WO2017219519A1 - 设备的控制方法、装置及系统 - Google Patents

设备的控制方法、装置及系统 Download PDF

Info

Publication number
WO2017219519A1
WO2017219519A1 PCT/CN2016/099469 CN2016099469W WO2017219519A1 WO 2017219519 A1 WO2017219519 A1 WO 2017219519A1 CN 2016099469 W CN2016099469 W CN 2016099469W WO 2017219519 A1 WO2017219519 A1 WO 2017219519A1
Authority
WO
WIPO (PCT)
Prior art keywords
grammar
voice
control
instruction
library
Prior art date
Application number
PCT/CN2016/099469
Other languages
English (en)
French (fr)
Inventor
胡书元
赵孙平
谢志华
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2017219519A1 publication Critical patent/WO2017219519A1/zh

Links

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
    • G10L15/28—Constructional details of speech recognition systems

Definitions

  • Embodiments of the present invention relate to the field of smart devices, and in particular, to a method, device, and system for controlling a device.
  • wearable devices are subject to product form, their size is generally small, physical size determines their storage resources and RAM resources are small, and computing power is weak. Therefore, when using wearable devices for voice control of other devices, offline Voice commands are basically limited to 3 to 5 sentences, and are set for a specific device, resulting in too few supported commands and insufficient supported devices, which affects the user experience.
  • wearable devices for voice control, the compatibility is poor (supporting fewer types of devices and supporting fewer voice commands), the industry generally adopts a preset APP or online identification solution to solve the problem.
  • Wearable devices control other devices such as other wearable devices, smart homes, smart cars have the following options:
  • the voice commands of most of the voice control appliances are integrated in the terminal device, and are installed on the terminal device in the form of APP, and the voice commands are sent to the device through infrared, WIFI, etc., to implement voice control;
  • the voice instruction set of the cloud storage device is used, and the wearable device controls the voice of the local device after accessing the cloud through the network.
  • the system resources of the device are relatively large, and cannot be used on the wearable device with limited system resources.
  • the APP application needs to be reinstalled before use, and the wearable device cannot be solved.
  • the embodiments of the present invention provide a method, an apparatus, and a system for controlling a device, so as to at least solve the technical problem that the compatibility is poor when the wearable device is used for voice control in the related art.
  • a method for controlling a device comprising: updating a grammar library based on the received plurality of grammar files, wherein each grammar file carries a control file corresponding to the grammar file a voice command of the external device; when the voice message is received, the target voice command corresponding to the voice information is identified by the updated syntax library; and the corresponding external device is controlled by the target voice command.
  • identifying, by the updated grammar library, the target voice instruction corresponding to the voice information comprises: using the updated grammar library, identifying the target voice instruction from the voice information, and determining, by the voice information, the target voice instruction request control External device.
  • controlling the corresponding external device by the target voice instruction comprises: generating a control feature code corresponding to the target voice instruction, wherein the control feature code corresponds to a control instruction of the external device; and transmitting the control feature code to the external device.
  • determining the external device controlled by the target voice instruction request based on the voice information comprises: identifying an instruction for indicating the control object from the voice information; and determining an external device corresponding to the instruction for indicating the control object.
  • updating the grammar library based on the received multiple grammar files comprises: parsing the voice instructions carried in the plurality of grammar files; saving the parsed voice instructions into the grammar library, and compiling the grammar library.
  • the gateway before updating the grammar library based on the received multiple grammar files, receiving the multiple grammar files by acquiring a plurality of grammar files corresponding to the plurality of external devices one by one, wherein the gateway is saved in the gateway
  • the grammar file of the device is a file obtained by the gateway device from any external device when any external device establishes a communication connection with the gateway device.
  • control method further includes: deleting the voice instruction corresponding to the one or more received grammar files in the grammar library.
  • the control method before deleting the voice instruction corresponding to the one or more received grammar files in the grammar library, the control method further includes: generating prompt information when disconnecting the communication connection with the target external device, wherein the prompting The information is used to prompt whether to delete a voice instruction corresponding to one or more received grammar files; receive a delete instruction or a reserve instruction, wherein the delete instruction is used to instruct execution of a voice corresponding to one or more grammar files in the deleted grammar library.
  • the step of the instruction, the reserved instruction is used to indicate that the voice instruction corresponding to the plurality of grammar files in the grammar library is reserved.
  • an apparatus for controlling an external device comprising: an updating unit configured to update a grammar library based on the received plurality of grammar files, wherein each grammar file carries a useful a voice instruction for controlling an external device corresponding to the grammar file; the identification unit is configured to: when receiving the voice information, identify a target voice instruction corresponding to the voice information through the updated grammar library; and the control unit is configured to pass the target voice The command controls the corresponding external device.
  • the updating unit includes: a parsing module configured to parse the voice commands carried in the plurality of grammar files; and a saving module configured to save the parsed voice commands into the grammar library and compile the grammar library.
  • a control system for a device comprising: a plurality of external devices, a gateway device, and a control device, wherein: each external device stores a grammar file, wherein each The grammar file carries a voice instruction for controlling an external device; the gateway device is connected to a plurality of external devices, and the gateway device is configured to send, when the control device accesses, a plurality of grammar files of the plurality of external devices saved on the gateway device to Controlling the device to update the grammar library of the control device through the plurality of grammar files; the control device is configured to, when receiving the voice information, identify the target voice command corresponding to the voice information through the updated grammar library, and control through the target voice command Corresponding external device.
  • a storage medium is also provided.
  • the medium may be configured to store program code for performing the following steps: updating a grammar library based on the received plurality of grammar files, wherein each grammar file carries a voice instruction for controlling an external device corresponding to the grammar file; When the voice information is received, the target voice command corresponding to the voice information is identified by the updated grammar library; and the corresponding external device is controlled by the target voice command.
  • the grammar library is updated based on the received grammar files, each grammar file carries a voice instruction for controlling an external device corresponding to the grammar file; when the voice message is received, the updated The grammar library identifies the target voice instruction corresponding to the voice information; and then controls the corresponding external device by the target voice instruction, because when the new external device is controlled, the grammar library can be updated by using the grammar file of the new external device, thereby solving
  • the wearable device is used for voice control, the technical problem of poor compatibility is achieved, and the technical effect of improving the compatibility of the wearable device for voice control is achieved.
  • FIG. 1 is a block diagram showing the hardware structure of a mobile terminal according to an embodiment of the present invention.
  • FIG. 2 is a flow chart of a method of controlling a device according to an embodiment of the present invention.
  • FIG. 3 is a schematic diagram of an optional voice control according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a control device of a device according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of performing syntax update according to an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of a transfer grammar file according to an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of establishing a connection according to an embodiment of the present invention.
  • FIG. 8 is a schematic diagram of syntax update according to an embodiment of the present invention.
  • FIG. 9 is a schematic diagram of grammar recognition and control in accordance with an embodiment of the present invention.
  • the method embodiment provided in Embodiment 1 of the present application can be executed in a mobile terminal (such as a wearable device), a computer terminal, or the like.
  • the mobile terminal may include one or more (only one shown) processor 101 (the processor 101 may include, but is not limited to, a microprocessor MCU or programmable A processing device such as a logic device FPGA, a memory 103 provided to store data, and a transmission device 105 provided as a communication function.
  • the structure shown in FIG. 1 is merely illustrative and does not limit the structure of the above electronic device.
  • the memory 103 can be configured as a software program and a module for storing application software, such as program instructions/modules corresponding to the control method of the device in the embodiment of the present invention, and the processor 101 executes by executing a software program and a module stored in the memory 103.
  • application software such as program instructions/modules corresponding to the control method of the device in the embodiment of the present invention
  • the processor 101 executes by executing a software program and a module stored in the memory 103.
  • the memory can include high speed random access memory and can also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory.
  • the memory can further include memory remotely located relative to the processor, which can be connected to the computer terminal over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the transmission device is arranged to receive or transmit data via a network.
  • the above-described network specific examples may include a wireless network provided by a communication provider of a computer terminal.
  • the transmission device includes a Network Interface Controller (NIC) that can pass The base station is connected to other network devices to communicate with the Internet.
  • the transmission device can be a Radio Frequency (RF) module configured to communicate with the Internet wirelessly.
  • RF Radio Frequency
  • a method embodiment of a method of controlling a device is provided, it being noted that the steps illustrated in the flowchart of the figures may be performed in a computer system such as a set of computer executable instructions, and Although the logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in a different order than the ones described herein.
  • FIG. 2 is a flowchart of a method for controlling a device according to an embodiment of the present invention. As shown in FIG. 2, the method includes the following steps:
  • Step S202 updating a grammar library based on the received plurality of grammar files, each grammar file carrying a voice instruction for controlling an external device corresponding to the grammar file.
  • Step S204 when the voice information is received, the target voice command corresponding to the voice information is identified by the updated grammar library.
  • Step S206 controlling the corresponding external device by the target voice instruction.
  • the grammar library is updated based on the received plurality of grammar files, each grammar file carrying a voice instruction for controlling a device corresponding to the grammar file; and when receiving the voice information, identifying by the updated grammar library And the target voice instruction corresponding to the voice information; and then controlling the corresponding device by using the target voice instruction, because the grammar library of the new device can be updated by using the grammar file of the new device when the new device is controlled, thereby solving the related art,
  • the wearable device performs voice control, the technical problem of poor compatibility achieves the technical effect of improving the compatibility of the wearable device for voice control.
  • the execution body of the foregoing steps may be a control device that supports voice recognition or expandable voice recognition, including but not limited to a wearable device, a mobile phone, a tablet, etc., and is mainly used for a self-resource amount (such as a storage resource and a computing resource).
  • a self-resource amount such as a storage resource and a computing resource.
  • the above external device that is, the controlled device
  • is a smart device such as a smart refrigerator, a smart TV, etc.
  • the voice instructions carried in the plurality of grammar files may be parsed; the parsed voice instructions are saved into the grammar library, and the grammar library is compiled.
  • the plurality of grammar files are received by acquiring a plurality of grammar files corresponding to the plurality of external devices one by one from the gateway device, and saving the syntax of the gateway device A file obtained by a gateway device from any external device when the file establishes a communication connection with the gateway device for any external device.
  • the foregoing gateway device includes, but is not limited to, a wireless router.
  • the following uses a wireless router as an example to describe an embodiment of the present application.
  • the specific steps of the home network-based one-to-many voice control provided by the present application are as follows:
  • step S11 the device to be controlled (ie, the controlled device) is connected to the wireless router through the WIFI wireless network.
  • Step S12 After the device to be controlled establishes a connection with the wireless router, the data transmission process is started, the home local area network accesses the smart home appliance (ie, the device to be controlled), and the voice grammar file in the device is transmitted to the dedicated storage device of the wireless router for storage.
  • the smart home appliance ie, the device to be controlled
  • Step S13 the wireless router classifies and stores the obtained grammar files according to a predetermined format, for example, storing the voice control commands of the television in a list named “TV”, and storing the voice control commands of the air conditioner in “AHU”.
  • the named list is medium.
  • Step S14 after the router recognizes that the wearable device having the voice recognition function is connected to the local area network, the router initiates a prompt to the wearable device to ask whether voice control is required, and when the confirmation is obtained, the wearable device automatically stores the grammar file stored in the router. Copy to local, compile it to take effect, and remind the user to update after completion.
  • Step S15 after the update is completed, voice control can be performed, for example, "television, switch next channel", the voice command will be decomposed into “awake words (television)” and “switch next channel (control command)" For each part, the wake-up word will start the voice recognition module of the corresponding device, and then control the command.
  • Step S16 after controlling the corresponding device according to the indication of the target voice instruction, the voice instruction corresponding to the one or more grammar files in the grammar library may be deleted, that is, when the wearable device disconnects and quits, the network is started to be executed. Update the process, delete (and optionally retain) the grammar file, leaving space for the device to facilitate the next network.
  • the prompt information is generated, and the prompt information is used to prompt whether to delete the voice instruction corresponding to the one or more grammar files; then wait for the user's selection, and Receiving a delete instruction or a reserve instruction corresponding to the user selection, the deletion instruction is used to instruct to perform a step of deleting a voice instruction corresponding to the one or more grammar files in the grammar library, and the reserve instruction is used to indicate that the reserved grammar library corresponds to the plurality of Voice instructions for grammar files.
  • the home wireless router is used as the storage device of the grammar file, and the three core steps of network update, voice wake-up, and voice recognition can implement one-to-many voice control of the wearable device.
  • the device to be controlled packages the voice grammar file to the wireless router, and the wireless router classifies and stores the voice grammar file data of the different devices to be controlled.
  • the wearable device accesses the local area network, the device obtains the voice control permission, obtains the grammar file in the router, and implements one-to-many voice control after compiling and waking up. Therefore, after the wearable device enters the home LAN, the effect of voice control on multiple devices is improved, and the compatibility between the voice recognition and each smart device is improved, thereby improving the user experience.
  • the functions can be realized by four main modules: a grammar file storage module, a grammar update module, a voice waking module, and a voice recognition module as shown in FIG. 3.
  • Syntax file storage module In the case where all external devices to be controlled are connected to a home LAN (a wireless network connected to a wireless router through a wireless communication mode), the module is responsible for receiving the device to be controlled (including the device to be controlled 1 to The grammar files in n) are classified and stored, and the module is completed by two steps.
  • Step S21 adding a device identification code, after the device to be controlled establishes a wireless communication connection with the wireless route, the grammar file is packaged, and the identification code of the device is added, and then transmitted to the wireless router, for example, the identification code of the television is 001, and the air conditioner It is 002.
  • Step S22 Generate a grammar list.
  • the wireless router After receiving the grammar file data packet, the wireless router generates a corresponding storage list according to the device identification code, where the identification code is a list name and the grammar is a list content. For example, “001 [TV] [Power On, Power Off, Switch Channel, ...]", “002 [Air Condition] [Power On, Shut Down, Increase Temperature, Turn Down Temperature, ...]", and then save in the grammar file storage module in.
  • Syntax update module This module is responsible for the update of the grammar library, which is completed by a 3-step collaboration.
  • Step S31 After the wearable device starts the voice control function, the network status check checks whether the connection is to the wireless network. When the wearable device is connected to the home LAN, the status bit is sent to the next syntax update module, otherwise the application is connected to the wireless route. For wireless networks, a status bit of "1" indicates a normal connection and a status bit of "0" indicates a disconnection.
  • Step S32 the grammar file is delivered.
  • the grammar file transfer action is initiated.
  • the action may be initiated by the wearable device or initiated by the router.
  • the grammar file storage module of the router will grammar.
  • the file list is passed to the wearable device for updating by the grammar update module.
  • Step S33 the step can be divided into two key actions of increasing and decreasing.
  • the grammar library increases or decreases the syntax instruction of the device to be controlled. If the network connection is normal, the syntax instruction of the device to be controlled is added. After the network is disconnected, the syntax command of the device to be controlled is deleted.
  • Voice wake-up module This module performs voice wake-up operation on the control device, which is completed in 3 steps.
  • Step S41 the device name is matched, and after the user inputs the voice instruction by using the microphone of the wearable device, the module matches the device name (such as a TV, a refrigerator, an air conditioner) included in the statement in the syntax list to determine the user request for control. Object.
  • the device name such as a TV, a refrigerator, an air conditioner
  • the target voice instruction corresponding to the voice information is identified by the updated grammar library, and the updated grammar library may be used to determine the target among the plurality of external devices based on the voice information.
  • the external device controlled by the voice instruction requests, that is, an instruction for indicating the control object is recognized from the voice information (eg, turning on the television, switching channels, etc.); determining an external one of the plurality of external devices corresponding to the instruction for indicating the control object device.
  • step S42 the grammar instruction is confirmed.
  • the grammar instruction set of the corresponding device is found and transmitted to the voice recognition module, so that only the voice instruction set of the current device is included in the voice recognition module.
  • Step S43 waking up the device to be controlled, after completing the above actions, the wearable device sends a control feature code corresponding to the voice command to the device to be controlled through the home local area network, and wakes up the voice recognition module on the device to be controlled.
  • the wearable device feeds back the current speech recognition module status.
  • the voice recognition module after the wearable device receives the confirmation information of the device to be controlled, the voice command is locally passed by the voice recognition engine, and after successfully identifying, the command is converted into a control feature code (the feature code and the local command of the device to be controlled M02) Correspondingly, it is sent to the device to be controlled, and the device to be controlled performs corresponding actions according to the feature code.
  • a control feature code the feature code and the local command of the device to be controlled M02
  • a control feature code corresponding to the target voice command may be generated, the control feature code corresponds to a control instruction of the external device, and then the control feature code is sent to the external device.
  • the control device controls the device to read the corresponding control command and execute it according to the control feature code.
  • the connection with the wireless router can be disconnected, and the disconnection update is performed (ie, the syntax update module performs the disconnect update), and the corresponding voice instruction is deleted to reserve the storage space for use in the next network connection.
  • the syntax database is transmitted as a control element through a standard interface, so that the wearable device can use more syntax instructions without adding hardware resources. It can realize one-to-many (the same device controls multiple devices), and even many-to-many functions, which bring great convenience to the voice interconnection between wearable devices and smart home devices.
  • the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform.
  • hardware can also be used, but in many cases the former is a better implementation.
  • the technical solution of the present invention in essence or the contribution to the related art can be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk, CD-ROM).
  • the instructions include a number of instructions for causing a terminal device (which may be a cell phone, computer, server, or network device, etc.) to perform the methods described in various embodiments of the present invention.
  • a control device for the device is also provided in the embodiment of the present invention.
  • the device is used to implement the above embodiments and preferred embodiments, and the description thereof has been omitted.
  • the term "module” may implement a combination of software and/or hardware of a predetermined function.
  • the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.
  • the apparatus may include an update unit 41, an identification unit 43, and a control unit 45.
  • the updating unit 41 is configured to update the grammar library based on the received plurality of grammar files, wherein each grammar file carries a voice instruction for controlling an external device corresponding to the grammar file.
  • the identification unit 43 is configured to recognize, when the voice information is received, the target voice command corresponding to the voice information through the updated grammar library.
  • the control unit 45 is configured to control the corresponding external device by the target voice command
  • the update unit updates the grammar library based on the received plurality of grammar files, each of the grammar files carrying a voice instruction for controlling an external device corresponding to the grammar file; and the recognition unit updates by receiving the voice information
  • the subsequent grammar library identifies the target voice instruction corresponding to the voice information; the control unit controls the corresponding external device through the target voice instruction, and the grammar library can be updated by using the grammar file of the new external device when controlling the new external device. Therefore, the technical problem of poor compatibility when using the wearable device for voice control in the related art is solved, and the technology for improving the compatibility of the voice control of the wearable device is realized. Effect.
  • the foregoing device may be used on a control device that supports voice recognition or expandable voice recognition, including but not limited to a wearable device, a mobile phone, a tablet, etc., and is mainly used for a wearable device.
  • the above-mentioned controlled device is a smart device (such as a smart refrigerator, a smart TV, etc.) that supports voice control.
  • the updating unit may include: a parsing module configured to parse out the voice commands carried in the plurality of grammar files; and a saving module configured to save the parsed voice commands into the grammar library and compile the grammar library.
  • the update unit acquires a plurality of grammar files corresponding to the plurality of external devices one by one from the gateway device, and the grammar file saved in the gateway device is A file acquired by the gateway device from any external device when an external device establishes a communication connection with the gateway device.
  • the above gateway devices include, but are not limited to, wireless routers.
  • the syntax database is transmitted as a control element through a standard interface, so that the wearable device can use more syntax instructions without adding hardware resources. It can realize one-to-many (the same device controls multiple devices), and even many-to-many functions, which bring great convenience to the voice interconnection between wearable devices and smart home devices.
  • the updating unit is further configured to use the updated grammar library to identify the target voice instruction from the voice information, and determine an external device controlled by the target voice instruction request based on the voice information.
  • the updating unit is further configured to generate a control signature corresponding to the target voice instruction, wherein the control signature corresponds to a control instruction of the external device; and the control signature is sent to the external device.
  • the updating unit is further configured to: identify an instruction for indicating the control object from the voice information; and determine an external device corresponding to the instruction for indicating the control object.
  • control unit is further configured to delete one of the received grammar libraries corresponding to one or more Voice instructions for grammar files.
  • control unit is further configured to generate prompt information when disconnecting the communication connection with the target external device, wherein the prompt information is used to prompt whether to delete the voice instruction corresponding to the one or more received grammar files; a delete instruction or a hold instruction, wherein the delete instruction is used to instruct execution of a step of deleting a voice instruction corresponding to one or more grammar files in the grammar library, the reserve instruction being used to indicate a voice corresponding to the plurality of grammar files in the reserved grammar library instruction.
  • each of the above modules may be implemented by software or hardware.
  • the foregoing may be implemented by, but not limited to, the foregoing modules are all located in the same processor; or, the above modules are in any combination.
  • the forms are located in different processors.
  • a control system for the device is also provided in the embodiment of the present invention.
  • the system includes: a plurality of external devices, a gateway device, and a wearable device.
  • a plurality of external devices each of which is stored with a grammar file, wherein each grammar file carries a voice instruction for controlling the external device.
  • the gateway device is configured to send, when the control device accesses, multiple grammar files of the plurality of external devices saved on the gateway device to the control device, to update the control device by using multiple grammar files Syntax library.
  • a control device configured to: when receiving the voice information, identify the target voice instruction corresponding to the voice information through the updated grammar library, and control the corresponding external device by using the indication of the target voice instruction.
  • the above control devices include, but are not limited to, wearable devices.
  • a grammar file of a plurality of external devices is saved on the gateway device, and when the control device accesses, the gateway device sends multiple grammar files of the plurality of external devices saved on the gateway device to the control device to pass the multiple
  • the grammar file updates the grammar library of the control device. Since the new external device is controlled, the grammar library of the new external device can be used to enter the grammar library.
  • the line update when the control device receives the voice information, identifies the target voice instruction corresponding to the voice information through the updated grammar library, and controls the corresponding external device by the instruction of the target voice instruction, thereby solving the related art and using
  • the wearable device performs voice control the technical problem of poor compatibility achieves the technical effect of improving the compatibility of the wearable device for voice control.
  • the one-to-many voice control method between the wearable device and the smart device is suitable for all devices including voice recognition or expandable voice recognition.
  • the present application only Smart watches are used as wearable devices, smart air conditioners, and smart TVs as an example. As shown in Figure 5:
  • Step S502 transmitting a grammar file.
  • the wireless router M03 and the device to be controlled M02 initiate a syntax update, and the control request requests control of the device to be controlled.
  • the device to be controlled pops up a dialog box (the content of the dialog box is whether or not to agree to control) is confirmed by the user. (Also can be a voice prompt).
  • the device to be controlled transmits the grammar file to the router by adding the device identification code and packaging the grammar file. If the user does not agree to control the application, select "No", then the feedback rejection flag is sent to the wireless route. After the wireless route receives the flag, it is judged whether or not to agree to the control. Otherwise, the process falls back to the beginning, and if so, the grammar file is received.
  • the wireless router stores the grammar files sent by different devices as a grammar storage list of a specific format.
  • Step S504 the voice recognition connection confirmation process is initiated by the wearable device M01 to establish a connection with the smart TV (ie, the device to be controlled).
  • an active initiation connection scheme may be adopted.
  • the wearable device M01 initiates a request, and the request determines whether a connection is required. After selecting “Yes”, the smart watch initiates a connection and sends a connection request to the wireless router. After selecting "No”, go back to the previous step or pop up the request again; if the wireless route audit approves the connection, after agreeing to connect, start the syntax list transmission process, and send the grammar file in the grammar storage list to the wearable device.
  • the wearable device determines whether the connection is successful, and starts the syntax update module after confirming that the connection is successful. A list of legal files, if the connection fails, the connection is started again.
  • Step S506 a syntax update step of transmitting a grammar file to the wearable device by wireless routing.
  • the grammar update step is a process of compiling the received grammar file, as shown in FIG. 8, receiving the grammar file in the grammar storage list, determining whether the reception is successful, receiving again if the reception fails, and performing the grammar library update if the reception is successful. , silently compile the steps, and then wait for the voice wake-up module to wake up.
  • Step S5062 Receive a grammar file, the wearable device starts a grammar update step, and the wireless router M03 sends the grammar file in the grammar storage list to the wearable device, and the wearable device determines whether the grammar file is successfully received. If it is judged as "success”, the process proceeds to step S5064, the new step grammar library; if it is judged as "failure", the grammar file is re-received.
  • Step S5064 The grammar library is updated. After receiving the grammar file, the wearable device parses the voice instruction, and then updates the voice instruction in the grammar database, and performs silent compilation to enable the voice recognition function.
  • the above grammar file format can be in bnf standard format or other standardized formats.
  • bnf is taken as an example, and the grammar file is updated according to the key steps of “grammr ⁇ slot ⁇ start ⁇ ”.
  • bnf is taken as an example, and the grammar file is updated according to the key steps of “grammr ⁇ slot ⁇ start ⁇ ”.
  • grammr ⁇ slot ⁇ start ⁇ is an instruction to select a TV channel:
  • Step S508 the voice recognition control step, after the wearable device fuses the grammar file, the voice control can be performed.
  • This step is mainly divided into two parts: voice wake-up and voice recognition. As shown in Figure 9:
  • the wearable device When the user speaks a single instruction, such as "Television opens Hunan Satellite TV", the wearable device exits standby, and the instruction recognizes on the wearable device M01, first determines the device identification code, and generates a wake-up command for voice wake-up. And sent to the device to be controlled M02, the device to be controlled exits standby and judges whether the heterodyne control is enabled. If not, the device continues to stand by, if yes, the voice recognition is started, and the device to be controlled responds according to the wakeup result, and the wakeup succeeds. The wearable device feeds back and initiates speech recognition, and when it fails, it returns to standby.
  • a single instruction such as "Television opens Hunan Satellite TV”
  • the fused grammar file can be removed when the network is disconnected.
  • This step is a process of updating to the reverse update of step S506, that is, the process of adding the grammar becomes the process of deleting the grammar instruction.
  • the syntax update has two trigger modes, one is that the network link is disconnected, that is, after the link link is disconnected (such as exceeding the distance supported by the communication, the signal is too weak, etc.), the syntax update is triggered;
  • the type is active click disconnection, whether it is the control device or the device to be controlled, click cancel control, the control flag will be restored, and the syntax update will be triggered.
  • Embodiments of the present invention also provide a storage medium.
  • the storage medium can be configured to store program code for performing the following steps:
  • the storage medium is further arranged to store program code for performing the following steps:
  • the foregoing storage medium may include, but not limited to, a USB flash drive, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, and a magnetic memory.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • a mobile hard disk e.g., a hard disk
  • magnetic memory e.g., a hard disk
  • the processor is executed according to the stored program code in the storage medium: updating the grammar library based on the received multiple grammar files, where each grammar file carries a control for corresponding to the grammar file The voice command of the external device; when the voice message is received, the target voice command corresponding to the voice information is identified by the updated grammar library; and the corresponding external device is controlled by the target voice command.
  • the processor performs: generating, according to the stored program code in the storage medium, a control feature code corresponding to the target voice instruction, wherein the control feature code corresponds to a control instruction of the external device; and the sending control feature Code to an external device.
  • the grammar library is updated based on the received grammar files, each grammar file carries a voice instruction for controlling an external device corresponding to the grammar file; when the voice message is received, the updated The grammar library identifies the target voice instruction corresponding to the voice information; and then controls the corresponding external device by the target voice instruction, because when the new external device is controlled, the grammar library can be updated by using the grammar file of the new external device, thereby solving
  • the wearable device is used for voice control, the technical problem of poor compatibility is achieved, and the technical effect of improving the compatibility of the wearable device for voice control is achieved.

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)
  • Selective Calling Equipment (AREA)
  • Telephonic Communication Services (AREA)

Abstract

一种设备的控制方法、装置及系统，该方法包括：基于接收到的多个语法文件更新语法库，其中每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令(S202)；在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令(S204)；通过目标语音指令控制对应的外部设备(S206)。该方法解决了相关技术中，使用可穿戴设备进行语音控制时，其兼容性较差的技术问题。

Description

设备的控制方法、装置及系统 技术领域
本发明实施例涉及智能设备领域，具体而言，涉及一种设备的控制方法、装置及系统。
背景技术
目前，可穿戴设备受制于产品形式，其体型普遍较小，物理尺寸决定了其存储资源和RAM资源较小，计算能力较弱，因此，使用可穿戴设备对其他设备进行语音控制时，其离线语音的指令基本局限在3至5句，且都是针对某个特定设备进行设置的，从而造成了其支持的指令过少，且支持的设备不够多，影响了用户的体验。
在面对使用可穿戴设备进行语音控制时，其兼容性较差(支持的设备类型少且支持的语音指令较少)的问题，业界普遍采用预置APP或者在线识别的方案来解决该问题，可穿戴设备控制其他设备(如其他可穿戴设备、智能家居、智能汽车)有如下几种方案：
方案一，在终端设备中将大部分的可声控电器的语音指令都集成在一起，以APP的形式安装在终端设备上，通过红外、WIFI等方式将语音指令发送给设备，实现语音控制；
方案二，利用云端存储设备的语音指令集，可穿戴设备通过网络接入云端后对本地设备进行语音控制。
在方案一中，对设备的系统资源消耗较大，无法在系统资源有限的可穿戴设备上使用，另外，如果更换了终端设备还要重新安装这些APP应用才能使用，仍然无法解决可穿戴设备的兼容性较差的问题；在方案二，当网络断开时，则无法使用语音控制功能。
针对相关技术中，使用可穿戴设备进行语音控制时，其兼容性较差的 技术问题，目前尚未提出有效的解决方案。
发明内容
本发明实施例提供了一种设备的控制方法、装置及系统，以至少解决相关技术中，使用可穿戴设备进行语音控制时，其兼容性较差的技术问题。
根据本发明实施例的一个方面，提供了一种设备的控制方法，该方法包括：基于接收到的多个语法文件更新语法库，其中，每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令；在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令；通过目标语音指令控制对应的外部设备。
可选地，通过更新后的语法库识别出与语音信息对应的目标语音指令包括：使用更新后的语法库，从语音信息中识别出目标语音指令，并基于语音信息确定被目标语音指令请求控制的外部设备。
可选地，通过目标语音指令控制对应的外部设备包括：生成对应于目标语音指令的控制特征码，其中，控制特征码对应于外部设备的控制指令；发送控制特征码至外部设备。
可选地，基于语音信息确定被目标语音指令请求控制的外部设备包括：从语音信息中识别出用于指示控制对象的指令；确定与用于指示控制对象的指令对应的外部设备。
可选地，基于接收到的多个语法文件更新语法库包括：解析出多个语法文件中携带的语音指令；将解析出的语音指令保存至语法库中，并编译语法库。
可选地，在基于接收到的多个语法文件更新语法库之前，采用如下方式接收多个语法文件：从网关设备获取与多个外部设备一一对应的多个语法文件，其中，保存在网关设备的语法文件为任一外部设备建立与网关设备的通信连接时，由网关设备从任一外部设备获取的文件。
可选地，在通过目标语音指令控制对应的外部设备之后，该控制方法还包括：删除语法库中对应于一个或多个接收到的语法文件的语音指令。
可选地，在删除语法库中对应于一个或多个接收到的语法文件的语音指令之前，该控制方法还包括：在断开与目标外部设备的通信连接时，生成提示信息，其中，提示信息用于提示是否删除对应于一个或多个接收到的语法文件的语音指令；接收删除指令或保留指令，其中，删除指令用于指示执行删除语法库中对应于一个或多个语法文件的语音指令的步骤，保留指令用于指示保留语法库中的对应于多个语法文件的语音指令。
根据本发明实施例的另一个方面，提供了一种外部设备的控制装置，该装置包括：更新单元，设置为基于接收到的多个语法文件更新语法库，其中，每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令；识别单元，设置为在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令；控制单元，设置为通过目标语音指令控制对应的外部设备。
可选地，更新单元包括：解析模块，设置为解析出多个语法文件中携带的语音指令；保存模块，设置为将解析出的语音指令保存至语法库中，并编译语法库。
根据本发明实施例的另一个方面，提供了一种设备的控制系统，该系统包括：多个外部设备、网关设备和控制设备,其中：每个外部设备上保存有语法文件，其中，每个语法文件中携带有用于控制外部设备的语音指令；网关设备与多个外部设备连接，网关设备设置为在控制设备接入时，发送保存在网关设备上的多个外部设备的多个语法文件至控制设备，以通过多个语法文件更新控制设备的语法库；控制设备设置为在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令，并通过目标语音指令控制对应的外部设备。
根据本发明实施例的另一个方面，还提供了一种存储介质。上述存储 介质可以被设置为存储用于执行以下步骤的程序代码：基于接收到的多个语法文件更新语法库，其中，每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令；在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令；通过目标语音指令控制对应的外部设备。
在本发明实施例中，基于接收到的多个语法文件更新语法库，每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令；在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令；然后通过目标语音指令控制对应的外部设备，由于在对新外部设备进行控制时，可利用新外部设备的语法文件对语法库进行更新，从而解决了相关技术中，使用可穿戴设备进行语音控制时，其兼容性较差的技术问题，实现了提高可穿戴设备进行语音控制的兼容性的技术效果。
附图说明
此处所说明的附图用来提供对本发明的进一步理解，构成本申请的一部分，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。在附图中：
图1是根据本发明实施例的一种移动终端的硬件结构框图；
图2是根据本发明实施例的设备的控制方法的流程图；
图3是根据本发明实施例的一种可选的语音控制的示意图；
图4是根据本发明实施例的设备的控制装置的示意图；
图5是根据本发明实施例的进行语法更新的示意图；
图6是根据本发明实施例的传输语法文件的示意图；
图7是根据本发明实施例的建立连接的示意图；
图8是根据本发明实施例的语法更新的示意图；
图9是根据本发明实施例的语法识别与控制的示意图。
具体实施方式
下文中将参考附图并结合实施例来详细说明本发明。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。
需要说明的是，本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
实施例1
本申请实施例一所提供的方法实施例可以在移动终端(如可穿戴设备)、计算机终端或者类似的运算装置中执行。以运行在移动终端上为例，如图1所示，移动终端可以包括一个或多个(图中仅示出一个)处理器101(处理器101可以包括但不限于微处理器MCU或可编程逻辑器件FPGA等的处理装置)、设置为存储数据的存储器103、以及设置为通信功能的传输装置105。本领域普通技术人员可以理解，图1所示的结构仅为示意，其并不对上述电子装置的结构造成限定。
存储器103可设置为存储应用软件的软件程序以及模块，如本发明实施例中的设备的控制方法对应的程序指令/模块，处理器101通过运行存储在存储器103内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的方法。存储器可包括高速随机存储器，还可包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器可进一步包括相对于处理器远程设置的存储器，这些远程存储器可以通过网络连接至计算机终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
传输装置设置为经由一个网络接收或者发送数据。上述的网络具体实例可包括计算机终端的通信供应商提供的无线网络。在一个实例中，传输装置包括一个网络适配器(Network Interface Controller，NIC)，其可通过 基站与其他网络设备相连从而可与互联网进行通讯。在一个实例中，传输装置可以为射频(Radio Frequency，RF)模块，其设置为通过无线方式与互联网进行通讯。
根据本发明实施例，提供了一种设备的控制方法的方法实施例，需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
图2是根据本发明实施例的设备的控制方法的流程图，如图2所示，该方法包括如下步骤：
步骤S202，基于接收到的多个语法文件更新语法库，每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令。
步骤S204，在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令。
步骤S206，通过目标语音指令控制对应的外部设备。
通过上述实施例，基于接收到的多个语法文件更新语法库，每个语法文件中携带有用于控制与语法文件对应的设备的语音指令；在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令；然后通过目标语音指令控制对应的设备，由于在对新设备进行控制时，可利用新设备的语法文件对语法库进行更新，从而解决了相关技术中，使用可穿戴设备进行语音控制时，其兼容性较差的技术问题，实现了提高可穿戴设备进行语音控制的兼容性的技术效果。
可选地，上述步骤的执行主体可以为支持语音识别或者可拓展语音识别的控制设备，包括但不局限于可穿戴设备、手机、平板等，主要用于自身资源量(如存储资源、计算资源等)较小的设备，如可穿戴设备，后续以可穿戴设备为例进行说明。上述的外部设备(也即被控制设备)为支持语音控制的智能设备(如智能冰箱、智能电视等)。
在上述实施例中，在基于接收到的多个语法文件更新语法库时，可解析出多个语法文件中携带的语音指令；将解析出的语音指令保存至语法库中，并编译语法库。
具体地，在基于接收到的多个语法文件更新语法库之前，采用如下方式接收多个语法文件：从网关设备获取与多个外部设备一一对应的多个语法文件，保存在网关设备的语法文件为任一外部设备建立与网关设备的通信连接时，由网关设备从任一外部设备获取的文件。
上述的网关设备包括但不局限于无线路由器，下面以无线路由器为例详述本申请的实施例。本申请提供的基于家庭网络的一对多语音控制的具体步骤如下：
步骤S11，待控制设备(即受控设备)通WIFI无线网络与无线路由器连接。
步骤S12，待控制设备与无线路由器建立连接后，启动数据传输流程，家庭局域网访问智能家电设备(即待控制设备)，并将设备中的语音语法文件传输到无线路由器的专用存储设备上保存。
步骤S13，无线路由器将得到的语法文件按照预定格式进行分类存储，如，将电视机的语音控制指令都存储在已“TV”命名的列表中，将空调的语音控制指令存储在以“AHU”命名的列表中等。
步骤S14，当路由器识别到具有语音识别功能的可穿戴设备连接该局域网后，路由器向可穿戴设备发起询问是否需要语音控制的提示，当得到确认后可穿戴设备自动将存储在路由器中的语法文件拷贝到本地，并进行编译使其生效，完成后提醒用户更新完毕。
步骤S15，在更新完毕之后，可以进行语音控制，例如，“电视机，切换下一个频道”，语音指令将被分解为“唤醒词(电视)”和“切换下一频道(控制指令)”两个部分，唤醒词将启动对应设备的语音识别模块，然后再进行指令控制。
步骤S16，在按照目标语音指令的指示控制对应的设备之后，可删除语法库中对应于一个或多个语法文件的语音指令，也即当可穿戴设备断开连接退网后，开始执行退网更新流程，删除(也可以选择保留)语法文件，给设备留出空间，方便下次组网。
具体地，在断开与外部设备(即待控制设备)的通信连接时，生成提示信息，提示信息用于提示是否删除对应于一个或多个语法文件的语音指令；然后等待用户的选择，并接收对应于用户选择的删除指令或保留指令，删除指令用于指示执行删除语法库中对应于一个或多个语法文件的语音指令的步骤，保留指令用于指示保留语法库中的对应于多个语法文件的语音指令。
在上述实施例中，将家庭无线路由器作为语法文件的存储设备，通过连网更新，语音唤醒，语音识别三个核心步骤可实现可穿戴设备的一对多的语音控制。在家庭局域网中，待控制设备与无线路由器连接后，待控制设备将语音语法文件打包发送给无线路由器，由无线路由器对接收到的不同待控制设备的语音语法文件数据进行分类存储。当可穿戴设备接入该局域网后通过申请获取语音控制权限，获取路由器中的语法文件，经过编译融合、语音唤醒后实现一对多语音控制。从而实现了可穿戴设备进入家庭局域网后，可对多个设备进行语音控制的效果，提升了语音识别与各个智能设备之间的兼容性，进而提升了用户体验。
在控制设备(即可穿戴设备)运行本申请的方法时，可通过如图3所示的语法文件存储模块、语法更新模块、语音唤醒模块以及语音识别模块4个主要模块实现其功能。
语法文件存储模块：在所有外部待控制设备都连接到家庭局域网(通过无线通讯模连接至无线路由的无线网络)的情况下，该模块负责将接收到的待控制设备(包括待控制设备1至n)中的语法文件进行分类存储，该模块由2个步骤协作完成。
步骤S21，加入设备识别码，待控制设备在与无线路由建立无线通讯连接后，将语法文件打包，并将设备的识别码加入，然后传输给无线路由器，例如，电视的识别码为001，空调的为002。
步骤S22，生成语法列表，无线路由器接收到语法文件数据包后，根据设备识别码生成对应的存储列表，识别码为列表名称，语法为列表内容。如，“001[电视][开机，关机，切换频道，……]”，“002[空调][开机，关机，调高温度，调低温度，……]”，然后保存在语法文件存储模块中。
语法更新模块：该模块负责语法库的更新，该模块由3步骤协作完成。
步骤S31，可穿戴设备启动语音控制功能后，网络状态检查，检查是否连接至无线网络，当可穿戴设备与家庭局域网连接正常，则发送状态位给下个语法更新模块，否则申请连接至无线路由的无线网络，状态位为“1”表示正常连接，状态位为“0”表示断开。
步骤S32，语法文件传递，当网络检查完成后，则启动语法文件传递动作，该动作可由可穿戴设备主动发起，也可以由路由器主动发起，在发起传递指令后，路由器的语法文件存储模块将语法文件列表传递给可穿戴设备，供语法更新模块进行更新。
步骤S33，该步骤可分为增加、减少两个关键动作，更新完成后，其语法库会增加或者减少待控制设备的语法指令，若网络连接正常后，则增加待控制设备的语法指令，若网络断开后，则删除待控制设备的语法指令。
语音唤醒模块：该模块对待控制设备进行语音唤醒操作，由3个步骤完成。
步骤S41，设备名称匹配，用户使用可穿戴设备的麦克风输入语音指令后，该模块对语句中含有的设备名称(如电视、电冰箱、空调)在语法列表中进行匹配，以确定用户请求控制的对象。
具体地，在通过更新后的语法库识别出与语音信息对应的目标语音指令是，可使用更新后的语法库，基于语音信息确定多个外部设备中被目标 语音指令请求控制的外部设备，即从语音信息中识别出用于指示控制对象的指令(如，打开电视、切换频道等)；确定多个外部设备中与用于指示控制对象的指令对应的外部设备。
步骤S42，确认语法指令，经过步骤S41后找到对应设备的语法指令集并传递给语音识别模块，使语音识别模块内只有当前设备的语音指令集。
步骤S43，唤醒待控制设备，完成以上动作后，可穿戴设备通过家庭局域网发送对应于语音指令的控制特征码给待控制设备，唤醒待控制设备上的语音识别模块，唤醒成功后待控制设备向可穿戴设备反馈当前语音识别模块状态。
语音识别模块，当可穿戴设备接收到待控制设备的确认信息后，语音指令在本地经过语音识别引擎，成功识别后，将指令转化为控制特征码(该特征码与待控制设备M02的本地指令对应)，发送给待控制设备，待控制设备根据特征码做出相应动作。
需要说明的是，在按照目标语音指令的指示控制对应的外部设备时，可生成对应于目标语音指令的控制特征码，控制特征码对应于外部设备的控制指令，然后发送控制特征码至外部待控制设备，控制设备根据控制特征码从本地读取对应的控制指令并执行。在控制完成之后，可断开与无线路由的连接，并执行断开更新(即语法更新模块执行断开更新)，删除对应的语音指令，以预留出存储空间，供下次联网时使用。
通过上述实施例，在可穿戴设备与智能设备建立连接后，通过标准接口，将语法数据库作为控制元素进行传递，使可穿戴设备在不用增加硬件资源的情况，也可以使用更多的语法指令，可实现一对多(同一个设备控制多个设备)，甚至多对多的功能，给可穿戴设备、智能家居设备之间的语音互联等都带来极大的便利。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当 然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本发明各个实施例所述的方法。
实施例2
本发明实施例中还提供了一种设备的控制装置。该装置用于实现上述实施例及优选实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。
图4是根据本发明实施例的设备的控制装置的示意图。如图4所示，该装置可以包括：更新单元41、识别单元43以及控制单元45。
更新单元41，设置为基于接收到的多个语法文件更新语法库，其中，每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令。
识别单元43，设置为在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令。
控制单元45，设置为通过目标语音指令控制对应的外部设备
通过上述实施例，更新单元基于接收到的多个语法文件更新语法库，每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令；识别单元在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令；控制单元通过目标语音指令控制对应的外部设备，由于在对新外部设备进行控制时，可利用新外部设备的语法文件对语法库进行更新，从而解决了相关技术中，使用可穿戴设备进行语音控制时，其兼容性较差的技术问题，实现了提高可穿戴设备进行语音控制的兼容性的技 术效果。
可选地，上述装置可用在支持语音识别或者可拓展语音识别的控制设备上，包括但不局限于可穿戴设备、手机、平板等，主要用于可穿戴设备。上述的被控制设备为支持语音控制的智能设备(如智能冰箱、智能电视等)。
在上述实施例中，更新单元可包括：解析模块，设置为解析出多个语法文件中携带的语音指令；保存模块，设置为将解析出的语音指令保存至语法库中，并编译语法库。
具体地，更新单元在获取与多个外部设备一一对应的多个语法文件时，是从网关设备获取与多个外部设备一一对应的多个语法文件，保存在网关设备的语法文件为任一外部设备建立与网关设备的通信连接时，由网关设备从任一外部设备获取的文件。上述的网关设备包括但不局限于无线路由器。
通过上述实施例，在可穿戴设备与智能设备建立连接后，通过标准接口，将语法数据库作为控制元素进行传递，使可穿戴设备在不用增加硬件资源的情况，也可以使用更多的语法指令，可实现一对多(同一个设备控制多个设备)，甚至多对多的功能，给可穿戴设备、智能家居设备之间的语音互联等都带来极大的便利。
可选地，更新单元还设置为使用更新后的语法库，从语音信息中识别出目标语音指令，并基于语音信息确定被目标语音指令请求控制的外部设备。
可选地，更新单元还设置为生成对应于目标语音指令的控制特征码，其中，控制特征码对应于外部设备的控制指令；发送控制特征码至外部设备。
可选地，更新单元还设置为从语音信息中识别出用于指示控制对象的指令；确定与用于指示控制对象的指令对应的外部设备。
可选地，控制单元还设置为删除语法库中对应于一个或多个接收到的 语法文件的语音指令。
可选地，控制单元还设置为在断开与目标外部设备的通信连接时，生成提示信息，其中，提示信息用于提示是否删除对应于一个或多个接收到的语法文件的语音指令；接收删除指令或保留指令，其中，删除指令用于指示执行删除语法库中对应于一个或多个语法文件的语音指令的步骤，保留指令用于指示保留语法库中的对应于多个语法文件的语音指令。
需要说明的是，上述各个模块是可以通过软件或硬件来实现的，对于后者，可以通过以下方式实现，但不限于此：上述模块均位于同一处理器中；或者，上述各个模块以任意组合的形式分别位于不同的处理器中。
实施例3
本发明实施例中还提供了一种设备的控制系统。该系统包括：多个外部设备、网关设备以及可穿戴设备。
多个外部设备，每个外部设备(即受控设备)上保存有语法文件，其中，每个语法文件中携带有用于控制外部设备的语音指令。
网关设备，与多个外部设备连接，网关设备设置为在控制设备接入时，发送保存在网关设备上的多个外部设备的多个语法文件至控制设备，以通过多个语法文件更新控制设备的语法库。
控制设备，控制设备设置为在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令，并通过目标语音指令的指示控制对应的外部设备。
上述的控制设备包括但不局限于可穿戴设备。
通过上述实施例，在网关设备上保存多个外部设备的语法文件，在控制设备接入时，网关设备发送保存在网关设备上的多个外部设备的多个语法文件至控制设备，以通过多个语法文件更新控制设备的语法库，由于在对新的外部设备进行控制时，可利用新的外部设备的语法文件对语法库进 行更新，控制设备在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令，并通过目标语音指令的指示控制对应的外部设备，从而解决了相关技术中，使用可穿戴设备进行语音控制时，其兼容性较差的技术问题，实现了提高可穿戴设备进行语音控制的兼容性的技术效果。
在上述实施例中，可穿戴设备与智能设备(即待控制设备或被控设备)之间的一对多的声控方式适合所有含有语音识别或者可拓展语音识别的设备，在本申请中，仅以智能手表为可穿戴设备，智能空调、智能电视为例进行详述。如图5所示：
步骤S502，传输语法文件。
如图6所示，连接成功后，无线路由器M03和待控制设备M02启动语法更新，发送控制申请请求对待控制设备的控制，待控制设备弹出对话框(对话框内容为是否同意控制)由用户确认(也可以为语音提示)，经过确认同意后待控制设备通过加入设备识别码，并打包语法文件，将语法文件传输给路由器。若用户不同意控制申请，选择“否”，则反馈拒绝标志给无线路由，在无线路由接收到标志后，判断是否同意控制，若否则流程回退到开始，若是则接收语法文件。无线路由器将不同设备发送的语法文件存储为特定格式的语法存储列表。
步骤S504，语音识别连接确认流程，由可穿戴设备M01发起连接，建立与智能电视(即待控制设备)的连接。
具体地，可采用主动发起连接方案，如图7所示，可穿戴设备M01启动请求，该请求判断是否需要连接，在选择“是”之后，智能手表启动连接，发送连接请求给无线路由，在选择“否”之后，则回到前一步骤或者再次弹出请求；由无线路由审核是否同意连接，在同意连接后，启动语法列表传输流程，将语法存储列表中的语法文件发送至可穿戴设备，可穿戴设备判断连接是否成功，在确认连接成功后启动语法更新模块，接收语 法文件列表，若连接失败则再次启动连接。
步骤S506，语法更新步骤，由无线路由传输语法文件给可穿戴设备。
语法更新步骤是将接收到的语法文件编译处理的过程，如图8所示，接收语法存储列表中的语法文件，判断接收是否成功，若接收失败则再次接收，若接收成功则执行语法库更新、静默编译的步骤，然后等待语音唤醒模块被唤醒。
步骤S5062，接收语法文件，可穿戴设备启动语法更新步骤，无线路由器M03发送语法存储列表中的语法文件给可穿戴设备，可穿戴设备再判断语法文件的接收是否成功。若判断为“成功”，则进入步骤S5064，新步语法库；若判断为“失败”，则重新接收语法文件。
步骤S5064，语法库更新，可穿戴设备在接收到语法文件后，解析得到语音指令，然后将语音指令更新在语法数据库中，并进行静默编译，以使能语音识别功能。
上述的语法文件格式可采用bnf标准格式，也可以使用其他标准化格式，本文以bnf为例，将语法文件按照“grammr\slot\start\”的关键步骤进行数据库更新。如下是一条选择电视频道的指令：
#BNF+IAT 1.0UTF-8；
！grammar switch_channel；
！slot<contact>；
！slot<appname>；
！slot<song>；
！start<actions>；
<actions>:<switch>
<switch>:(打开|选择)<contact>；
<contact>:CCTV|湖南卫视|陕西卫视|中央一台|
在上述指令中，先确定指令的目的是切换频道(即“switch_channel”)，然后确定动作为打开或者切换(即“<actions>:<switch>”)，打开或者切换的目标(即“<contact>”)可以为“CCTV、湖南卫视、陕西卫视、中央一台”等。需要说明的是，在不同的系统或者设备中，其具体指令格式可根据具体情况来确定，本申请对此不做限定。
步骤S508，语音识别控制步骤，可穿戴设备融合语法文件后，可进行语音控制。该步骤主要分为语音唤醒和语音识别两部分。如图9所示：
在用户说出单条指令时，如“电视打开湖南卫视”，可穿戴设备退出待机，指令在可穿戴设备M01上中进行识别，首先进行设备识别码的判断，并生成用于语音唤醒的唤醒指令，发送给待控制设备M02，待控制设备退出待机并判断是否使能异端控制，若没有则继续待机，若有则启动语音识别，待控制设备根据唤醒结果给出反馈进行响应，唤醒成功则给可穿戴设备一个反馈并启动语音识别，唤醒失败则返回待机。
对语音指令进行识别判断，判断指令是否合法，如果指令是“001[电视][语法指令集]”中的指令，则合法，并发送控制指令给待控制设备，如果不是则提示用户重新输入语音指令(如语音提示请重说)。待控制设备根据控制指令识别动作,完成动作后待机。
在上述实施例中，网络断开时，可去掉融合的语法文件。该步骤是更新为步骤S506的反向更新，即将增加语法的过程变成删除语法指令的过程。在该步骤中，语法更新有2种触发方式，一种是网络链接断开，即链接链路断开后(如超过通信支持的距离、信号过弱等)，就会触发语法更新；另一种是主动点击断开，无论是控制设备还是待控制设备，点击取消控制，则将控制标志恢复，同时触发语法更新。在语法更新后，需要提示用户“语音控制已断开”。
实施例4
本发明的实施例还提供了一种存储介质。可选地，在本实施例中，上 述存储介质可以被设置为存储用于执行以下步骤的程序代码：
S1，基于接收到的多个语法文件更新语法库，其中，每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令；
S2，在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令；
S3，通过目标语音指令控制对应的外部设备。
可选地，存储介质还被设置为存储用于执行以下步骤的程序代码：
S4，生成对应于目标语音指令的控制特征码，其中，控制特征码对应于外部设备的控制指令；
S5，发送控制特征码至外部设备。
可选地，在本实施例中，上述存储介质可以包括但不限于：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
可选地，在本实施例中，处理器根据存储介质中已存储的程序代码执行：基于接收到的多个语法文件更新语法库，其中，每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令；在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令；通过目标语音指令控制对应的外部设备。
可选地，在本实施例中，处理器根据存储介质中已存储的程序代码执行：生成对应于目标语音指令的控制特征码，其中，控制特征码对应于外部设备的控制指令；发送控制特征码至外部设备。
可选地，本实施例中的具体示例可以参考上述实施例及可选实施方式中所描述的示例，本实施例在此不再赘述。
显然，本领域的技术人员应该明白，上述的本发明的各模块或各步骤 可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本发明不限制于任何特定的硬件和软件结合。
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。
工业实用性
在本发明实施例中，基于接收到的多个语法文件更新语法库，每个语法文件中携带有用于控制与语法文件对应的外部设备的语音指令；在接收到语音信息时，通过更新后的语法库识别出与语音信息对应的目标语音指令；然后通过目标语音指令控制对应的外部设备，由于在对新外部设备进行控制时，可利用新外部设备的语法文件对语法库进行更新，从而解决了相关技术中，使用可穿戴设备进行语音控制时，其兼容性较差的技术问题，实现了提高可穿戴设备进行语音控制的兼容性的技术效果。

Claims (11)

  1. 一种设备的控制方法，包括：
    基于接收到的多个语法文件更新语法库，其中，每个所述语法文件中携带有用于控制与所述语法文件对应的外部设备的语音指令；
    在接收到语音信息时，通过更新后的所述语法库识别出与所述语音信息对应的目标语音指令；
    通过所述目标语音指令控制对应的外部设备。
  2. 根据权利要求1所述的控制方法，其中，通过更新后的所述语法库识别出与所述语音信息对应的目标语音指令包括：
    使用更新后的所述语法库，从所述语音信息中识别出所述目标语音指令，并基于所述语音信息确定被所述目标语音指令请求控制的外部设备。
  3. 根据权利要求2所述的控制方法，其中，通过所述目标语音指令控制对应的外部设备包括：
    生成对应于所述目标语音指令的控制特征码，其中，所述控制特征码对应于所述外部设备的控制指令；
    发送所述控制特征码至所述外部设备。
  4. 根据权利要求2所述的控制方法，其中，基于所述语音信息确定被所述目标语音指令请求控制的外部设备包括：
    从所述语音信息中识别出用于指示控制对象的指令；
    确定与所述用于指示控制对象的指令对应的所述外部设备。
  5. 根据权利要求1至4中任意一项所述的控制方法，其中，基于接收到的多个语法文件更新语法库包括：
    解析出所述多个语法文件中携带的语音指令；
    将解析出的语音指令保存至所述语法库中。
  6. 根据权利要求1所述的控制方法，其中，在基于接收到的多个语法文件更新语法库之前，采用如下方式接收所述多个语法文件：
    从网关设备获取与多个外部设备一一对应的所述多个语法文件，其中，保存在所述网关设备的所述语法文件为任一外部设备建立与所述网关设备的通信连接时，由所述网关设备从所述任一外部设备获取的文件。
  7. 根据权利要求1至4中任意一项所述的控制方法，其中，在通过所述目标语音指令控制对应的外部设备之后，所述控制方法还包括：
    删除所述语法库中对应于一个或多个接收到的所述语法文件的语音指令。
  8. 根据权利要求7所述的控制方法，其中，在删除所述语法库中对应于一个或多个接收到的所述语法文件的语音指令之前，所述控制方法还包括：
    在断开与所述外部设备的通信连接时，生成提示信息，其中，所述提示信息用于提示是否删除对应于一个或多个所述语法文件的语音指令；
    接收删除指令或保留指令，其中，所述删除指令用于指示执行删除所述语法库中对应于一个或多个接收到的所述语法文件的语音指令的步骤，所述保留指令用于指示保留所述语法库中的对应于多个所述语法文件的语音指令。
  9. 一种设备的控制装置，包括：
    更新单元，设置为基于接收到的多个语法文件更新语法库，其中，每个所述语法文件中携带有用于控制与所述语法文件对应的外部设备的语音指令；
    识别单元，设置为在接收到语音信息时，通过更新后的所述语法库识别出与所述语音信息对应的目标语音指令；
    控制单元，设置为通过所述目标语音指令控制对应的外部设备。
  10. 根据权利要求9所述的控制装置，其中，所述更新单元包括：
    解析模块，设置为解析出所述多个语法文件中携带的语音指令；
    保存模块，设置为将解析出的语音指令保存至所述语法库中。
  11. 一种设备的控制系统，包括：多个外部设备、网关设备和控制设备，其中：
    每个所述外部设备上保存有语法文件，其中，每个所述语法文件中携带有用于控制所述外部设备的语音指令；
    网关设备与所述多个外部设备连接，所述网关设备设置为在控制设备接入时，发送保存在所述网关设备上的所述多个外部设备的多个语法文件至所述控制设备，以通过所述多个语法文件更新所述控制设备的语法库；
    所述控制设备设置为在接收到语音信息时，通过更新后的所述语法库识别出与所述语音信息对应的目标语音指令，并通过所述目标语音指令控制对应的所述外部设备。
PCT/CN2016/099469 2016-06-24 2016-09-20 设备的控制方法、装置及系统 WO2017219519A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610473802.3A CN107545892B (zh) 2016-06-24 2016-06-24 设备的控制方法、装置及系统
CN201610473802.3 2016-06-24

Publications (1)

Publication Number Publication Date
WO2017219519A1 true WO2017219519A1 (zh) 2017-12-28

Family

ID=60783270

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/099469 WO2017219519A1 (zh) 2016-06-24 2016-09-20 设备的控制方法、装置及系统

Country Status (2)

Country Link
CN (1) CN107545892B (zh)
WO (1) WO2017219519A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109945406A (zh) * 2019-03-13 2019-06-28 青岛海尔空调器有限总公司 空调器
US11393463B2 (en) * 2019-04-19 2022-07-19 Soundhound, Inc. System and method for controlling an application using natural language communication

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110164198A (zh) * 2018-01-25 2019-08-23 安徽华晶微电子材料科技有限公司 一种智能可穿戴设备
WO2022061293A1 (en) 2020-09-21 2022-03-24 VIDAA USA, Inc. Display apparatus and signal transmission method for display apparatus
CN112153440B (zh) * 2020-10-10 2023-04-25 Vidaa美国公司 一种显示设备及显示系统
CN113223535B (zh) * 2021-03-22 2024-04-05 惠州市德赛西威汽车电子股份有限公司 一种车载语音技能实时推荐下载系统及方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101989285A (zh) * 2009-08-07 2011-03-23 赛微科技股份有限公司 数据的查询和提供方法、查询系统及其可携式装置与服务器
CN102708858A (zh) * 2012-06-27 2012-10-03 厦门思德电子科技有限公司 基于编组方式的语音库实现语音识别系统及其方法
CN103959374A (zh) * 2011-11-17 2014-07-30 环球电子有限公司 用于控制装置的声控配置的系统和方法
CN104183237A (zh) * 2014-09-04 2014-12-03 百度在线网络技术（北京）有限公司 用于便携式终端的语音处理方法及装置
CN105094807A (zh) * 2015-06-25 2015-11-25 三星电子（中国）研发中心 一种实现语音控制的方法及装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030007609A1 (en) * 2001-07-03 2003-01-09 Yuen Michael S. Method and apparatus for development, deployment, and maintenance of a voice software application for distribution to one or more consumers
US8180735B2 (en) * 2006-12-29 2012-05-15 Prodea Systems, Inc. Managed file backup and restore at remote storage locations through multi-services gateway at user premises
CN102546267B (zh) * 2012-03-26 2015-06-10 杭州华三通信技术有限公司 网络设备的自动配置方法和管理服务器
CN102760433A (zh) * 2012-07-06 2012-10-31 广东美的制冷设备有限公司 联网家电用声控遥控器及其控制方法
CN103955179A (zh) * 2014-04-08 2014-07-30 小米科技有限责任公司 一种远程智能控制方法和装置
CN105611033A (zh) * 2014-11-25 2016-05-25 中兴通讯股份有限公司 一种语音控制的方法及装置
CN104768204A (zh) * 2015-03-25 2015-07-08 广东欧珀移动通信有限公司 一种网络接入管理方法、可穿戴设备及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101989285A (zh) * 2009-08-07 2011-03-23 赛微科技股份有限公司 数据的查询和提供方法、查询系统及其可携式装置与服务器
CN103959374A (zh) * 2011-11-17 2014-07-30 环球电子有限公司 用于控制装置的声控配置的系统和方法
CN102708858A (zh) * 2012-06-27 2012-10-03 厦门思德电子科技有限公司 基于编组方式的语音库实现语音识别系统及其方法
CN104183237A (zh) * 2014-09-04 2014-12-03 百度在线网络技术（北京）有限公司 用于便携式终端的语音处理方法及装置
CN105094807A (zh) * 2015-06-25 2015-11-25 三星电子（中国）研发中心 一种实现语音控制的方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109945406A (zh) * 2019-03-13 2019-06-28 青岛海尔空调器有限总公司 空调器
US11393463B2 (en) * 2019-04-19 2022-07-19 Soundhound, Inc. System and method for controlling an application using natural language communication

Also Published As

Publication number Publication date
CN107545892A (zh) 2018-01-05
CN107545892B (zh) 2021-07-30

Similar Documents

Publication Publication Date Title
WO2017219519A1 (zh) 设备的控制方法、装置及系统
US10484806B2 (en) Managing audio output through an intermediary
TWI743405B (zh) 語音播報方法、智慧型播報裝置、編碼有電腦程式指令的一個或多個非暫時性電腦儲存媒體以及智慧型播報設備
WO2019091171A1 (zh) 语音控制智能家电的方法、装置、系统和电子设备
CN110839271B (zh) 设备连接方法、系统、平台及相应设备
CN107517438B (zh) 请求分享蓝牙设备的方法及电子设备、计算机存储介质
CN110996405A (zh) 耳机连接方法、终端、耳机盒子与计算机可读存储介质
CN104635501A (zh) 智能家居控制方法和系统
WO2016169231A1 (zh) 一种基于蓝牙组建稳态微微网的方法及其系统
WO2017024696A1 (zh) 多播放设备的蓝牙连接控制方法、装置及音乐播放系统
WO2016058254A1 (zh) 家电的控制方法、控制装置及家庭数据终端
CN105898893B (zh) 一种移动终端与物联网设备全双工通信的方法
WO2017167020A1 (zh) 配置信息推送方法及装置
WO2018107593A1 (zh) 一种在不同终端间共享文件的方法及设备
CN105956463B (zh) 一种设备控制方法、装置及终端
CN104639409A (zh) 音箱自动加入音箱自组网的方法和装置
CN110324193A (zh) 一种终端升级管理方法及装置
CN112433836A (zh) 应用程序自动唤醒方法、装置和计算机设备
CN110012527B (zh) 唤醒方法及电子设备
WO2017219653A1 (zh) 设备的控制方法、装置及系统、文件的发送方法和装置
WO2017071567A1 (zh) 无线保真WiFi热点的连接控制方法及装置
WO2017031870A1 (zh) 一种播放设备分组控制方法及用户终端
US8855693B2 (en) Method and apparatus for controlling wireless devices
CN103986697A (zh) 一种音频数据传输的方法和装置
CN112702428A (zh) 一种分布式物联网设备互操作方法及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16906059

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16906059

Country of ref document: EP

Kind code of ref document: A1