WO2021195897A1 - 语音控制方法及智能终端 - Google Patents

语音控制方法及智能终端 Download PDF

Info

Publication number
WO2021195897A1
WO2021195897A1 PCT/CN2020/082218 CN2020082218W WO2021195897A1 WO 2021195897 A1 WO2021195897 A1 WO 2021195897A1 CN 2020082218 W CN2020082218 W CN 2020082218W WO 2021195897 A1 WO2021195897 A1 WO 2021195897A1
Authority
WO
WIPO (PCT)
Prior art keywords
app
type
voice command
apps
voice
Prior art date
Application number
PCT/CN2020/082218
Other languages
English (en)
French (fr)
Inventor
刘勇军
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to PCT/CN2020/082218 priority Critical patent/WO2021195897A1/zh
Priority to CN202080098739.4A priority patent/CN115298650A/zh
Publication of WO2021195897A1 publication Critical patent/WO2021195897A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/445—Program loading or initiating
    • 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

Definitions

  • This application relates to the field of intelligent voice technology, and in particular to a voice control method and an intelligent terminal.
  • the integration of intelligent voice is basically the integration of each application (APP) itself Third-party voice services to support voice interaction.
  • APP application
  • Third-party voice services to support voice interaction.
  • each APP independently integrates a voice interaction technology. This method can only achieve voice interaction within the APP, but cannot achieve cross-APP voice interaction.
  • the live broadcast APP is currently running, and the user can control the live broadcast APP to switch channels through the integrated voice function of the live broadcast APP.
  • users want to watch on-demand programs they cannot directly use voice interaction. They need to manually run the on-demand APP, and then control the on-demand related services through the voice function of the on-demand APP. Therefore, how to achieve cross-APP voice interaction is an urgent problem to be solved.
  • the embodiments of the present application disclose a voice-based control method and a smart terminal, which can implement voice interaction across APPs, simplify user operations, and improve user operation efficiency.
  • the first aspect of the embodiments of the present application discloses a voice control method.
  • the above method is applied to a smart terminal.
  • At least two application software APPs are installed on the smart terminal.
  • Each APP supports one or more types of voice commands.
  • the method includes: receiving a voice instruction; determining that the type of the voice instruction is the first type; determining a target APP that supports the voice instruction of the first type from at least two APPs installed on the smart terminal; using the target APP to execute the voice instruction .
  • the voice commands are classified, and then an APP that can support this type of voice command on the smart terminal is searched, and the voice command is executed by using the APP.
  • the APPs installed on the smart terminal can be integrated to realize voice interaction between cross-APPs. Simplify user operations and improve user operation efficiency.
  • the method before receiving the voice command, further includes: respectively declaring one or more types of voice commands supported by each of the configuration files of at least two APPs installed on the smart terminal.
  • the type of voice command supported by the APP can be declared in the configuration file of the APP, so that after receiving the voice command, the smart terminal can determine that the voice command can be executed by searching for the type of voice command declared in the configuration file of each APP App, and distribute the voice command to the APP that can execute the voice command to realize voice control.
  • the foregoing determining from the at least two APPs installed on the smart terminal the target APP supporting the first type of voice command includes: determining from the at least two APPs installed on the smart terminal M first APPs supporting the above-mentioned first type of voice command; M is a positive integer; the target APP is determined from the above M first APPs.
  • the embodiment of this application provides a way to determine the target APP.
  • the smart terminal can further determine the APP that finally executes the voice command from the multiple APPs to realize the voice command. control.
  • the foregoing determining a target APP that supports the foregoing first type of voice command from at least two APPs installed on the foregoing smart terminal includes: determining whether the foregoing first type of voice command has a corresponding default APP; the above-mentioned default APP is an APP that processes the above-mentioned first type of voice command by default; in the case that the above-mentioned first type of voice command has a corresponding default APP, it is determined that the default APP corresponding to the above-mentioned first type of voice command is the target APP .
  • the default APP can be set by the manufacturer at the factory, and the manufacturer can derive default APPs corresponding to various types of voice commands based on the operation habits of a large number of users.
  • the default APP can also be set by the user according to his own usage habits.
  • the embodiment of this application provides another way to determine the target APP. Firstly, check whether the first type of voice command has a corresponding default APP. If there is a default APP, the default APP will be used first to process the voice command to ensure the command The final distribution result meets the needs of users.
  • the foregoing determining a target APP that supports the foregoing first type of voice command from at least two APPs installed on the foregoing smart terminal includes: determining whether the foregoing first type of voice command has a corresponding default APP; the above-mentioned default APP is an APP that processes the above-mentioned first type of voice command by default; in the case that the above-mentioned first type of voice command does not have a corresponding default APP, it is determined to support the above from at least two APPs installed on the above-mentioned smart terminal M first APPs of the first type of voice command; M is a positive integer; the target APP is determined from the above M first APPs.
  • the embodiment of the present application provides another way to determine the target APP.
  • the target APP is selected from a plurality of first APPs.
  • the embodiments of the present application can comprehensively consider how to distribute voice commands in various situations, improve the accuracy of command distribution, and improve user experience.
  • the target APP is the most frequently used APP among the apps that support the first type of voice command, or the target APP is the last used APP among the apps that support the first type of voice command.
  • the APP whose time is closest to the current moment.
  • the embodiment of the application can select the most frequently used APP, or select the most recently used APP to execute the voice command, and take the user's operating habits into consideration to ensure that the command is distributed Accuracy rate, improve user experience.
  • the target APP is the APP currently running.
  • the currently running APP if the currently running APP supports the first type of voice command, then the currently running APP is used as the target APP.
  • the currently running APP may be prioritized as the target APP, and the voice command can be distributed in combination with the current application scenario, so as to improve the accuracy of voice command distribution and improve user experience.
  • the APP that supports the first type of voice command is obtained according to a command relationship table, and the command relationship table includes at least two APPs installed on the smart terminal and each of the at least two APPs supports The type of voice command.
  • the voice command types supported by each APP installed on the smart terminal may be recorded in the command relationship table.
  • the smart terminal can look up the command relationship table to determine which APPs support this type of voice command, and further distribute the command to achieve voice control, thereby reducing user operations and improving the efficiency of voice control.
  • the APP currently running on the smart terminal is not the target APP; before using the target APP to execute the voice command, the method further includes: running the target APP.
  • the target APP may be run before the voice command is executed by the target APP, which reduces the manual operation steps of the user to run the APP and improves the efficiency of voice control.
  • the foregoing method further includes: stopping the running of the foregoing currently running APP.
  • the currently running APP is switched before the target APP is used to execute the voice command, which reduces the operation of the user to manually switch APPs and improves the efficiency of voice control.
  • the command relationship table further includes the installation paths corresponding to the at least two APPs;
  • the running the target APP includes: looking up the command relationship table, determining the installation path of the target APP, according to the above The installation path of the target APP runs the above-mentioned target APP.
  • the embodiment of the present application can record the installation path of each APP through the command relationship table, and the smart terminal can run the target APP by searching the installation path recorded in the command relationship table to realize intelligent voice control without manual operation by the user and improve operation efficiency.
  • the embodiments of the present application provide a smart device.
  • the smart device is used in a smart terminal.
  • At least two application software APPs are installed on the smart terminal.
  • Each APP supports one or more types of voice commands.
  • the smart device includes: a receiving module for receiving a voice command; a first determining module for determining that the type of the voice command is the first type; a second determining module for selecting from at least two APPs installed on the smart terminal Determine a target APP that supports the above-mentioned first type of voice command; the above-mentioned target APP is used to execute the above-mentioned voice command.
  • the above-mentioned first determination module is an intelligent voice component
  • the above-mentioned second determination module is an application management component
  • the smart device further includes: a declaration module for respectively declaring one or more types of voice commands supported by each in the configuration files of the at least two APPs installed on the smart terminal.
  • the above-mentioned second determining module includes specifically configured to: determine, from at least two APPs installed on the above-mentioned smart terminal, M first APPs that support the above-mentioned first type of voice command; M is positive Integer; the target APP is determined from the above M first APPs.
  • the second APP determining module is specifically configured to: determine whether the first type of voice command has a corresponding default APP; the foregoing default APP is an APP that processes the first type of voice command by default; In the case that the above-mentioned first type of voice command has a corresponding default APP, it is determined that the default APP corresponding to the above-mentioned first type of voice command is the target APP.
  • the second determining module is specifically configured to determine whether the first type of voice command has a corresponding default APP; the default APP is an APP that processes the first type of voice command by default; In the case that the first type of voice command does not have a corresponding default APP, determine the M first APPs that support the first type of voice command from at least two APPs installed on the smart terminal; M is a positive integer; The target APP is determined among the above M first APPs.
  • the target APP is the most frequently used APP among the apps that support the first type of voice command, or the target APP is the last used APP among the apps that support the first type of voice command.
  • the APP whose time is closest to the current moment.
  • the target APP is the APP currently running.
  • the APP that supports the first type of voice command is obtained according to a command relationship table, and the command relationship table includes at least two APPs installed on the smart terminal and each of the at least two APPs supports The type of voice command.
  • the APP currently running on the above-mentioned smart terminal is not the above-mentioned target APP; the above-mentioned smart device further includes: an operating module for running the above-mentioned target APP.
  • the above-mentioned running module is a television virtual machine (TVM).
  • TVM television virtual machine
  • the smart device further includes: a shutdown module, configured to stop running the currently running APP before the running module runs the target APP.
  • the command relationship table further includes the installation paths corresponding to the at least two APPs; the running module is specifically configured to: look up the command relationship table, determine the installation path of the target APP, and determine the installation path of the target APP according to the target The installation path of the APP runs the above-mentioned target APP.
  • the embodiments of the present application provide a smart device.
  • the smart device is used in a smart terminal.
  • At least two application software APPs are installed on the smart terminal.
  • Each APP supports one or more types of voice commands.
  • the device includes: a processor and a transmission interface; the processor is configured to call software instructions stored in the memory to execute: receive voice instructions through the transmission interface; determine that the type of the voice instruction is the first type; The target APP that supports the first type of voice command is determined among the at least two APPs installed on the computer; the target APP is used to execute the voice command.
  • the above-mentioned processor before the above-mentioned voice command is received, the above-mentioned processor further executes: respectively declare in the configuration files of at least two APPs installed on the above-mentioned smart terminal one or more types of voice commands that each supports .
  • the processor executes the target APP that supports the first type of voice command from the at least two APPs installed on the smart terminal, it specifically executes: at least the one installed on the smart terminal M first APPs that support the above-mentioned first type of voice command are determined among the two APPs; M is a positive integer; the target APP is determined from the above-mentioned M first APPs.
  • the processor executes the determination of a target APP supporting the first type of voice instruction from at least two APPs installed on the smart terminal, specifically executes: determining the first type of voice instruction Whether there is a corresponding default APP; the above-mentioned default APP is an APP that handles the above-mentioned first type of voice command by default; in the case that the above-mentioned first type of voice command has a corresponding default APP, it is determined that the above-mentioned first type of voice command corresponds to The default APP is the target APP.
  • the processor executes the determination of a target APP supporting the first type of voice instruction from at least two APPs installed on the smart terminal, specifically executes: determining the first type of voice instruction Whether there is a corresponding default APP; the above-mentioned default APP is an APP that processes the above-mentioned first type of voice command by default; in the case that the above-mentioned first type of voice command does not have a corresponding default APP, at least two installed from the above-mentioned smart terminal M first APPs that support the above-mentioned first type of voice command are determined in the APP; M is a positive integer; the target APP is determined from the above M first APPs.
  • the target APP is the most frequently used APP among the apps that support the first type of voice command, or the target APP is the last used APP among the apps that support the first type of voice command.
  • the APP whose time is closest to the current moment.
  • the target APP is the APP currently running.
  • the APP that supports the first type of voice command is obtained according to a command relationship table, and the command relationship table includes at least two APPs installed on the smart terminal and each of the at least two APPs supports The type of voice command.
  • the APP currently running on the smart terminal is not the target APP; before the processor executes the voice command using the target APP, the processor further executes: run the target APP.
  • the above-mentioned processor before the above-mentioned processor runs the above-mentioned target APP, the above-mentioned processor further executes: stop running the above-mentioned currently running APP.
  • the command relationship table further includes the respective installation paths of the at least two APPs; when the processor runs the target APP, it specifically executes: look up the command relationship table to determine the installation of the target APP Path, run the above-mentioned target APP according to the installation path of the above-mentioned target APP.
  • an embodiment of the present application provides a computer-readable storage medium, and the foregoing computer-readable storage medium stores instructions.
  • the foregoing instructions run on a computer or processor, the foregoing computer or processor executes the application.
  • the voice control method provided by the first aspect or any one of the possible implementation manners of the first aspect of the embodiment.
  • the embodiments of the present application provide a computer program product containing instructions.
  • the computer program product is run on a computer or a processor, the computer or processor is caused to execute the first aspect or the first aspect of the embodiments of the present application.
  • a voice control method provided by any one of the possible implementations of the aspect.
  • the smart device provided in the second aspect, the smart device provided in the third aspect, the computer storage medium provided in the fourth aspect, and the computer program product provided in the fifth aspect provided above are all used to execute the smart device provided in the first aspect.
  • Fig. 1 is a schematic structural diagram of an exemplary voice control system provided by an embodiment of the present application
  • FIG. 2 is a schematic diagram of the hardware structure of an exemplary smart terminal provided by an embodiment of the present application.
  • Fig. 3 is a schematic diagram of the software structure of an exemplary smart terminal provided by an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of an exemplary voice control method provided by an embodiment of the present application.
  • FIG. 5A is a schematic diagram of an exemplary user interface for setting a default APP according to an embodiment of the present application
  • FIG. 5B is a schematic diagram of an exemplary user interface for setting a default APP according to an embodiment of the present application
  • Fig. 6 is a schematic diagram of an exemplary default list provided by an embodiment of the present application.
  • FIG. 7 is a schematic flowchart of another exemplary voice control method provided by an embodiment of the present application.
  • FIG. 8 is a schematic diagram of an exemplary voice control flow of a set-top box provided by an embodiment of the present application.
  • Fig. 9 is a schematic structural diagram of another exemplary smart device provided by an embodiment of the present application.
  • Fig. 10 is a schematic structural diagram of another exemplary smart device provided by an embodiment of the present application.
  • the smart terminal involved in this application can install multiple APPs, and at least some of the APPs support voice interaction.
  • This application classifies voice commands, and after receiving the voice command, determines the app that executes the voice command from the apps that support the voice command type, which can realize cross-APP voice interaction, reduce user operations, and improve operation efficiency.
  • the smart terminal involved in the embodiments of this application may be, for example, a set-top box, a mobile phone, a tablet computer, a desktop, a laptop, a notebook computer, an ultra-mobile personal computer (UMPC), a handheld computer, a netbook, and a personal digital Assistant (personal digital assistant, PDA), wearable electronic devices, virtual reality devices, etc.
  • the smart terminal is a set-top box as an example for description.
  • a set-top box is a device that connects the TV to an external signal source. It can convert the compressed digital signal into video content and display it on the TV.
  • Fig. 1 shows a schematic structural diagram of a voice control system provided by an embodiment of the present application.
  • the voice control system 10 may include: a set-top box 100, an external signal source 200, and a television 300.
  • the set-top box 100 can establish a communication connection with the external signal source 200.
  • the external signal source can be a wired cable, a satellite antenna, a broadband network, or terrestrial broadcasting.
  • the external signal source 200 is a broadband network as an example for description.
  • the set-top box 100 may receive an instruction to watch channel A (or A program) input by the user, and send the instruction to the external signal source 200. After receiving the instruction, the external signal source 200 returns the data of channel A (or program A) to the set-top box 100.
  • the set-top box 100 can convert the data returned by the external signal source 200 to display it on the television 300 for the user to watch.
  • the user can input instructions through the keys on the set-top box 100, or through the remote controller (not shown in FIG. 1) connected to the set-top box 100.
  • the user may input voice instructions through the microphone module on the set-top box 100, or input voice instructions through the microphone module on the remote control connected to the set-top box 100.
  • the instructions input by the user involved in the following embodiments of the present application are all voice instructions.
  • a TVOS or other system can be installed on the set-top box 100 involved in the embodiment of the present application, and the system can support intelligent voice recognition.
  • the user can operate the set-top box to achieve corresponding functions by inputting voice commands.
  • TVOS will be used as an example for description. It can be seen that the embodiments of the present application may also be applicable to Android systems, Linux systems, etc., and the embodiments of the present application do not limit the specific embodiment of the smart terminal and the system installed on the smart terminal.
  • FIG. 2 shows a schematic diagram of the hardware structure of the smart terminal 100.
  • the smart terminal 100 may include a processor 110, a transceiver 120, a display screen 130, buttons 140, an indicator 150, a microphone 160, an internal memory 170, a transmission interface 180, a power management module 190, and so on.
  • the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the smart terminal 100.
  • the smart terminal 100 may include more or fewer components than those shown in the figure, or combine certain components, or split certain components, or arrange different components.
  • the illustrated components can be implemented in hardware, software, or a combination of software and hardware.
  • the processor 110 may include one or more processing units.
  • the processor 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), and an image signal processor. (image signal processor, ISP), controller, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural-network processing unit (NPU), etc.
  • AP application processor
  • modem processor modem processor
  • GPU graphics processing unit
  • image signal processor image signal processor
  • ISP image signal processor
  • controller video codec
  • digital signal processor digital signal processor
  • DSP digital signal processor
  • NPU neural-network processing unit
  • the different processing units may be independent devices or integrated in one or more processors.
  • the transceiver 120 may include an infrared transceiver for receiving instructions sent by a remote controller.
  • the transceiver 120 may be used to receive instructions issued by a user operating a remote control, such as an instruction to switch channels, an instruction to adjust the volume, an instruction to turn on or turn off the smart terminal 100, and so on.
  • the display screen 130 may be used to display information such as the channel where the smart terminal 100 is currently located.
  • the display screen 194 includes a display panel.
  • the display panel can adopt liquid crystal display (LCD), organic light-emitting diode (OLED), active matrix organic light-emitting diode or active-matrix organic light-emitting diode (active-matrix organic light-emitting diode).
  • LCD liquid crystal display
  • OLED organic light-emitting diode
  • active matrix organic light-emitting diode active-matrix organic light-emitting diode
  • active-matrix organic light-emitting diode active-matrix organic light-emitting diode
  • AMOLED flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, quantum dot light-emitting diode (QLED), etc.
  • the button 140 may include a power-on button, a volume button, a channel switching button, and so on.
  • the button 140 may be a mechanical button. It can also be a touch button.
  • the smart terminal 100 may receive key input, and generate signal input of keys related to user settings and function control of the smart terminal 100.
  • the indicator 150 may be an indicator light, which may be used to indicate the working status of the smart terminal 100, and may also be used to indicate notification messages and the like.
  • the microphone 160 is also called “microphone” or “microphone”, and is used to convert sound signals into electrical signals.
  • the user can approach the microphone 160 through the mouth to make a sound, and input a sound signal to the microphone 160.
  • the smart terminal 100 can be provided with at least one microphone 160.
  • the smart terminal 100 may be provided with two microphones 160, which can implement noise reduction functions in addition to collecting sound signals.
  • the smart terminal 100 may also be provided with three, four or more microphones 160 to collect sound signals, reduce noise, identify the source of sound, and realize the function of directional recording.
  • the internal memory 170 may be used to store computer executable program code, the executable program code including instructions.
  • the internal memory 170 may include a storage program area and a storage data area.
  • the storage program area can store an operating system, an application program (such as a sound playback function, an image playback function, etc.) required by at least one function, and the like.
  • the storage data area can store data created during the use of the smart terminal 100 (such as audio data, video data, user history viewing records, etc.) and the like.
  • the internal memory 170 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash storage (UFS), and the like.
  • the processor 110 executes various functional applications and data processing of the smart terminal 100 by running instructions stored in the internal memory 170 and/or instructions stored in a memory provided in the processor.
  • the smart terminal performs data interaction with external devices through the transmission interface 180.
  • the smart terminal receives externally sent data or sends data from the smart terminal through the transmission interface.
  • the transmission interface 180 may be, for example, a high definition multimedia interface (HDMI), a display port (DP), a digital video interface (digital visual interface, DVI), and a universal serial bus (universal serial bus, USB) and other interfaces.
  • the USB interface can be a Micro USB interface, a USB Type C interface, and so on.
  • the external device may be the external signal source 200
  • the transmission interface 180 may be HDMI, DP, DVI, etc.
  • the smart terminal 100 can exchange data with the external signal source 200.
  • the smart terminal 100 can send the user-input “switch to channel A” instruction to the external signal source 200 through the transmission interface 180, and the external signal source 200 can also send the broadcast content of the A channel to the smart terminal through the transmission interface 180.
  • Terminal 100 etc.
  • the external device may also be a USB device, and the transmission interface 180 may be a USB interface.
  • the external device communicates with the processor 110 through the transmission interface 180 to realize the data reading function. For example, play music, video and other files saved in a USB device.
  • the power management module 141 is used to connect an external power source, provide power to various components of the smart terminal 100, and maintain the normal operation of the smart terminal 100.
  • the software system of the smart terminal 100 may adopt a layered architecture.
  • the embodiment of the present application takes a TVOS with a layered architecture as an example to illustrate the software structure of the smart terminal 100 by way of example.
  • FIG. 3 is a block diagram of the software structure of the smart terminal 100 according to an embodiment of the present application.
  • the layered architecture includes several layers, each with clear roles and division of labor. Communication between layers through interfaces.
  • the TVOS is divided into five layers, from top to bottom, the application layer, the application framework layer, the execution environment layer, the component layer, and the Linux kernel layer.
  • the application layer can include a series of application packages.
  • the application package may include applications such as Kiwifruit, Bilibili, System Settings, Kugou, Quick Search for Movies, and Smart Home.
  • the application framework layer provides an application programming interface (application programming interface, API) and a programming framework for applications at the application layer.
  • API application programming interface
  • the application framework layer may include a JAVA application framework and a Web application framework.
  • the execution environment layer provides an execution environment for the application framework of the application framework layer.
  • the Java application execution environment is used to interpret and execute Java bytecode, and it mainly includes a Java virtual machine and a Java core library.
  • This Java application execution environment is called a television virtual machine (TVM), that is, a Java virtual machine environment that can support digital TV applications.
  • TVM television virtual machine
  • the web application execution environment is used to interpret and execute web pages composed of hypertext markup language (HTML) tags, cascading style sheets (CSS) tags, JS scripts, etc., essentially a web browser .
  • the component layer is implemented in C/C++ code, including application management components, digital TV components, media engine components, multi-screen interactive components, application installation components, intelligent voice components, and file management components.
  • GUI User interface
  • system services such as application management, installation package management, and content management.
  • the Linux kernel layer is the layer between hardware and software.
  • the Linux kernel layer contains at least the display driver, USB driver, audio driver, and remote control driver.
  • the remote control driver of the Linux kernel layer captures the corresponding voice command and sends it to the smart voice component of the component layer.
  • the smart voice component analyzes the voice command and determines that the type of the voice command is the first Type, the application management component of the component layer can find that the APP that executes the voice command of this type is kiwi, and then call the TVM of the execution environment layer to run the kiwi APP, so that the kiwi APP executes the above-mentioned voice commands to achieve voice control.
  • the voice control method can be executed by the smart terminal 100 in FIG. 1.
  • At least two APPs are installed on the smart terminal 100, and each APP can support one or more types of voice commands.
  • FIG. 4 is a schematic flowchart of a voice control method provided by an embodiment of the present application. As shown in Figure 4, the method includes but is not limited to the following steps:
  • the smart terminal 100 may receive a voice command sent by a remote controller connected to it through the transceiver 120.
  • the remote control can receive voice instructions input by the user through a microphone on the remote control, and send the received voice instructions to the smart terminal through wireless transmission methods such as infrared and Bluetooth.
  • the smart terminal 100 may also receive a voice instruction input by the user through the microphone 160.
  • S402 Determine that the type of the voice command is the first type.
  • the manufacturer or developer can classify the voice commands that may be involved in the user's use process.
  • the voice instruction can be matched with each instruction library, and the instruction type corresponding to the instruction library with the highest matching degree is the type of the voice instruction.
  • the smart terminal 100 receives a voice instruction, the voice instruction can be input into the model, and the type of the model output is the type of the voice instruction.
  • the type of the voice command received by the smart terminal 100 is referred to as the first type.
  • the following exemplarily shows the types of voice commands that some users may be involved in during use, and what voice commands correspond to each voice command type.
  • voice commands can be divided into the following categories: video-on-demand (com.voice.command.video), live TV programs (com.voice.command.tv), and music playback (com.voice.command). .music), system settings (com.voice.command.setting), and information notification (com.voice.command.notify).
  • the voice instruction of the video-on-demand type may be, for example, "I want to watch XX variety show", "I want to watch XX movie” and so on.
  • the voice instruction of the live TV program can be, for example, "I want to watch XX TV", “I want to watch XX channel” and so on.
  • the voice instructions for music playback can be, for example, "play XX song”, “I want to listen to Jay Chou's song”, “please play a nursery rhyme”, and so on.
  • the voice commands of the system settings can be, for example, “please increase the volume”, “please decrease the display brightness”, “please increase the color saturation”, “please shut down”, etc.
  • the voice command of the information notification type may be, for example, "please turn on the air conditioner in the living room", “please turn off the kettle” and so on.
  • the smart terminal 100 can investigate or collect more types of voice commands and the voice commands that may correspond to these types of voice commands during the use of the user after leaving the factory, and update the operating system of the smart terminal 100 regularly or irregularly (for example, but not Limited to TVOS), so that the smart terminal 100 can support more types of voice commands, cover application scenarios more comprehensively, and improve user experience.
  • the operating system of the smart terminal 100 regularly or irregularly (for example, but not Limited to TVOS), so that the smart terminal 100 can support more types of voice commands, cover application scenarios more comprehensively, and improve user experience.
  • S403 Determine a target APP that supports the first type of voice command from at least two APPs installed on the smart terminal.
  • the developer may respectively declare one or more types of voice commands supported by each in the configuration files of at least two APPs installed on the smart terminal 100. Specifically, it can be filled in its configuration file through the Intent-fliter field.
  • the package manager (package manager) can obtain the voice command types supported by the APP from the configuration file of the APP, and save it in PackageInfo.
  • the package manager can be located in the application management component of the component layer.
  • PackageInfo is mainly used to store some information of the acquired installation package, which can be recorded through fields, including: package name (packageName), version number (versionCode), version name (versionName), installation path, etc.
  • PackageInfo may also be used to store the types of voice commands supported by the APP.
  • the name of the APP is hiVoiceService, and the APP declares in the configuration file that the types of voice commands it supports are as follows:
  • the package manager can obtain the supported voice command types from the configuration file of the APP as TV program live broadcast (com.voice.command.tv) and information notification type (com.voice.command.notify) , And save the supported voice command types in PackageInfo.
  • the package manager When distributing voice commands, the package manager searches for PackageInfo according to the type of the voice command, and can determine the APP that supports this type of voice command, so as to distribute the voice command to the supported APP.
  • the APP that supports the first type of voice command may be referred to as the first APP.
  • the package manager may also construct a command relationship table after acquiring the voice command types supported by the APP when the APP is installed.
  • the relationship table can record the types of voice commands that the APP claims to support and the installation path of the APP.
  • the smart terminal 100 can directly look up the command relationship table to determine which APPs correspond to the first type, that is, which APPs support the first type of voice instructions.
  • the smart terminal 100 may also receive the first type of voice command for the first time during the command distribution process, and the package manager searches for the APP that supports the first type of voice command for the first time.
  • the package manager searches for the APP that supports the first type of voice command for the first time.
  • the command relationship table can be updated to increase the type of voice command supported by the APP and its installation path.
  • the embodiment of the present application does not limit the time for constructing the command relationship table.
  • command relationship table may be as shown in Table 1.
  • the currently running APP (top-level APP) is the APP currently being used by the user, that is, the APP that the smart terminal 100 displays to the user through the television 300.
  • the smart terminal 100 can obtain the PackageInfo of the currently running APP from the task manager. By judging whether the first type is included in the PackageInfo, if it is included, it is determined that the currently running APP is the target APP.
  • Manner 2 Determine M first APPs that support the first type of voice command from at least two APPs installed on the smart terminal 100; then determine the target APP from the M first APPs.
  • the target APP may be the most frequently used APP among the M first APPs, or the target APP may be the APP whose last use time is the closest to the current moment among the M first APPs.
  • the smart terminal 100 may also record the APP used by the user in different time periods of each day, and the target APP may be the APP that the user has used the most times in the past in the M first APPs.
  • the smart terminal 100 may prompt the user that there are M first APPs so that the user can make a selection.
  • the smart terminal 100 may prompt the user through a screen or voice that there are M first APPs, and the user may make a selection through the remote control, or the button 140, or input a voice command.
  • This application does not limit the method of determining the target APP from the M first APPs.
  • Method 3 Determine whether the first type of voice command has a corresponding default APP. If yes, it is determined that the default APP is the target APP. If not, use method two to determine the target APP.
  • the default APP is an APP that processes this type of voice command by default.
  • the default APP can be set uniformly by the manufacturer, or it can be set by the user according to their own needs.
  • FIG. 5A and 5B exemplarily show some schematic diagrams of user interfaces for a user to set a default APP.
  • Fig. 5A exemplarily shows a user interface for setting a default APP corresponding to a video-on-demand category
  • Fig. 5B exemplarily shows a user interface for setting a default APP corresponding to a music playing category.
  • the user interface 50 for setting the default APP corresponding to the video-on-demand category may include a command type list 510 and an APP list 520 that supports this type of voice command.
  • the user can select the instruction type to be set in the instruction type list 510 through the remote controller connected to the smart terminal 100, or the user can select the instruction type to be set in the instruction type list 510 through the button 140 on the smart terminal 100.
  • the selected instruction type to be set can be marked to prompt the user.
  • the list 520 can display APPs that support the instruction type.
  • the user can select the default APP corresponding to this type through the remote control or the button 140 on the smart terminal 100. Similarly, the selected default APP can be marked to prompt the user.
  • the smart terminal 100 may show the default list to the user through the television 300 connected to it.
  • the default list may include various voice command types and their corresponding default APPs.
  • the user can further modify the default APP through the default list. Specifically, it can be modified by the remote control or the button 140, or the default APP can be modified by inputting a voice command.
  • the embodiment of this application does not limit the way of modifying the default APP.
  • the smart terminal 100 can search the PackageInfo of the APP to obtain the installation path of the APP.
  • the default list may include not only the default APP corresponding to different instruction types, but also the installation path of the default APP.
  • the smart terminal 100 can also determine the installation path of the default APP, so as to run the default APP and execute the voice command.
  • the smart terminal 100 can distribute the voice command to the currently running APP.
  • the smart terminal 100 can stop the currently running APP and run the target APP. Specifically, the smart terminal 100 can run the target APP by searching the installation path of the target APP recorded in PackageInfo, or the smart terminal 100 can run the target APP by searching the installation path of the target APP recorded in the command relationship table.
  • the smart terminal 100 can run the aforementioned running APP and the target APP at the same time. Specifically, the smart terminal 100 may divide its current display interface into a first display area and a second display area. The relevant interface of the currently running APP is displayed in the first display area, and the relevant interface of the target APP is displayed in the second display area.
  • the target APP When the target APP starts running, the target APP can be used to execute voice commands.
  • the embodiments of the present application may classify the voice instructions, and after receiving the voice instructions, determine the APP that executes the voice instructions from APPs that support the type of voice instructions. Integrate the APP installed on the smart terminal to realize cross-APP voice interaction. There is no need for the user to manually input the APP switching operation, and then input the voice command. Simplify user operations and improve operational efficiency.
  • the voice control method can include the following steps:
  • S701 is the same as S401, and will not be repeated here.
  • S702 Determine that the type of the voice command is the first type.
  • S702 is the same as S402, and will not be repeated here.
  • S703 Obtain the PackageInfo of the top-level APP from the task manager.
  • the top-level APP supports the first type of voice command.
  • the top-level APP is the APP that is currently running, that is, the APP that the user is currently using, that is, the APP that the smart terminal 100 displays to the user through the television 300.
  • S704 Determine whether there is the first type in the PackageInfo of the top-level APP. If yes, execute S705; if not, execute S706.
  • S705 Send a voice command to the top-level APP.
  • the voice command can be directly sent to the top-level APP, so that the top-level APP executes the voice command.
  • the currently running APP can be prioritized as the target APP, and the voice command can be distributed in combination with the current application scenario, which improves the accuracy of voice command distribution and enhances the user experience.
  • S706 Determine whether there is a default APP corresponding to the first type of voice command. If yes, execute S707; if not, execute S709.
  • S706-S707 can refer to the description of the third method of determining the target APP in S403, which will not be repeated here.
  • S709 Query the command relationship table, and determine M APPs that support the first type of voice command.
  • command relationship table can refer to the related description in Table 1, which will not be repeated here.
  • the target APP is not the currently running APP, which will not be repeated here.
  • the currently running APP can be directly used to execute the voice command. If the currently running APP does not support the first type of voice command, when the target APP or the default APP starts running, the target APP or the default APP can be used to execute the voice command.
  • the currently running APP does not support the first type of voice command, and the first type of voice command does not have a corresponding default APP, and there is no APP that supports the first type of voice command on the smart terminal 100, no processing is performed. Or the user is prompted that the voice command entered is incorrect.
  • the embodiments of the present application may classify the voice instructions, and after receiving the voice instructions, determine the APP that executes the voice instructions from APPs that support the type of voice instructions. Integrate the APP installed on the smart terminal to realize cross-APP voice interaction. There is no need for the user to manually input the APP switching operation, and then input the voice command. Simplify user operations and improve operational efficiency.
  • Fig. 8 shows a schematic diagram of a voice control flow of a set-top box.
  • TVOS can be installed on the set-top box, and based on TVOS, multiple APPs can be installed on the set-top box. Three APPs (APP1, APP2, APP3) are exemplarily shown in FIG. 8.
  • TVOS can collect voice, receive commands, and send commands to the command distributor. Then the command distributor sends the voice command to the corresponding APP.
  • the command distribution mode of the command distributor refer to the several modes of determining the target APP in the foregoing embodiment, which will not be repeated here.
  • FIG. 9 is a schematic structural diagram of a smart device provided by an embodiment of the present application.
  • the smart device can be used in the smart terminal shown in FIG. 2.
  • At least two application software APPs are installed on the smart terminal, and each APP supports one or more types of voice commands.
  • the smart device 90 may include a receiving module 910, a first determining module 920, and a second determining module 930. in:
  • the receiving module 910 is used to receive voice instructions. For details, please refer to the description of S401, which will not be repeated here.
  • the first determining module 920 is configured to determine that the type of the above-mentioned voice command is the first type. For details, please refer to the description of S402, which will not be repeated here.
  • the second determining module 930 is configured to determine a target APP that supports the above-mentioned first type of voice command from at least two APPs installed on the smart terminal. For details, please refer to the description of S403, which will not be repeated here.
  • the target APP can be used to execute the aforementioned voice commands.
  • S404 the description of S404, which will not be repeated here.
  • the first determination module may be an intelligent voice component in the component layer of FIG. 3, and the above-mentioned second determination module may be an application management component in the component layer of FIG. 3.
  • the smart device 90 further includes: a declaration module for respectively declaring one or more types of voice commands supported by each of the configuration files of at least two APPs installed on the smart terminal.
  • the second determining module 930 is specifically configured to:
  • M first APPs supporting the above-mentioned first type of voice command are determined from at least two APPs installed on the smart terminal; M is a positive integer; and the target APP is determined from the above M first APPs.
  • the second determining module 93 is specifically configured to: determine whether the first type of voice command has a corresponding default APP; the above-mentioned default APP is an APP that processes the above-mentioned first type of voice command by default; In the case that the first type of voice command has a corresponding default APP, it is determined that the default APP corresponding to the first type of voice command is the target APP.
  • the second determining module 930 is specifically configured to: determine whether the first type of voice command has a corresponding default APP; the foregoing default APP is an APP that processes the first type of voice command by default; In the case that the first type of voice command does not have a corresponding default APP, determine the M first APPs that support the first type of voice command from at least two APPs installed on the smart terminal; M is a positive integer; The target APP is determined among the above M first APPs.
  • the target APP is the most frequently used APP among the apps that support the first type of voice command, or the target APP is the last used APP among the apps that support the first type of voice command.
  • the APP whose time is closest to the current moment.
  • the above-mentioned target APP is the above-mentioned currently running APP.
  • the APP that supports the first type of voice command is obtained according to a command relationship table, and the command relationship table includes at least two APPs installed on the smart terminal and each of the at least two APPs supported Voice command type.
  • the APP currently running on the smart terminal is not the aforementioned target APP.
  • the smart device 90 also includes: an operating module, which is used to run the above-mentioned target APP.
  • the running module may be the TVM in the execution environment layer of FIG. 3.
  • the smart device 90 further includes: a stop module, which is used to stop running the above-mentioned currently running APP before the running module runs the above-mentioned target APP.
  • the above-mentioned command relationship table further includes respective installation paths of the above-mentioned at least two APPs.
  • the running module is specifically used to look up the above-mentioned command relationship table, determine the installation path of the above-mentioned target APP, and run the above-mentioned target APP according to the installation path of the above-mentioned target APP.
  • the smart device provided in the embodiment of the present application can classify voice commands. After receiving the voice instruction, the APP that executes the voice instruction is determined from the APPs that support this type of voice instruction. Integrate the APP installed on the smart terminal to realize cross-APP voice interaction. There is no need for the user to manually input the APP switching operation, and then input the voice command. Simplify user operations and improve operational efficiency.
  • FIG. 10 is another smart device provided by an embodiment of the present application.
  • the smart device can be used in the smart terminal shown in FIG. 2.
  • At least two application software APPs are installed on the smart terminal, and each APP supports one One or more types of voice commands.
  • the smart device 400 includes a processor 410 and a transmission interface 420.
  • the smart device 400 may further include a memory 430.
  • the processor 410, the memory 430, and the transmission interface 420 are connected to each other through a bus 440.
  • the memory 430 includes but is not limited to random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or A portable read-only memory (compact disc read-only memory, CD-ROM), the memory 430 is used for related instructions and data.
  • the transmission interface 420 is used to receive and send data.
  • the processor 410 may be one or more central processing unit (CPU), microcontroller (microcontroller unit, MCU), graphics processing unit (GPU), image signal processor (image signal processor, ISP), neural network processor (neural-network processing unit, NPU), digital signal processor (digital signal processor, DSP), application processor (application processor, AP), etc.
  • CPU central processing unit
  • MCU microcontroller unit
  • GPU graphics processing unit
  • image signal processor image signal processor
  • ISP image signal processor
  • NPU neural network processor
  • DSP digital signal processor
  • application processor application processor
  • the processor 410 in the smart device 400 is configured to call the software instructions stored in the memory 430 to execute:
  • the processor 410 before the above-mentioned voice command is received, the processor 410 further executes: respectively declare in the configuration files of at least two APPs installed on the above-mentioned smart terminal one or more types of voice commands that each supports .
  • the processor 410 executes the target APP that supports the first type of voice command from the at least two APPs installed on the smart terminal, it specifically executes: M first APPs that support the above-mentioned first type of voice command are determined among the two APPs; M is a positive integer; the target APP is determined from the above-mentioned M first APPs.
  • the processor 410 executes determining a target APP supporting the first type of voice command from at least two APPs installed on the smart terminal, specifically executes: determining the first type of voice command Whether there is a corresponding default APP; the above-mentioned default APP is an APP that handles the above-mentioned first type of voice command by default; in the case that the above-mentioned first type of voice command has a corresponding default APP, it is determined that the above-mentioned first type of voice command corresponds to The default APP is the target APP.
  • the processor 410 executes determining a target APP supporting the first type of voice command from at least two APPs installed on the smart terminal, specifically executes: determining the first type of voice command Whether there is a corresponding default APP; the above-mentioned default APP is an APP that processes the above-mentioned first type of voice command by default; in the case that the above-mentioned first type of voice command does not have a corresponding default APP, at least two installed from the above-mentioned smart terminal M first APPs that support the above-mentioned first type of voice command are determined in the APP; M is a positive integer; the target APP is determined from the above M first APPs.
  • the target APP is the most frequently used APP among the apps that support the first type of voice command, or the target APP is the last used APP among the apps that support the first type of voice command.
  • the APP whose time is closest to the current moment.
  • the target APP is the APP currently running.
  • the APP that supports the first type of voice command is obtained according to a command relationship table, and the command relationship table includes at least two APPs installed on the smart terminal and each of the at least two APPs supports The type of voice command.
  • the APP currently running on the smart terminal is not the target APP; before the processor 410 executes the voice command using the target APP, the processor 410 also executes: run the target APP.
  • the processor 410 before the processor 410 runs the aforementioned target APP, the processor 410 further executes: stop running the aforementioned currently running APP.
  • the command relationship table further includes the respective installation paths of the at least two APPs; when the processor 410 runs the target APP, it specifically executes: look up the command relationship table to determine the installation of the target APP Path, run the above-mentioned target APP according to the installation path of the above-mentioned target APP.
  • the smart device provided in the embodiment of the present application can classify voice commands. After receiving the voice instruction, the APP that executes the voice instruction is determined from the APPs that support this type of voice instruction. Integrate the APP installed on the smart terminal to realize cross-APP voice interaction. There is no need for the user to manually input the APP switching operation, and then input the voice command. Simplify user operations and improve operational efficiency.
  • the embodiments of the present application also provide a computer-readable storage medium that stores instructions in the computer-readable storage medium, and when it runs on a computer or a processor, the computer or the processor executes any one of the above methods. Or multiple steps. If each component module of the above-mentioned smart device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the computer readable storage medium.
  • the above embodiments it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software it can be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium.
  • the computer instructions can be sent from a website, computer, server, or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (such as infrared, wireless, microwave, etc.) Another website site, computer, server or data center for transmission.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center integrated with one or more available media.
  • the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital video disc (DVD)), or a semiconductor medium (for example, a solid state disk, SSD)) etc.
  • the embodiment of the present application also provides a computer program product.
  • the computer program product runs on an intelligent terminal, the method flow shown in FIG. 4 or FIG. 5 is realized.
  • the program can be stored in a computer readable storage medium. During execution, it may include the procedures of the above-mentioned method embodiments.
  • the storage medium may be a magnetic disk, an optical disc, a read only memory (ROM) or a random access memory (RAM), etc.
  • the modules in the device of the embodiment of the present application may be combined, divided, and deleted according to actual needs.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Stored Programmes (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本申请实施例提供一种语音控制方法及智能装置。该方法应用于智能终端，该智能终端上安装至少两个应用软件APP，每个APP支持一种或多种类型的语音指令，该方法包括：接收语音指令；确定该语音指令的类型为第一类型；从该智能终端上安装的至少两个APP中确定支持该第一类型的语音指令的目标APP；采用该目标APP执行该语音指令。采用本申请实施例可以实现跨APP的语音交互，简化用户操作，提升用户的操作效率。

Description

语音控制方法及智能终端 技术领域
本申请涉及智能语音技术领域，尤其涉及一种语音控制方法及智能终端。
背景技术
在目前的机顶盒(set top box，STB)中，无论是电视机操作系统(television operator system，TVOS)，还是其他系统，对于智能语音的集成，基本上是各个应用软件(application，APP)自身集成第三方的语音服务来支持语音交互。也就是说，每个APP都独立集成一个语音交互技术，此方式只能达成在APP内部完成语音交互，而无法实现跨APP的语音交互。
例如，当前正在运行的是直播APP，通过直播APP集成的语音功能，用户可以控制直播APP切换频道。但是，如果用户想看点播节目时，则不能直接采用语音交互，需要人为的将点播APP运行起来，再通过点播APP的语音功能来控制点播的相关业务。因此，如何实现跨APP的语音交互，是一个亟待解决的问题。
发明内容
本申请实施例公开了一种基于语音控制方法及智能终端，能够实现跨APP的语音交互，简化用户操作，提升用户的操作效率。
本申请实施例第一方面公开了一种语音控制方法，上述方法应用于智能终端，上述智能终端上安装至少两个应用软件APP，每个APP支持一种或多种类型的语音指令，上述方法包括：接收语音指令；确定上述语音指令的类型为第一类型；从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP；采用上述目标APP执行上述语音指令。
本申请实施例中，通过对语音指令进行分类，然后查找智能终端上可以支持该类型的语音指令的APP，采用该APP执行语音指令。实施本申请实施例，可以将智能终端上安装的APP整合在一起，实现跨APP之间的语音交互。简化用户操作，提升用户的操作效率。
在一种可能的实现方式中，上述接收语音指令之前，上述方法还包括：分别在上述智能终端上安装的至少两个APP的配置文件中声明各自支持的一种或多种语音指令的类型。
本申请实施例可以通过在APP的配置文件中声明该APP支持的语音指令类型，以便智能终端在接收到语音指令后，通过查找各个APP的配置文件声明的语音指令类型来确定可以执行该语音指令的APP，并将该语音指令派发给可以执行该语音指令的APP，实现语音控制。
在一种可能的实现方式中，上述从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP，包括：从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的M个第一APP；M为正整数；从上述M个第一APP中确定目标APP。
本申请实施例提供了一种确定目标APP的方式，当支持第一类型的语音指令的APP 有多个时，智能终端可以进一步从这多个APP中确定最终执行该语音指令的APP，实现语音控制。
在一种可能的实现方式中，上述从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP，包括：确定上述第一类型的语音指令是否有对应的默认APP；上述默认APP为默认处理上述第一类型的语音指令的APP；在上述第一类型的语音指令有对应的默认APP的情况下，确定上述第一类型的语音指令对应的默认APP为目标APP。
可能地，默认APP可以是出厂时由厂商设置的，厂商可以根据统计大量用户的操作习惯后得出各种类型的语音指令对应的默认APP。
可能地，默认APP也可以是用户根据自己的使用习惯设置的。
本申请实施例提供了另一种确定目标APP的方式，首先查看第一类型的语音指令是否有对应的默认APP，若有默认的APP，则优先采用默认的APP来处理该语音指令，保证指令最终的派发结果符合用户需求。
在一种可能的实现方式中，上述从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP，包括：确定上述第一类型的语音指令是否有对应的默认APP；上述默认APP为默认处理上述第一类型的语音指令的APP；在上述第一类型的语音指令没有对应的默认APP的情况下，从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的M个第一APP；M为正整数；从上述M个第一APP中确定目标APP。
本申请实施例提供了另一种确定目标APP的方式，在第一类型的语音指令没有对应的默认APP的情况下，再从多个第一APP中选择目标APP。本申请实施例可以全面考虑各种情况下语音指令该如何派发，提高指令派发的准确率，提升用户体验。
在一种可能的实现方式中，上述目标APP为支持上述第一类型的语音指令的APP中使用频率最高的APP，或者上述目标APP为上述支持上述第一类型的语音指令的APP中上一次使用时间离当前时刻最近的APP。
当有多个支持第一类型的语音指令的APP时，本申请实施例可以选择使用频率最高的APP，或者选择用户最近使用的APP来执行语音指令，将用户的操作习惯考虑进来，保证指令派发的准确率，提升用户体验。
在一种可能的实现方式中，在上述智能终端当前正在运行的APP支持上述第一类型的语音指令的情况下，上述目标APP为上述当前正在运行的APP。
本申请实施例中，若当前正在运行的APP支持第一类型的语音指令，则将该当前正在运行的APP作为目标APP。实施本申请实施例，可以优先考虑当前运行的APP为目标APP，结合当前的应用场景来派发语音指令，提高语音指令派发的准确率，提升用户体验。
在一种可能的实现方式中，支持上述第一类型的语音指令的APP是根据命令关系表获得的，上述命令关系表包括上述智能终端上安装的至少两个APP以及上述至少两个APP各自支持的语音指令类型。
本申请实施例可以将智能终端上安装的各个APP各自支持的语音指令类型记录在命令关系表中。当接收到某类型的语音指令时，智能终端可以查找命令关系表确定支持该类型 的语音指令的APP有哪些，进一步进行指令派发，实现语音控制，从而减少用户操作，提升语音控制的效率。
在一种可能的实现方式中，上述智能终端当前正在运行的APP不是上述目标APP；上述采用上述目标APP执行上述语音指令之前，上述方法还包括：运行上述目标APP。
本申请实施例可以在采用目标APP执行语音指令之前，先运行该目标APP，减少用户手动操作来运行APP的步骤，提高语音控制的效率。
在一种可能的实现方式中，上述运行上述目标APP之前，上述方法还包括：停止运行上述当前正在运行的APP。
本申请实施例中，在采用目标APP执行语音指令之前先切换当前正在运行的APP，减少用户手动切换APP的操作，提高语音控制的效率。
在一种可能的实现方式中，上述命令关系表还包括上述至少两个APP各自对应的安装路径；上述运行上述目标APP，包括：查找上述命令关系表，确定上述目标APP的安装路径，根据上述目标APP的安装路径运行上述目标APP。
本申请实施例可以通过命令关系表记载各个APP的安装路径，智能终端可以通过查找命令关系表中记载的安装路径来运行目标APP，以实现智能语音控制，无需用户手动操作，提升操作效率。
第二方面，本申请实施例提供了一种智能装置，上述智能装置用于智能终端，上述智能终端上安装至少两个应用软件APP，每个APP支持一种或多种类型的语音指令，上述智能装置包括：接收模块，用于接收语音指令；第一确定模块，用于确定上述语音指令的类型为第一类型；第二确定模块，用于从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP；上述目标APP，用于执行上述语音指令。
在一种可能的实现方式中，上述第一确定模块为智能语音组件，上述第二确定模块为应用管理组件。
在一种可能的实现方式中，智能装置还包括：声明模块，用于分别在上述智能终端上安装的至少两个APP的配置文件中声明各自支持的一种或多种语音指令的类型。
在一种可能的实现方式中，上述第二确定模块包括具体用于：从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的M个第一APP；M为正整数；从上述M个第一APP中确定目标APP。
在一种可能的实现方式中，上述第二APP确定模块具体用于：确定上述第一类型的语音指令是否有对应的默认APP；上述默认APP为默认处理上述第一类型的语音指令的APP；在上述第一类型的语音指令有对应的默认APP的情况下，确定上述第一类型的语音指令对应的默认APP为目标APP。
在一种可能的实现方式中，上述第二确定模块具体用于：确定上述第一类型的语音指令是否有对应的默认APP；上述默认APP为默认处理上述第一类型的语音指令的APP；在上述第一类型的语音指令没有对应的默认APP的情况下，从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的M个第一APP；M为正整数；从上述M个第一APP中确定目标APP。
在一种可能的实现方式中，上述目标APP为支持上述第一类型的语音指令的APP中使 用频率最高的APP，或者上述目标APP为上述支持上述第一类型的语音指令的APP中上一次使用时间离当前时刻最近的APP。
在一种可能的实现方式中，在上述智能终端当前正在运行的APP支持上述第一类型的语音指令的情况下，上述目标APP为上述当前正在运行的APP。
在一种可能的实现方式中，支持上述第一类型的语音指令的APP是根据命令关系表获得的，上述命令关系表包括上述智能终端上安装的至少两个APP以及上述至少两个APP各自支持的语音指令类型。
在一种可能的实现方式中，上述智能终端当前正在运行的APP不是上述目标APP；上述智能装置还包括：运行模块，用于运行上述目标APP。
在一种可能的实现方式中，上述运行模块为电视虚拟机(television virtual machine，TVM)。
在一种可能的实现方式中，智能装置还包括：停止运行模块，用于在上述运行模块运行上述目标APP之前，停止运行上述当前正在运行的APP。
在一种可能的实现方式中，上述命令关系表还包括上述至少两个APP各自对应的安装路径；上述运行模块具体用于：查找上述命令关系表，确定上述目标APP的安装路径，根据上述目标APP的安装路径运行上述目标APP。
第三方面，本申请实施例提供了一种智能装置，上述智能装置用于智能终端，上述智能终端上安装至少两个应用软件APP，每个APP支持一种或多种类型的语音指令，智能装置包括：处理器和传输接口；上述处理器被配置为调用存储在存储器中的软件指令以执行：通过所述传输接口接收语音指令；确定上述语音指令的类型为第一类型；从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP；采用上述目标APP执行上述语音指令。
在一种可能的实现方式中，上述接收语音指令之前，上述处理器还执行：分别在上述智能终端上安装的至少两个APP的配置文件中声明各自支持的一种或多种语音指令的类型。
在一种可能的实现方式中，上述处理器执行从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP时，具体执行：从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的M个第一APP；M为正整数；从上述M个第一APP中确定目标APP。
在一种可能的实现方式中，上述处理器执行从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP时，具体执行：确定上述第一类型的语音指令是否有对应的默认APP；上述默认APP为默认处理上述第一类型的语音指令的APP；在上述第一类型的语音指令有对应的默认APP的情况下，确定上述第一类型的语音指令对应的默认APP为目标APP。
在一种可能的实现方式中，上述处理器执行从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP时，具体执行：确定上述第一类型的语音指令是否有对应的默认APP；上述默认APP为默认处理上述第一类型的语音指令的APP；在上述第一类型的语音指令没有对应的默认APP的情况下，从上述智能终端上安装的至少两 个APP中确定支持上述第一类型的语音指令的M个第一APP；M为正整数；从上述M个第一APP中确定目标APP。
在一种可能的实现方式中，上述目标APP为支持上述第一类型的语音指令的APP中使用频率最高的APP，或者上述目标APP为上述支持上述第一类型的语音指令的APP中上一次使用时间离当前时刻最近的APP。
在一种可能的实现方式中，在上述智能终端当前正在运行的APP支持上述第一类型的语音指令的情况下，上述目标APP为上述当前正在运行的APP。
在一种可能的实现方式中，支持上述第一类型的语音指令的APP是根据命令关系表获得的，上述命令关系表包括上述智能终端上安装的至少两个APP以及上述至少两个APP各自支持的语音指令类型。
在一种可能的实现方式中，上述智能终端当前正在运行的APP不是上述目标APP；上述处理器执行采用上述目标APP执行上述语音指令之前，上述处理器还执行：运行上述目标APP。
在一种可能的实现方式中，上述处理器运行上述目标APP之前，上述处理器还执行：停止运行上述当前正在运行的APP。
在一种可能的实现方式中，上述命令关系表还包括上述至少两个APP各自对应的安装路径；上述处理器运行上述目标APP时，具体执行：查找上述命令关系表，确定上述目标APP的安装路径，根据上述目标APP的安装路径运行上述目标APP。
第四方面，本申请实施例提供了一种计算机可读存储介质，上述计算机可读存储介质中存储有指令，当上述指令在计算机或处理器上运行时，使得上述计算机或处理器执行本申请实施例第一方面或第一方面的任意一种可能的实现方式提供的语音控制方法。
第五方面，本申请实施例提供了一种包含指令的计算机程序产品，当上述计算机程序产品在计算机或处理器上运行时，使得上述计算机或处理器执行本申请实施例第一方面或第一方面的任意一种可能的实现方式提供的语音控制方法。
可以理解地，上述提供的第二方面提供的智能装置、第三方面提供的智能装置、第四方面提供的计算机存储介质，以及第五方面提供的计算机程序产品均用于执行第一方面所提供的语音控制方法。因此，其所能达到的有益效果可参考第一方面所提供的语音控制方法中的有益效果，此处不再赘述。
附图说明
图1是本申请实施例提供的一种示例性的语音控制系统的结构示意图；
图2是本申请实施例提供的一种示例性的智能终端的硬件结构示意图；
图3是本申请实施例提供的一种示例性的智能终端的软件结构示意图；
图4是本申请实施例提供的一种示例性的语音控制方法的流程示意图；
图5A是本申请实施例提供的一种示例性的设置默认APP的用户界面示意图；
图5B是本申请实施例提供的一种示例性的设置默认APP的用户界面示意图；
图6是本申请实施例提供的一种示例性的默认列表的示意图；
图7是本申请实施例提供的另外一种示例性的语音控制方法的流程示意图；
图8是本申请实施例提供的一种示例性的机顶盒的语音控制流程示意图；
图9是本申请实施例提供的另外一种示例性的智能装置的结构示意图；
图10是本申请实施例提供的另外一种示例性的智能装置的结构示意图。
具体实施方式
下面结合本申请实施例中的附图对本申请实施例进行描述。
本申请中涉及的智能终端可以安装多个APP，其中至少部分APP支持语音交互。本申请通过对语音指令进行分类，在收到语音指令后，从支持该语音指令类型的APP中确定执行该语音指令的APP，可以实现跨APP的语音交互，减少用户操作，提升操作效率。
本申请实施例中涉及的智能终端例如可以是机顶盒、手机、平板电脑、桌面型、膝上型、笔记本电脑、超级移动个人计算机(ultra-mobile personal computer，UMPC)、手持计算机、上网本、个人数字助理(personal digital assistant，PDA)、可穿戴电子设备、虚拟现实设备等。本申请以下实施例中均以智能终端是机顶盒为例进行说明。机顶盒是一个连接电视机与外部信号源的设备。它可以将压缩的数字信号转换成视频内容，并在电视上显示出来。
图1示出了本申请实施例提供的一种语音控制系统的结构示意图。如图1所示，语音控制系统10可以包括：机顶盒100、外部信号源200及电视机300。
其中，机顶盒100可以与外部信号源200建立通信连接。其中，外部信号源可以是有线电缆、卫星天线、宽带网络或者地面广播等。图1中以外部信号源200为宽带网络为例进行说明。机顶盒100可以接收用户输入的收看A频道(或A节目)的指令，并将该指令发送给外部信号源200。外部信号源200在接收到该指令后，将A频道(或A节目)的数据返回给机顶盒100。机顶盒100可以对外部信号源200返回的数据进行转换，使其在电视机300中显示出来，以供用户观看。
可知，用户可以通过机顶盒100上的按键输入指令，也可以通过与机顶盒100连接的遥控器(图1中未示出)输入指令。或者，用户可以通过机顶盒100上的麦克风模块输入语音指令，也可以通过与机顶盒100连接的遥控器上的麦克风模块输入语音指令。本申请以下实施例中涉及的用户输入的指令均为语音指令。
本申请实施例中涉及的机顶盒100上可安装TVOS或其他系统，该系统可支持智能语音识别。用户可以通过输入语音指令操作机顶盒实现相应的功能。本申请以下实施例中将以TVOS为例进行说明。可知，本申请实施例还可以适用于Android系统、Linux系统等，本申请实施例对于智能终端的具体体现形式以及智能终端上安装的系统均不作限定。
接下来，介绍本申请以下实施例中提供的示例性智能终端。
图2示出了智能终端100的硬件结构示意图。
智能终端100可以包括处理器110，收发器120、显示屏130、按键140、指示器150、麦克风160、内部存储器170、传输接口180及电源管理模块190等。
可以理解的是，本申请实施例示意的结构并不构成对智能终端100的具体限定。在本申请另一些实施例中，智能终端100可以包括比图示更多或更少的部件，或者组合某些部 件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
处理器110可以包括一个或多个处理单元，例如：处理器110可以包括应用处理器(application processor，AP)，调制解调处理器，图形处理器(graphics processing unit，GPU)，图像信号处理器(image signal processor，ISP)，控制器，视频编解码器，数字信号处理器(digital signal processor，DSP)，基带处理器，和/或神经网络处理器(neural-network processing unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。
收发器120可以包括红外收发器，用于接收遥控器发送的指令。本申请实施例中，收发器120可以用于接收用户操作遥控器发出的指令，如切换频道的指令、调节音量的指令、开启或关闭智能终端100的指令等。
显示屏130可以用于显示智能终端100当前所处的频道等信息。显示屏194包括显示面板。显示面板可以采用液晶显示屏(liquid crystal display，LCD)，有机发光二极管(organic light-emitting diode，OLED)，有源矩阵有机发光二极体或主动矩阵有机发光二极体(active-matrix organic light emitting diode的，AMOLED)，柔性发光二极管(flex light-emitting diode，FLED)，Miniled，MicroLed，Micro-oLed，量子点发光二极管(quantum dot light emitting diodes，QLED)等。
按键140可以包括开机键，音量键，频道切换键等。按键140可以是机械按键。也可以是触摸式按键。智能终端100可以接收按键输入，产生与智能终端100的用户设置以及功能控制有关的按键的信号输入。
指示器150可以是指示灯，可以用于指示智能终端100的工作状态，也可以用于指示通知消息等。
麦克风160也称“话筒”，“传声器”，用于将声音信号转换为电信号。当用户输入语音指令时，用户可以通过人嘴靠近麦克风160发声，将声音信号输入到麦克风160。智能终端100可以设置至少一个麦克风160。在另一些实施例中，智能终端100可以设置两个麦克风160，除了采集声音信号，还可以实现降噪功能。在另一些实施例中，智能终端100还可以设置三个，四个或更多麦克风160，实现采集声音信号，降噪，还可以识别声音来源，实现定向录音功能等。本申请实施例中，用户不仅可以通过智能终端上的麦克风160输入语音指令，用户还可以通过与智能终端100连接的遥控器上的麦克风输入语音指令。
内部存储器170可以用于存储计算机可执行程序代码，所述可执行程序代码包括指令。内部存储器170可以包括存储程序区和存储数据区。其中，存储程序区可存储操作系统，至少一个功能所需的应用程序(比如声音播放功能，图像播放功能等)等。存储数据区可存储智能终端100使用过程中所创建的数据(比如音频数据，视频数据，用户历史观看记录等)等。此外，内部存储器170可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件，闪存器件，通用闪存存储器(universal flash storage，UFS)等。处理器110通过运行存储在内部存储器170的指令，和/或存储在设置于处理器中的存储器的指令，执行智能终端100的各种功能应用以及数据处理。
智能终端通过传输接口180与外部设备进行数据交互，例如智能终端通过该传输接口接收外部发送的数据或者将智能终端的数据发送出去。该传输接口180例如可以是高清晰 度多媒体接口(high definition multimedia interface，HDMI)、显示接口(display port，DP)、数字视频接口(digital visual interface，DVI)及通用串行总线(universal serial bus，USB)等接口。其中，USB接口可以是Micro USB接口，USB Type C接口等。在一些可能的实施例中，外部设备可以是外部信号源200，传输接口180可以是HDMI、DP、DVI等。通过该传输接口180，智能终端100可以与外部信号源200进行数据交互。例如，智能终端100可以通过该传输接口180将用户输入的“切换至A频道”的指令发送给外部信号源200，外部信号源200也可以通过该传输接口180将A频道的播放内容发送给智能终端100，等等。在另外一些可能的实施例中，外部设备还可以是USB设备，传输接口180可以是USB接口。外部设备通过传输接口180与处理器110通信，实现数据读取功能。例如播放USB设备中保存的音乐，视频等文件等。
电源管理模块141用于连接外部电源，为智能终端100的各个部件提供电源，维持智能终端100的正常运行。
智能终端100的软件系统可以采用分层架构，本申请实施例以分层架构的TVOS为例，示例性说明智能终端100的软件结构。
图3是本申请实施例的智能终端100的软件结构框图。
分层架构包括若干个层，每一层都有清晰的角色和分工。层与层之间通过接口通信。在一些实施例中，将TVOS分为五层，从上至下分别为应用层，应用框架层，执行环境层，组件层，以及Linux内核层。
应用层可以包括一系列应用程序包。
如图3所示，应用程序包可以包括奇异果、哔哩哔哩、系统设置、酷狗、影视快搜和智能家居等应用程序。
应用框架层为应用层的应用程序提供应用编程接口(application programming interface，API)和编程框架。如图3所示，应用框架层可以包括JAVA应用框架及Web应用框架。
执行环境层为应用框架层的应用框架提供执行环境。Java应用执行环境用以解释执行Java字节码，主要包括Java虚拟机和Java核心库。此Java应用执行环境称之为电视虚拟机(television virtual machine，TVM)，即能支撑数字电视应用的Java虚拟机环境。Web应用执行环境用以解释执行由超文本标记语言(hyper text markup language，HTML)标签、层叠样式表(cascading style sheets，CSS)标签、JS脚本等组成的Web页面，本质上是一个Web浏览器。
组件层以C/C++代码实现，包括应用管理组件、数字电视组件、媒体引擎组件、多屏互动组件、应用安装组件、智能语音组件以及文件管理组件等。提供的系统服务主要有数字电子(digital television，DTV)、视频点播系统(video on demand，VOD)等与数字电视相关的服务，有窗口管理、事件管理以及人机交互等基本图像用户界面(graphical user interface，GUI)服务，有应用管理、安装包管理以及内容管理等系统服务。
Linux内核层是硬件和软件之间的层。Linux内核层至少包含显示驱动，USB驱动，音频驱动以及遥控器驱动等。
下面结合语音控制场景，示例性说明智能终端100软件以及硬件的工作流程。
当遥控器接收到语音指令，Linux内核层的遥控器驱动捕捉到相应的语音指令，发送给组件层的智能语音组件，智能语音组件对该语音指令进行分析，确定该语音指令的类型为第一类型，组件层的应用管理组件可以查找执行该类型的语音指令的APP为奇异果，则调用执行环境层的TVM运行奇异果APP，使奇异果APP执行上述语音指令，实现语音控制。
接下来结合图1示出的语音控制系统架构，图2示出的智能终端的硬件结构，以及图3示出的智能终端的软件结构示意图，详细介绍本申请实施例提供的语音控制方法。该语音控制方法可以由图1中的智能终端100执行。智能终端100上安装至少两个APP，每个APP可支持一种或多种类型的语音指令。
请参见图4，图4是本申请实施例提供的一种语音控制方法的流程示意图。如图4所示，该方法包括但不限于如下步骤：
S401：接收语音指令。
可能地，智能终端100可以通过收发器120接收与其连接的遥控器发送的语音指令。具体地，遥控器可以通过遥控器上的麦克风接收用户输入的语音指令，并通过红外、蓝牙等无线传输方式将其接收的语音指令发送给智能终端。
可能地，智能终端100还可以通过麦克风160接收用户输入的语音指令。
S402：确定语音指令的类型为第一类型。
具体地，在智能终端100出厂时，厂商或开发人员可以对用户使用过程中可能涉及的语音指令进行分类。
可能地，厂商或开发人员可以为不同类型的语音指令建立相应的指令库。当智能终端100接收到语音指令时，可以将该语音指令与各个指令库进行匹配，匹配度最高的指令库对应的指令类型为该语音指令的类型。
可能地，厂商或开发人员可以采用大量的已知类型的语音指令训练一个语音指令识别模型。当智能终端100接收到语音指令时，可以将该语音指令输入到该模型中，模型输出的类型即为该语音指令的类型。本申请实施例中，将智能终端100接收的语音指令的类型称为第一类型。
以下示例性示出一些用户在使用过程中可能涉及的语音指令类型，以及各个语音指令类型对应的语音指令有哪些。
示例性地，可以将语音指令分为以下几类：视频点播类(com.voice.command.video)、电视节目直播类(com.voice.command.tv)、音乐播放类(com.voice.command.music)、系统设置类(com.voice.command.setting)以及信息通知类(com.voice.command.notify)。其中，视频点播类的语音指令例如可以是“我要看XX综艺”、“我要看XX电影”等。电视节目直播类的语音指令例如可以是“我要看XX卫视”、“我要看XX频道”等。音乐播放类的语音指令例如可以是“播放XX歌曲”、“我想听周杰伦的歌”、“请播放儿歌”等。系统设置类的语音指令例如可以是“请增大音量”、“请减小显示亮度”、“请增大色彩饱和度”、“请关机”等。信息通知类的语音指令例如可以是“请打开客厅空调”、“请将热水壶断电”等。
可能地，智能终端100可以在出厂后用户使用过程中调研或搜集更多的语音指令的类型以及该类型可能对应的语音指令，并定期或不定期的更新智能终端100的操作系统(例 如但不限于TVOS)，以使智能终端100可以支持更多类型的语音指令，更加全面的覆盖应用场景，提升用户体验。
S403：从智能终端上安装的至少两个APP中确定支持第一类型的语音指令的目标APP。
首先，介绍如何确定某APP是否支持某类型的语音指令。
具体地，开发人员可以分别在智能终端100上安装的至少两个APP的配置文件中声明各自支持的一种或多种语音指令的类型。具体可以通过Intent-fliter字段填入其配置文件中。在安装APP时，包管理器(package manage)可以从该APP的配置文件中获取该APP支持的语音指令类型，并保存在PackageInfo中。其中，包管理器可以位于组件层的应用管理组件中。通常，PackageInfo主要用于存储获取到的安装包的一些信息，这些信息可通过字段记录，包括：包名(packageName)、版本号(versionCode)、版本名(versionName)、安装路径等。本申请实施例中，PackageInfo还可以用于存储该APP支持的语音指令的类型。
示例性地，APP的名称为hiVoiceService，该APP在配置文件中声明其支持的语音指令的类型如下：
<service android:name＝".hiVoiceService"
<intent-filter>
<action android:name＝"com.voice.command"/>
<category android:name＝"com.voice.command.tv"/>
<category android:name＝"com.voice.command.notify"/>
</intent-filter>
</service>
安装该APP时，包管理器可以从该APP的配置文件中获取其支持的语音指令类型为电视节目直播类(com.voice.command.tv)以及信息通知类(com.voice.command.notify)，并将其支持的语音指令类型保存在PackageInfo中。
其次，介绍如何确定支持某类型的语音指令的APP有哪些。
在分发语音指令时，包管理器按照语音指令所属的类型去查找PackageInfo，可以确定支持该类型的语音指令的APP，从而将该语音指令分发给支持的APP。本申请实施例中可以将支持第一类型的语音指令的APP称为第一APP。
为了提高指令分发的速度、避免包管理器重复查找PackageInfo，本申请实施例还可以在安装APP时由包管理器获取到该APP支持的语音指令类型后，构建一个命令关系表。该关系表中可以记录该APP声明其支持的语音指令的类型以及该APP的安装路径。后续在分发指令时，智能终端100可以直接查找命令关系表，确定第一类型对应的APP有哪些，即支持第一类型的语音指令的APP有哪些。
不限于在安装APP时构建命令关系表，智能终端100还可以在指令分发的过程中，智能终端100首次接收到第一类型的语音指令，包管理器首次查找支持第一类型语音指令的APP并确定执行该指令的目标APP时，记录目标APP支持的语音指令的类型，并从目标APP的PackageInfo中确定该APP的安装路径。当智能终端100再接收到其他类型的语音指令，并确定最终执行该类型的语音指令的APP时，可更新命令关系表，增加该APP支持的语音指令的类型以及其安装路径。本申请实施例对构建命令关系表的时间不做限定。
示例性的，命令关系表可如表1所示。
表1命令关系表
APP名称 支持的语音指令的类型 安装路径
奇异果 视频点播类；系统设置类 "E:/dev/qiyiguo/qiyiguo Server/"
酷狗 音乐播放类；系统设置类 "D:/dev/kugou/kugou Server/"
电视猫 电视节目直播类；信息通知类 "E:/dev/dianshimao/dianshimao Server/"
影视快搜 电视节目直播类；信息通知类 "E:/dev/yingshikuaisou/yingshikuaisou Server/"
芒果TV 视频点播类；音乐播放类 "E:/dev/mangguoTV/mangguoTV Server/"
最后，介绍确定目标APP的方式，主要有以下几种：
方式一：若智能终端100当前正在运行的APP支持第一类型的语音指令，则该当前正在运行的APP为目标APP。
具体地，当前正在运行的APP(顶层APP)即为用户当前正在使用的APP，即智能终端100通过电视机300展示给用户的APP。智能终端100可以从任务管理器中获取当前正在运行的APP的PackageInfo。通过判断PackageInfo中是否包含第一类型，若是包含，则确定当前正在运行的APP为目标APP。
方式二：从智能终端100上安装的至少两个APP中确定支持第一类型的语音指令的M个第一APP；再从M个第一APP中确定目标APP。
具体地，当M＝1时，即支持第一类型的语音指令的第一APP的数量为1时，确定该第一APP即为目标APP。当M大于或等于2时，需进一步从这M个第一APP中确定目标APP。
此时，目标APP可以为M个第一APP中使用频率最高的APP，或者目标APP可以为所述M个第一APP中上一次使用时间离当前时刻最近的APP。
可能地，智能终端100还可以记录每天不同时段中用户使用的APP，目标APP可以是这M个第一APP中用户以往在该时段使用次数最多的APP。
可能地，智能终端100可以提示用户存在M个第一APP，以便用户做出选择。具体地，智能终端100可以通过画面或者语音提示用户存在M个第一APP，用户可以通过遥控器、或者按键140、或者输入语音指令做出选择。本申请对于从M个第一APP中确定目标APP的方式不做限定。
方式三：确定第一类型的语音指令是否有对应的默认APP。若有，则确定该默认APP为目标APP。若没有，采用方式二确定目标APP。
具体地，默认APP即为默认处理该类型的语音指令的APP。默认APP可以由厂商统一设置，也可以由用户根据自身需求来设置。
图5A和图5B示例性示出了用户设置默认APP的一些用户界面示意图。图5A示例性示出了设置视频点播类对应的默认APP的用户界面，图5B示例性示出了设置音乐播放类对应的默认APP的用户界面。
如图5A所示，用于设置视频点播类对应的默认APP的用户界面50可以包括：指令类 型列表510，及支持该类型的语音指令的APP列表520。
用户可以通过与智能终端100连接的遥控器在指令类型列表510中选择待设置的指令类型，或者用户可以通过智能终端100上的按键140在指令类型列表510中选择待设置的指令类型。被选中的待设置的指令类型可以被标记以提示用户。
当用户选中待设置的指令类型后，列表520中可以显示支持该指令类型的APP。用户可以通过遥控器或智能终端100上的按键140选择该类型对应的默认APP。同样地，被选中的默认APP可以被标记以提示用户。
设置音乐播放类对应的默认APP的过程与设置视频点播类对应的默认APP的过程一致，此处不赘述。但是对比图5A与图5B可以看出，不同的指令类型对应的列表520不同，这是因为支持不同类型的语音指令的APP可能不同。
此外，用户还可以查看默认列表。智能终端100可以通过与其相连的电视机300向用户展示默认列表。如图6所示，默认列表可以包括各种语音指令类型与其对应的默认的APP。用户可以通过该默认列表进一步修改默认APP。具体可以通过遥控器或者按键140修改，或者可以通过输入语音指令来修改默认APP。本申请实施例对修改默认APP的方式不作限定。
通过查找默认列表确认第一类型对应的默认APP之后，智能终端100可以查找该APP的PackageInfo获取该APP的安装路径。或者，默认列表中不仅可以包括不同指令类型对应的默认APP，还可以包括该默认APP的安装路径。通过查找默认列表确认第一类型对应的默认APP之后，智能终端100还可以确定该默认APP的安装路径，以便运行该默认APP，执行语音指令。
S404：采用目标APP执行语音指令。
可能地，目标APP为当前正在运行的APP，则智能终端100可以将该语音指令分发给当前正在运行的APP。
可能地，目标APP不是当前正在运行的APP，则智能终端100可以停止当前正在运行的APP，并运行目标APP。具体地，智能终端100可以通过查找PackageInfo中记录的目标APP的安装路径来运行目标APP，或者智能终端100可以通过查找命令关系表中记录的目标APP的安装路径来运行目标APP。
可能地，目标APP不是当前正在运行的APP，则智能终端100可以同时运行前述正在运行的APP以及目标APP。具体地，智能终端100可以将其当前的显示界面分为第一显示区域及第二显示区域。在第一显示区域中显示当前正在运行的APP的相关界面，在第二显示区域中显示目标APP的相关界面。
当目标APP开始运行后，即可采用目标APP来执行语音指令。
本申请实施例可以通过对语音指令进行分类，在接收到语音指令后，从支持该类型的语音指令的APP中确定执行该语音指令的APP。将智能终端上安装的APP整合在一起，实现跨APP的语音交互。无需用户手动输入APP的切换操作，再输入语音指令。简化用户操作，提升操作效率。
接下来结合图7介绍本申请实施例提供的一种详细的语音控制方法。如图7所示，语 音控制方法可以包括以下几个步骤：
S701：接收语音指令。
具体地，S701与S401一致，此处不赘述。
S702：确定语音指令的类型为第一类型。
具体地，S702与S402一致，此处不赘述。
S703：从任务管理器获得顶层APP的PackageInfo。
具体地，判断出用户输入的语音指令的类型为第一类型后，可优先判断顶层APP是否支持第一类型的语音指令。
其中，顶层APP即为当前正在运行的APP，即为用户当前正在使用的APP，即未智能终端100通过电视机300展示给用户的APP。
S704：判断顶层APP的PackageInfo中是否有第一类型。若是，执行S705；若否，执行S706。
具体地，判断PackageInfo中是否有第一类型的具体过程可以参考前述关于如何确定某APP是否支持某类型的语音指令的相关描述，此处不再赘述。
S705：发送语音指令给顶层APP。
在顶层APP支持第一类型的语音指令的语音指令后，可以直接将该语音指令发送给顶层APP，以使顶层APP执行该语音指令。这样可以优先考虑当前运行的APP为目标APP，结合当前的应用场景来派发语音指令，提高语音指令派发的准确率，提升用户体验。
S706：判断是否有第一类型的语音指令对应的默认APP。若是，执行S707；若否，执行S709。
S707：发送语音指令给默认APP。
具体地，S706-S707具体可参考S403中关于确定目标APP的方式三的描述，此处不再赘述。
S708：运行默认APP。
具体地，运行默认APP的方式具体可以参考S404中关于目标APP不是当前正在运行的APP的部分的描述，此处不再赘述。
S709：查询命令关系表，确定支持第一类型的语音指令的M个APP。
具体地，命令关系表可参考表1的相关描述，此处不再赘述。
S710：从M个APP中选择目标APP。
具体地，从M个APP中选择目标APP的方式可参考S403中关于确定目标APP的方式二的描述，此处不再赘述。
S711：运行目标APP。
具体地，运行目标APP的方式具体可以参考S404中关于目标APP不是当前正在运行的APP的部分的描述，此处不再赘述。
S712：执行语音指令。
具体地，若当前正在运行的APP支持第一类型的语音指令，则可直接采用当前正在运行的APP执行该语音指令。若当前正在运行的APP不支持第一类型的语音指令，则当目标APP或默认APP开始运行后，即可采用目标APP或默认APP来执行语音指令。
若当前正在运行的APP不支持第一类型的语音指令，且第一类型的语音指令没有对应的默认APP，且智能终端100上没有支持第一类型的语音指令的APP，则不做任何处理，或者提示用户输入的语音指令有误。
本申请实施例可以通过对语音指令进行分类，在接收到语音指令后，从支持该类型的语音指令的APP中确定执行该语音指令的APP。将智能终端上安装的APP整合在一起，实现跨APP的语音交互。无需用户手动输入APP的切换操作，再输入语音指令。简化用户操作，提升操作效率。
图8示出了一种机顶盒的语音控制流程示意图。如图8所示，机顶盒上可以安装TVOS，且基于TVOS，机顶盒上可以安装多个APP。图8中示例性示出了三个APP(APP1、APP2、APP3)。TVOS可以进行语音采集，接收命令，并将命令发送给命令分发器。再由命令分发器将该语音指令发送给对应的APP。命令分发器的命令分发方式可参考前述实施例中关于确定目标APP的几种方式，此处不再赘述。
上述详细阐述了本申请实施例的方法，下面提供本申请实施例的装置。
请参见图9，图9是本申请实施例提供的一种智能装置的结构示意图，该智能装置可用于图2示出的智能终端。智能终端上安装至少两个应用软件APP，每个APP支持一种或多种类型的语音指令，智能装置90可以包括接收模块910、第一确定模块920及第二确定模块930。其中：
接收模块910，用于接收语音指令。具体可参考S401的描述，此处不再赘述。
第一确定模块920，用于确定上述语音指令的类型为第一类型。具体可参考S402的描述，此处不再赘述。
第二确定模块930，用于从智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP。具体可参考S403的描述，此处不再赘述。
目标APP可以用于执行上述语音指令。具体可参考S404的描述，此处不再赘述。
在一种可能的实现方式中，第一确定模块可以是图3组件层中的智能语音组件，上述第二确定模块可以是图3组件层中的的应用管理组件。
在一种可能的实现方式中，智能装置90还包括：声明模块，用于分别在智能终端上安装的至少两个APP的配置文件中声明各自支持的一种或多种语音指令的类型。
在一种可能的实现方式中，第二确定模块930具体用于：
从智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的M个第一APP；M为正整数；从上述M个第一APP中确定目标APP。
在一种可能的实现方式中，第二确定模块93具体用于：确定第一类型的语音指令是否有对应的默认APP；上述默认APP为默认处理上述第一类型的语音指令的APP；在上述第一类型的语音指令有对应的默认APP的情况下，确定上述第一类型的语音指令对应的默认APP为目标APP。
在一种可能的实现方式中，第二确定模块930具体用于：确定上述第一类型的语音指令是否有对应的默认APP；上述默认APP为默认处理上述第一类型的语音指令的APP；在 上述第一类型的语音指令没有对应的默认APP的情况下，从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的M个第一APP；M为正整数；从上述M个第一APP中确定目标APP。
在一种可能的实现方式中，上述目标APP为支持上述第一类型的语音指令的APP中使用频率最高的APP，或者上述目标APP为上述支持上述第一类型的语音指令的APP中上一次使用时间离当前时刻最近的APP。
在一种可能的实现方式中，在智能终端当前正在运行的APP支持上述第一类型的语音指令的情况下，上述目标APP为上述当前正在运行的APP。
在一种可能的实现方式中，支持上述第一类型的语音指令的APP是根据命令关系表获得的，上述命令关系表包括智能终端上安装的至少两个APP以及上述至少两个APP各自支持的语音指令类型。
在一种可能的实现方式中，智能终端当前正在运行的APP不是上述目标APP。
智能装置90还包括：运行模块，用于运行上述目标APP。
在一种可能的实现方式中，运行模块可以是图3执行环境层中的TVM。
在一种可能的实现方式中，智能装置90还包括：停止运行模块，用于在运行模块运行上述目标APP之前，停止运行上述当前正在运行的APP。
在一种可能的实现方式中，上述命令关系表还包括上述至少两个APP各自对应的安装路径。
运行模块具体用于：查找上述命令关系表，确定上述目标APP的安装路径，根据上述目标APP的安装路径运行上述目标APP。
本申请实施例提供的智能装置可以通过对语音指令进行分类。在接收到语音指令后，从支持该类型的语音指令的APP中确定执行该语音指令的APP。将智能终端上安装的APP整合在一起，实现跨APP的语音交互。无需用户手动输入APP的切换操作，再输入语音指令。简化用户操作，提升操作效率。
请参见图10，图10是本申请实施例提供的另一种智能装置，该智能装置可用于图2示出的智能终端，该智能终端上安装至少两个应用软件APP，每个APP支持一种或多种类型的语音指令。智能装置400包括处理器410及传输接口420。可选地，智能装置400还可以包括存储器430。处理器410、存储器430和传输接口420通过总线440相互连接。
存储器430包括但不限于是随机存储记忆体(random access memory，RAM)、只读存储器(read-only memory，ROM)、可擦除可编程只读存储器(erasable programmable read only memory，EPROM)、或便携式只读存储器(compact disc read-only memory，CD-ROM)，该存储器430用于相关指令及数据。传输接口420用于接收和发送数据。
处理器410可以是一个或多个中央处理器(central processing unit，CPU)、微控制器(microcontroller unit，MCU)、图形处理器(graphics processing unit，GPU)、图像信号处理器(image signal processor，ISP)、神经网络处理器(neural-network processing unit，NPU)、数字信号处理器(digital signal processor，DSP)以及应用处理器(application processor，AP)等。在处理器410是一个CPU的情况下，该CPU可以是单核CPU，也可以是多核CPU。
智能装置400中的处理器410被配置为调用存储在存储器430中存储的软件指令以执行：
通过传输接口420接收语音指令；确定上述语音指令的类型为第一类型；从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP；采用上述目标APP执行上述语音指令。
在一种可能的实现方式中，上述接收语音指令之前，处理器410还执行：分别在上述智能终端上安装的至少两个APP的配置文件中声明各自支持的一种或多种语音指令的类型。
在一种可能的实现方式中，处理器410执行从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP时，具体执行：从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的M个第一APP；M为正整数；从上述M个第一APP中确定目标APP。
在一种可能的实现方式中，处理器410执行从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP时，具体执行：确定上述第一类型的语音指令是否有对应的默认APP；上述默认APP为默认处理上述第一类型的语音指令的APP；在上述第一类型的语音指令有对应的默认APP的情况下，确定上述第一类型的语音指令对应的默认APP为目标APP。
在一种可能的实现方式中，处理器410执行从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的目标APP时，具体执行：确定上述第一类型的语音指令是否有对应的默认APP；上述默认APP为默认处理上述第一类型的语音指令的APP；在上述第一类型的语音指令没有对应的默认APP的情况下，从上述智能终端上安装的至少两个APP中确定支持上述第一类型的语音指令的M个第一APP；M为正整数；从上述M个第一APP中确定目标APP。
在一种可能的实现方式中，上述目标APP为支持上述第一类型的语音指令的APP中使用频率最高的APP，或者上述目标APP为上述支持上述第一类型的语音指令的APP中上一次使用时间离当前时刻最近的APP。
在一种可能的实现方式中，在上述智能终端当前正在运行的APP支持上述第一类型的语音指令的情况下，上述目标APP为上述当前正在运行的APP。
在一种可能的实现方式中，支持上述第一类型的语音指令的APP是根据命令关系表获得的，上述命令关系表包括上述智能终端上安装的至少两个APP以及上述至少两个APP各自支持的语音指令类型。
在一种可能的实现方式中，上述智能终端当前正在运行的APP不是上述目标APP；处理器410执行采用上述目标APP执行上述语音指令之前，处理器410还执行：运行上述目标APP。
在一种可能的实现方式中，处理器410运行上述目标APP之前，处理器410还执行：停止运行上述当前正在运行的APP。
在一种可能的实现方式中，上述命令关系表还包括上述至少两个APP各自对应的安装路径；处理器410运行上述目标APP时，具体执行：查找上述命令关系表，确定上述目标 APP的安装路径，根据上述目标APP的安装路径运行上述目标APP。
本申请实施例提供的智能装置可以通过对语音指令进行分类。在接收到语音指令后，从支持该类型的语音指令的APP中确定执行该语音指令的APP。将智能终端上安装的APP整合在一起，实现跨APP的语音交互。无需用户手动输入APP的切换操作，再输入语音指令。简化用户操作，提升操作效率。
本申请实施例还提供了一种计算机可读存储介质，该计算机可读存储介质中存储有指令，当其在计算机或处理器上运行时，使得计算机或处理器执行上述任一个方法中的一个或多个步骤。上述智能装置的各组成模块如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在所述计算机可读取存储介质中。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者通过所述计算机可读存储介质进行传输。所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，数字多功能光盘(digital video disc，DVD))、或者半导体介质(例如，固态硬盘(solid state disk，SSD))等。
本申请实施例还提供一种计算机程序产品，当所述计算机程序产品在智能终端上运行时，图4或图5所示的方法流程得以实现。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储器(read only memory，ROM)或随机存储器(random access memory，RAM)等。
本申请实施例方法中的步骤可以根据实际需要进行顺序调整、合并和删减。
本申请实施例装置中的模块可以根据实际需要进行合并、划分和删减。
以上所述，以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。

Claims (25)

  1. 一种语音控制方法，其特征在于，所述方法应用于智能终端，所述智能终端上安装至少两个应用软件APP，每个APP支持一种或多种类型的语音指令，所述方法包括：
    接收语音指令；
    确定所述语音指令的类型为第一类型；
    从所述智能终端上安装的至少两个APP中确定支持所述第一类型的语音指令的目标APP；
    采用所述目标APP执行所述语音指令。
  2. 如权利要求1所述的方法，其特征在于，所述接收语音指令之前，所述方法还包括：分别在所述智能终端上安装的至少两个APP的配置文件中声明各自支持的一种或多种语音指令的类型。
  3. 如权利要求1或2所述的方法，其特征在于，所述从所述智能终端上安装的至少两个APP中确定支持所述第一类型的语音指令的目标APP，包括：
    从所述智能终端上安装的至少两个APP中确定支持所述第一类型的语音指令的M个第一APP；M为正整数；
    从所述M个第一APP中确定目标APP。
  4. 如权利要求1或2所述的方法，其特征在于，所述从所述智能终端上安装的至少两个APP中确定支持所述第一类型的语音指令的目标APP，包括：
    确定所述第一类型的语音指令是否有对应的默认APP；所述默认APP为默认处理所述第一类型的语音指令的APP；
    在所述第一类型的语音指令有对应的默认APP的情况下，确定所述第一类型的语音指令对应的默认APP为目标APP。
  5. 如权利要求1或2所述的方法，其特征在于，所述从所述智能终端上安装的至少两个APP中确定支持所述第一类型的语音指令的目标APP，包括：
    确定所述第一类型的语音指令是否有对应的默认APP；所述默认APP为默认处理所述第一类型的语音指令的APP；
    在所述第一类型的语音指令没有对应的默认APP的情况下，从所述智能终端上安装的至少两个APP中确定支持所述第一类型的语音指令的M个第一APP；M为正整数；
    从所述M个第一APP中确定目标APP。
  6. 如权利要求1-3、5任一项所述的方法，其特征在于，所述目标APP为支持所述第一类型的语音指令的APP中使用频率最高的APP，或者所述目标APP为所述支持所述第一类型的语音指令的APP中上一次使用时间离当前时刻最近的APP。
  7. 如权利要求1或2所述的方法，其特征在于，在所述智能终端当前正在运行的APP支持所述第一类型的语音指令的情况下，所述目标APP为所述当前正在运行的APP。
  8. 如权利要求1-7任一项所述的方法，其特征在于，支持所述第一类型的语音指令的APP是根据命令关系表获得的，所述命令关系表包括所述智能终端上安装的至少两个APP以及所述至少两个APP各自支持的语音指令类型。
  9. 如权利要求1至8任一项所述的方法，其特征在于，所述智能终端当前正在运行的APP不是所述目标APP；
    所述采用所述目标APP执行所述语音指令之前，所述方法还包括：运行所述目标APP。
  10. 如权利要求9所述的方法，其特征在于，所述运行所述目标APP之前，所述方法还包括：停止运行所述当前正在运行的APP。
  11. 如权利要求9或10所述的方法，其特征在于，所述命令关系表还包括所述至少两个APP各自对应的安装路径；
    所述运行所述目标APP，包括：查找所述命令关系表，确定所述目标APP的安装路径，根据所述目标APP的安装路径运行所述目标APP。
  12. 一种智能装置，其特征在于，所述智能装置用于智能终端，所述智能终端上安装至少两个应用软件APP，每个APP支持一种或多种类型的语音指令，所述智能装置包括：
    接收模块，用于接收语音指令；
    第一确定模块，用于确定所述语音指令的类型为第一类型；
    第二确定模块，用于从所述智能终端上安装的至少两个APP中确定支持所述第一类型的语音指令的目标APP；
    所述目标APP，用于执行所述语音指令。
  13. 如权利要求12所述的智能装置，其特征在于，还包括：声明模块，用于分别在所述智能终端上安装的至少两个APP的配置文件中声明各自支持的一种或多种语音指令的类型。
  14. 如权利要求12或13所述的智能装置，其特征在于，所述第二确定模块具体用于：
    从所述智能终端上安装的至少两个APP中确定支持所述第一类型的语音指令的M个第一APP；M为正整数；
    从所述M个第一APP中确定目标APP。
  15. 如权利要求12或13所述的智能装置，其特征在于，所述第二确定模块具体用于：
    确定所述第一类型的语音指令是否有对应的默认APP；所述默认APP为默认处理所述第一类型的语音指令的APP；
    在所述第一类型的语音指令有对应的默认APP的情况下，确定所述第一类型的语音指令对应的默认APP为目标APP。
  16. 如权利要求12或13所述的智能装置，其特征在于，所述第二确定模块具体用于：
    确定所述第一类型的语音指令是否有对应的默认APP；所述默认APP为默认处理所述第一类型的语音指令的APP；
    在所述第一类型的语音指令没有对应的默认APP的情况下，从所述智能终端上安装的至少两个APP中确定支持所述第一类型的语音指令的M个第一APP；M为正整数；
    从所述M个第一APP中确定目标APP。
  17. 如权利要求12-14、16任一项所述的智能装置，其特征在于，所述目标APP为支持所述第一类型的语音指令的APP中使用频率最高的APP，或者所述目标APP为所述支持所述第一类型的语音指令的APP中上一次使用时间离当前时刻最近的APP。
  18. 如权利要求12或13所述的智能装置，其特征在于，在所述智能终端当前正在运 行的APP支持所述第一类型的语音指令的情况下，所述目标APP为所述当前正在运行的APP。
  19. 如权利要求12-18任一项所述的智能装置，其特征在于，支持所述第一类型的语音指令的APP是根据命令关系表获得的，所述命令关系表包括所述智能终端上安装的至少两个APP以及所述至少两个APP各自支持的语音指令类型。
  20. 如权利要求12-19任一项所述的智能装置，其特征在于，所述智能终端当前正在运行的APP不是所述目标APP；
    所述智能装置还包括：运行模块，用于运行所述目标APP。
  21. 如权利要求20所述的智能装置，其特征在于，还包括：停止运行模块，用于在所述运行模块运行所述目标APP之前，停止运行所述当前正在运行的APP。
  22. 如权利要求20或21所述的智能装置，其特征在于，所述命令关系表还包括所述至少两个APP各自对应的安装路径；
    所述运行模块具体用于：查找所述命令关系表，确定所述目标APP的安装路径，根据所述目标APP的安装路径运行所述目标APP。
  23. 一种智能装置，其特征在于，包括：处理器和传输接口；
    所述处理器被配置为调用存储在存储器中的软件指令以执行如权利要求1-11任一项所述的语音控制方法。
  24. 一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当所述指令在计算机或处理器上运行时，使得所述计算机或处理器执行如权利要求1-11任一项所述的语音控制方法。
  25. 一种包含指令的计算机程序产品，当所述计算机程序产品在计算机或处理器上运行时，使得所述计算机或处理器执行如权利要求1-11任一项所述的语音控制方法。
PCT/CN2020/082218 2020-03-30 2020-03-30 语音控制方法及智能终端 WO2021195897A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2020/082218 WO2021195897A1 (zh) 2020-03-30 2020-03-30 语音控制方法及智能终端
CN202080098739.4A CN115298650A (zh) 2020-03-30 2020-03-30 语音控制方法及智能终端

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/082218 WO2021195897A1 (zh) 2020-03-30 2020-03-30 语音控制方法及智能终端

Publications (1)

Publication Number Publication Date
WO2021195897A1 true WO2021195897A1 (zh) 2021-10-07

Family

ID=77927005

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/082218 WO2021195897A1 (zh) 2020-03-30 2020-03-30 语音控制方法及智能终端

Country Status (2)

Country Link
CN (1) CN115298650A (zh)
WO (1) WO2021195897A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114116042A (zh) * 2021-10-29 2022-03-01 航天信息股份有限公司 一种面向Linux服务系统的命令处理方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7203645B2 (en) * 2001-04-27 2007-04-10 Intel Corporation Speech recognition system loading different recognition engines for different applications
CN103442138A (zh) * 2013-08-26 2013-12-11 华为终端有限公司 语音控制方法、装置及终端
CN104916287A (zh) * 2015-06-10 2015-09-16 青岛海信移动通信技术股份有限公司 一种语音控制的方法、装置和移动设备
CN110018858A (zh) * 2019-04-02 2019-07-16 北京蓦然认知科技有限公司 一种基于语音控制的应用管理方法、装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7203645B2 (en) * 2001-04-27 2007-04-10 Intel Corporation Speech recognition system loading different recognition engines for different applications
CN103442138A (zh) * 2013-08-26 2013-12-11 华为终端有限公司 语音控制方法、装置及终端
CN104916287A (zh) * 2015-06-10 2015-09-16 青岛海信移动通信技术股份有限公司 一种语音控制的方法、装置和移动设备
CN110018858A (zh) * 2019-04-02 2019-07-16 北京蓦然认知科技有限公司 一种基于语音控制的应用管理方法、装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114116042A (zh) * 2021-10-29 2022-03-01 航天信息股份有限公司 一种面向Linux服务系统的命令处理方法及系统
CN114116042B (zh) * 2021-10-29 2024-04-26 航天信息股份有限公司 一种面向Linux服务系统的命令处理方法及系统

Also Published As

Publication number Publication date
CN115298650A (zh) 2022-11-04

Similar Documents

Publication Publication Date Title
CN113110941B (zh) 使用应用容器管理代码和依赖性数据的传递
US11437030B2 (en) Electronic apparatus and method for voice recognition
US7949727B2 (en) Table based distributed control for a network of consumer electronics
WO2017193612A1 (zh) 使用移动终端对电器设备进行操控的设备、系统和方法
US20080196038A1 (en) Utilizing a first managed process to host at least a second managed process
US20070168194A1 (en) Scheduling audio modalities for data management and data rendering
AU2012261531A1 (en) Electronic device, server and control method thereof
KR20160014629A (ko) 업데이트에 대한 기지의 의존관계를 관리하는 기법
US20180352299A1 (en) Image display apparatus and operation method therefor
CN112002321B (zh) 显示设备、服务器及语音交互方法
WO2021195897A1 (zh) 语音控制方法及智能终端
CN114510170B (zh) 一种组件展示方法及显示设备
KR101865343B1 (ko) 웹 서비스 애플리케이션 개발을 위한 서버측 프레임워크 장치, 이에 의해 개발된 웹 서비스 애플리케이션의 실행 방법 및 이를 위한 컴퓨터 프로그램
US20190034380A1 (en) Multi-device synchronization for immersive experiences
KR20150078033A (ko) 응용 프로그램을 실행하는 전자 장치 및 방법
US20120174003A1 (en) Application managment system and method using the same
CN114564214A (zh) 显示设备、应用安装方法及存储介质
CN114860131A (zh) 车载多媒体应用的控制方法、装置、设备、介质和产品
CN112911359B (zh) 一种资源显示方法、显示设备及遥控器
KR100948472B1 (ko) 데이터 언어에서 변수들의 자동 업데이팅
CN114217715A (zh) 富媒体播放页面控制方法、装置、电子设备及存储介质
CN111586481B (zh) 一种终端及应用的处理方法
KR102052498B1 (ko) 리모콘장치 및 그 동작 방법
US20230393820A1 (en) MVVM Architecture-Based Application Development Method and Terminal
CN112492402B (zh) 一种显示设备

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: 20929560

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: 20929560

Country of ref document: EP

Kind code of ref document: A1