline voice equipment stores the offline voice firmware and identifies a voice control instruction sent by the user according to the offline voice firmware.
7. The apparatus of claim 6, wherein the speech training scheme comprises a plurality of training steps;
the processing unit is specifically configured to:
and displaying the current training step to the user, and continuing to display the training steps after the current training step to the user after receiving the voice information corresponding to the current training step input by the user until the training steps in the voice training scheme are completely displayed.
8. The apparatus as recited in claim 6, said processing unit to further:
after receiving the voice instruction file to be trained, storing the voice instruction file in a file list so that the user can view the trained voice instruction file.
9. A computing device, comprising:
a memory for storing program instructions;
a processor for calling program instructions stored in said memory to execute the method of any one of claims 1 to 5 in accordance with the obtained program.
10. A computer-readable storage medium having computer-executable instructions stored thereon for causing a computer to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911295463.4A CN111105795B (en) | 2019-12-16 | 2019-12-16 | Method and device for training offline voice firmware of smart home |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911295463.4A CN111105795B (en) | 2019-12-16 | 2019-12-16 | Method and device for training offline voice firmware of smart home |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111105795A CN111105795A (en) | 2020-05-05 |
| CN111105795B true CN111105795B (en) | 2022-12-16 |
Family
ID=70422876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911295463.4A Active CN111105795B (en) | 2019-12-16 | 2019-12-16 | Method and device for training offline voice firmware of smart home |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111105795B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115424615A (en) * | 2022-09-01 | 2022-12-02 | 深圳市人马互动科技有限公司 | Intelligent equipment voice control method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102302855A (en) * | 2005-09-12 | 2012-01-04 | 百利游戏有限公司 | User interface system and method |
| CN108172223A (en) * | 2017-12-14 | 2018-06-15 | 深圳市欧瑞博科技有限公司 | Voice instruction recognition method, device and server and computer readable storage medium |
| CN109256116A (en) * | 2018-09-27 | 2019-01-22 | 深圳市语芯维电子有限公司 | Pass through the method for speech recognition keypad function, system, equipment and storage medium |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8825482B2 (en) * | 2005-09-15 | 2014-09-02 | Sony Computer Entertainment Inc. | Audio, video, simulation, and user interface paradigms |
| US20070271104A1 (en) * | 2006-05-19 | 2007-11-22 | Mckay Martin | Streaming speech with synchronized highlighting generated by a server |
| US10463340B2 (en) * | 2009-10-15 | 2019-11-05 | Masimo Corporation | Acoustic respiratory monitoring systems and methods |
| US9430465B2 (en) * | 2013-05-13 | 2016-08-30 | Facebook, Inc. | Hybrid, offline/online speech translation system |
| CN106856447A (en) * | 2015-12-09 | 2017-06-16 | 北京三星通信技术研究有限公司 | The processing method and relevant apparatus and terminal device of interactive contents information |
| CN106454898A (en) * | 2016-10-20 | 2017-02-22 | 北京小米移动软件有限公司 | Intelligent scene configuration method and device |
| CN109215641A (en) * | 2017-07-03 | 2019-01-15 | 九阳股份有限公司 | Home appliance voice control method and system based on cloud |
| CN109671421B (en) * | 2018-12-25 | 2020-07-10 | 苏州思必驰信息科技有限公司 | Off-line navigation customizing and implementing method and device |
| CN110120221A (en) * | 2019-06-06 | 2019-08-13 | 上海蔚来汽车有限公司 | The offline audio recognition method of user individual and its system for vehicle system |
| CN110534096A (en) * | 2019-08-22 | 2019-12-03 | 北京技德***技术有限公司 | A kind of artificial intelligent voice recognition methods and system based on microcontroller |
-
2019
- 2019-12-16 CN CN201911295463.4A patent/CN111105795B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102302855A (en) * | 2005-09-12 | 2012-01-04 | 百利游戏有限公司 | User interface system and method |
| CN108172223A (en) * | 2017-12-14 | 2018-06-15 | 深圳市欧瑞博科技有限公司 | Voice instruction recognition method, device and server and computer readable storage medium |
| CN109256116A (en) * | 2018-09-27 | 2019-01-22 | 深圳市语芯维电子有限公司 | Pass through the method for speech recognition keypad function, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111105795A (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108683574B (en) | Equipment control method, server and intelligent home system | |
| US11874904B2 (en) | Electronic device including mode for using an artificial intelligence assistant function of another electronic device | |
| CN105654950B (en) | Adaptive voice feedback method and device | |
| CN111989685A (en) | Learning method of cross-domain personalized vocabulary and electronic device thereof | |
| CN112291203B (en) | Locally saving data for voice actions with selective offline capability | |
| KR20200012933A (en) | Shortened voice user interface for assistant applications | |
| CN107004410A (en) | Voice and connecting platform | |
| CN111261151B (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN107146612A (en) | Voice guide method, device, smart machine and server | |
| CN110851221B (en) | Smart home scene configuration method and device | |
| CN103021403A (en) | Voice recognition based selecting method and mobile terminal device and information system thereof | |
| CN103049567A (en) | Retrieval method, retrieval system and natural language understanding system | |
| CN103442130A (en) | Voice control method, mobile terminal device and voice control system | |
| CN101291336A (en) | System and method for concurrent multimodal communication | |
| CN109671435B (en) | Method and apparatus for waking up smart device | |
| CN107655154A (en) | Terminal control method, air conditioner and computer-readable recording medium | |
| US20050137866A1 (en) | Interactive speech recognition model | |
| CN112735418A (en) | Voice interaction processing method and device, terminal and storage medium | |
| CN110619878B (en) | Voice interaction method and device for office system | |
| KR20200115660A (en) | How to apply intelligent | |
| KR20200074690A (en) | Electonic device and Method for controlling the electronic device thereof | |
| CN111178081A (en) | Semantic recognition method, server, electronic device and computer storage medium | |
| CN111105795B (en) | Method and device for training offline voice firmware of smart home | |
| CN107808662B (en) | Method and device for updating grammar rule base for speech recognition | |
| CN115840841A (en) | Multi-modal dialog method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 266100 Songling Road, Laoshan District, Qingdao, Shandong Province, No. 399 Applicant after: Qingdao Hisense Smart Life Technology Co.,Ltd. Address before: 266100 Songling Road, Laoshan District, Qingdao, Shandong Province, No. 399 Applicant before: QINGDAO HISENSE SMART HOME SYSTEMS Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |