WO2017173566A1 - 一种语音控制方法、装置及系统 - Google Patents

一种语音控制方法、装置及系统 Download PDF

Info

Publication number
WO2017173566A1
WO2017173566A1 PCT/CN2016/078440 CN2016078440W WO2017173566A1 WO 2017173566 A1 WO2017173566 A1 WO 2017173566A1 CN 2016078440 W CN2016078440 W CN 2016078440W WO 2017173566 A1 WO2017173566 A1 WO 2017173566A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
instruction
processing device
control device
voice
Prior art date
Application number
PCT/CN2016/078440
Other languages
English (en)
French (fr)
Inventor
张钦亮
朱萸
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 CN201680006596.3A priority Critical patent/CN107466458B/zh
Priority to PCT/CN2016/078440 priority patent/WO2017173566A1/zh
Publication of WO2017173566A1 publication Critical patent/WO2017173566A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B15/00Systems controlled by a computer
    • G05B15/02Systems controlled by a computer electric
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/28Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a voice control method, apparatus, and system.
  • various home devices in a smart home scene such as a refrigerator, a washing machine, and a television, all support voice interaction. If the user implements voice control on the refrigerator, it needs to move to the vicinity of the refrigerator for voice interaction.
  • the embodiment of the invention provides a voice control method, device and system, which are used to solve the problem of poor voice control of the processing device in the prior art.
  • the embodiment of the present invention provides a voice control method, where the method is applied to a voice control system, where the voice control system includes a control device and multiple processing devices, and the method includes:
  • the control device acquires an instruction corresponding to the voice signal of the user by using at least one of the plurality of processing devices; and then, according to the instruction, determining an execution object for the instruction; when the execution object is When the device is controlled, the control device performs an operation corresponding to the instruction; when the execution object is a second processing device of the plurality of processing devices, the control device sends the device to the second processing device An instruction for notifying the second processing device The operation corresponding to the instruction is executed.
  • the control device in the voice control system can acquire an instruction corresponding to the voice signal of the user through the at least one first processing device, thereby determining an execution object of the instruction, and implementing control on the execution object. Since the control device can acquire the instruction by the at least one first processing device, finally implementing the control device to control the execution object, and therefore, the voice control method can overcome the distance between the user and the execution object.
  • the problem of speech loss can overcome the problem of speech loss caused by the distance between the user and the control device.
  • the voice control method can implement voice control on the execution object anytime and anywhere, and improve the flexibility of voice control. Sex.
  • the control device before the control device acquires an instruction corresponding to the voice signal of the user by the at least one first processing device, the control device determines the at least one first processing device; and the control device The at least one first processing device sends a voice input open command, and the voice input open command is used to notify the at least one first processing device to start listening to the user's voice signal.
  • the control device determines the at least one first processing device in the current voice control system that may receive the voice signal of the user at the current time, and then the control device turns on the voice input function of the determined processing device, The power consumption caused by the at least one first processing device being activated by the voice parsing function for a long time is avoided, and the processing device other than the at least one processing device in the voice control system is prevented from being activated by the voice parsing function. Power consumption.
  • control device determines the at least one first processing device, including:
  • the control device acquires a physical location of the user and a physical location of the plurality of processing devices; the control device determines a physical location of each of the plurality of processing devices and the a distance between physical locations of the user; wherein the control device filters out, in the plurality of processing devices, the at least one of a distance between the physical location and the physical location of the user that is less than a first set distance threshold a processing device; or,
  • the control device filters out, in the plurality of processing devices, the at least one first processing device in a standby state or an operating state.
  • control device may determine the at least one first processing device, and further notify the at least one first processing device to start listening to the user's voice signal.
  • control device acquires the physical location of the user, including:
  • the control device acquires the positioning indication information sent by the user positioning device, where the positioning indication information is used to notify the control device that the distance between the physical location of the user and the physical location of the user positioning device is less than the second setting. a distance threshold; the control device acquires a physical location of the user positioning device, and uses a physical location of the user positioning device as a physical location of the user; or
  • the control device receives a physical location of the user sent by a third processing device of the plurality of processing devices, where the physical location of the user is determined by the third processing device.
  • control device can accurately determine the physical location of the user, and thus can ensure that the control device can determine the at least one first processing device.
  • control device acquires an instruction corresponding to the voice signal of the user by using the at least one first processing device, including:
  • control device can obtain an instruction corresponding to the voice signal of the user, thereby determining an execution object for the instruction, and implementing control on the execution object.
  • control device determines, according to the instruction, an execution object that the instruction is for, including:
  • the control device determines execution object information included in the instruction, and determines the execution object according to the execution object information;
  • control device Determining, by the control device, an operation corresponding to the instruction, the control device determining the execution object having an operation function corresponding to executing the instruction;
  • the control device Determining, by the control device, an operation corresponding to the instruction, the control device determining the execution object having an operation function corresponding to the instruction and located within a set space, wherein the physical location of the user is The set space range (for example, the room where the user is located).
  • control device can accurately determine the execution object for which the instruction is directed.
  • an embodiment of the present invention provides a voice control method, which is applied to a voice control system, where the voice control system includes a control device and multiple processing devices, and the method includes:
  • the first processing device of the plurality of processing devices acquires a voice signal of the user
  • the first processing device parses the voice signal of the user, obtains an instruction corresponding to the voice signal of the user, and sends the instruction to the control device.
  • the first processing device sends a voice signal or a corresponding instruction of the user to the control device, so that the control device acquires an instruction corresponding to the voice signal of the user, thereby determining an execution object of the instruction, and finally Implementing control of the execution object by the control device. Therefore, the voice control method can overcome the problem of voice loss caused by the distance between the user and the execution object, and can overcome the distance between the user and the control device. The problem of speech loss, obviously, the voice control method can realize voice control of the execution object anytime and anywhere, and improve the flexibility of voice control.
  • the first processing device before the first processing device acquires the voice signal of the user, the first processing device receives a voice input opening command sent by the control device; and starts an instruction according to the voice input opening command. User's voice signal.
  • the user after the first processing device receives the voice input open command, The user starts to listen to the voice signal of the user, and avoids the power consumption caused by the first processing device being activated by the voice resolution function for a long time.
  • the first processing device determines, according to the instruction, at least two execution objects that the instruction is for, When it is determined that the first processing device is included in the at least two execution objects, the first processing device performs an operation corresponding to the instruction.
  • the first processing device when the first processing device parses the instruction corresponding to the voice signal of the user, it may continue to determine whether it is an execution object corresponding to the instruction, and if so, directly perform the operation corresponding to the instruction to avoid Transmitting the instruction to the control device, and the process for the control device to deliver the instruction to the first processing device, shortening a delay of the first processing device to perform an operation corresponding to the instruction, Improve the user experience.
  • an embodiment of the present invention further provides a control device, which has a function of implementing the behavior of the control device in the example of the foregoing method.
  • the functions may be implemented by hardware or by corresponding software implemented by hardware.
  • the hardware or software includes one or more modules corresponding to the functions described above.
  • the structure of the control device includes an obtaining unit, a processing unit, and a sending unit, and the units may perform corresponding functions in the foregoing method examples.
  • the units may perform corresponding functions in the foregoing method examples.
  • the control device includes an obtaining unit, a processing unit, and a sending unit, and the units may perform corresponding functions in the foregoing method examples.
  • control device includes a transceiver, a processor, a bus, and a memory for communicating with a processing device in a voice control system, the processor being configured to The control device is supported to perform the corresponding functions in the above methods.
  • the memory is coupled to the processor, which stores program instructions and data necessary for the control device.
  • an embodiment of the present invention further provides a first processing device, where the first processing device has a function of implementing behavior of the first processing device in the foregoing method instance.
  • the functions may be implemented by hardware or by corresponding software implemented by hardware.
  • the hardware or software includes one or more modules corresponding to the functions described above.
  • the structure of the first processing device includes an acquiring unit, and the first The sending unit, or the obtaining unit, the processing unit, and the second sending unit, may perform the corresponding functions in the foregoing method examples.
  • the sending unit, or the obtaining unit, the processing unit, and the second sending unit may perform the corresponding functions in the foregoing method examples.
  • the method example which is not described herein.
  • the first processing device includes a transceiver, a processor, a bus, a memory, and a microphone
  • the transceiver is configured to perform communication interaction with a control device in a voice control system
  • the microphone For acquiring a voice signal of a user, the processor is configured to support the first processing device to perform a corresponding function in the above method.
  • the memory is coupled to the processor, which stores program instructions and data necessary for the first processing device.
  • an embodiment of the present invention provides a voice control system, where the system includes a control device and a plurality of processing devices, and the plurality of processing devices include at least one first processing device.
  • the control device in the voice control system may acquire an instruction corresponding to the voice signal of the user by using at least one first processing device, thereby determining an execution object of the instruction, and implementing control on the execution object. Since the control device can acquire the instruction by the at least one first processing device, finally implementing the control device to control the execution object, and therefore, the voice control method can overcome the distance between the user and the execution object.
  • the problem of speech loss can overcome the problem of speech loss caused by the distance between the user and the control device.
  • the voice control method can implement voice control on the execution object anytime and anywhere, and improve the flexibility of voice control. Sex.
  • FIG. 1 is a schematic structural diagram of a voice control system according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a voice control method according to an embodiment of the present invention.
  • FIG. 3 is a flowchart of another voice control method according to an embodiment of the present invention.
  • FIG. 4 is a flowchart of an example of a voice control method according to an embodiment of the present invention.
  • FIG. 5 is a structural diagram of a control device according to an embodiment of the present invention.
  • FIG. 6 is a structural diagram of a first processing device according to an embodiment of the present disclosure.
  • FIG. 6B is a structural diagram of a first processing device according to an embodiment of the present disclosure.
  • FIG. 7 is a structural diagram of another control device according to an embodiment of the present invention.
  • FIG. 8 is a structural diagram of another first processing device according to an embodiment of the present disclosure.
  • FIG. 9 is a schematic diagram of a voice control system according to an embodiment of the present invention.
  • the embodiment of the invention provides a voice control method, device and system, which are used to solve the problem of poor voice control of the processing device in the prior art.
  • the method and the device are based on the same inventive concept. Since the principles of the method and the device for solving the problem are similar, the implementation of the device and the method can be referred to each other, and the repeated description is not repeated.
  • the voice control system includes a control device, and the control device can acquire an instruction corresponding to the voice signal of the user by using at least one first processing device, thereby determining an execution object of the instruction, and implementing control on the execution object. . Since the control device can acquire the instruction by the at least one first processing device, finally implementing the control device to control the execution object, and therefore, the voice control method can overcome the distance between the user and the execution object.
  • the problem of speech loss can overcome the problem of speech loss caused by the distance between the user and the control device.
  • the voice control method can implement voice control on the execution object anytime and anywhere, and improve the flexibility of voice control. Sex.
  • a voice control system including a control device and a plurality of processing devices, the control device having a voice input function, and/or a voice parsing function, the plurality of processing devices also having a voice input function, and/or a voice parsing function .
  • the user can control the voice through the voice signal sent. Control of equipment in the system.
  • the control device and the processing device in the voice control system may be different.
  • the processing device may be various smart homes such as a refrigerator, a washing machine, a television, a home lighting device, and the like, and the control device is a home computer.
  • the voice signal of the user that is, the voice emitted by the user, the voice signal of the user involved in the present invention is a sound that the user desires to perform certain operations when the user controls the device in the voice control system, and the voice signal of the user
  • the physical sound is the sound wave emitted by human beings, which is a continuously changing analog signal.
  • the voice input function is a function of monitoring the voice signal of the user and extracting the voice signal of the user when the voice signal of the user is monitored.
  • the control device or the processing device in the voice control system implements the voice input function through a microphone.
  • the voice parsing function is a function of recognizing and parsing a user's voice signal and obtaining an instruction corresponding to the user's voice signal. This instruction notifies the user of the device (execution object) that he or she wants to control, and performs some operations that the user desires.
  • the control device or the processing device in the voice control system implements the voice input function through a voice recognition module.
  • the control device may control and manage the processing device in the voice control system, for example, send an instruction corresponding to the voice signal of the user to a processing device, and cause the processing device to perform an operation corresponding to the instruction; to the processing device Sending a voice input enable command, controlling the processing device to activate the voice input function, and starting to monitor the user's voice signal.
  • the processing device can receive various instructions of the control device, and perform operations corresponding to the instruction, and have a voice input function (ie, including a microphone).
  • a voice input function ie, including a microphone
  • the voice input opening command is sent to the processing device in the voice control system, and the processing device can be controlled to start the voice input function and start monitoring the voice signal of the user.
  • the first processing device is a processing device that receives a voice signal of the user from the plurality of processing devices.
  • the second processing device is a device (execution object) that the user desires to control among the plurality of processing devices.
  • a third processing device which is a process that can determine a physical location of the user among the plurality of processing devices device.
  • the user positioning device is a portable device carried on the user in the voice control system for positioning the user.
  • the user positioning device may be a device that a user, such as a mobile phone, often carries, or a wearable device such as a smart watch or a wristband.
  • the user positioning device has motion sensor detection and physiological detection (such as pulse rate, blood pressure, blood oxygen, or blood sugar).
  • the detection function may be used to detect whether the user positioning device is carried on the user, so as to determine that the user is consistent with the physical location of the user positioning device; the user positioning device may also be a detection device placed in a fixed position.
  • the user positioning device determines whether the user is nearby, and when the user positioning device has a camera detection or infrared detection function, whether the user is detected, whether the user is detected, whether the user is nearby, or by determining the physical location of the user Describe the distance between the physical location of the user positioning device and the size of the second distance threshold to determine whether the user is nearby.
  • the user positioning device determines that the user is consistent with the physical location of the user positioning device or the user is in the vicinity of the user positioning device (the distance between the physical location of the user and the physical location of the user positioning device is less than
  • the positioning indication information is sent to the control device and/or the plurality of processing devices in the voice control system.
  • Positioning indication information when the user positioning device determines that the distance between the physical location of the user and the physical location of the user positioning device is less than a set second distance threshold, to the control device in the voice control system and Or sent by the plurality of processing devices to notify the control device and/or the plurality of processing devices to use the physical location of the user positioning device as a physical location of the user.
  • the first message is that when the processing device in the voice control system detects that the user is in the vicinity of the user, or detects the user through functions such as infrared detection, camera detection or body temperature detection, it is determined that the user can be at the current time (ie, the user's physics) When the position is unchanged, it can be sent when the user's voice signal is received.
  • the first set distance threshold is used to determine whether the user is in the vicinity of the processing device (or the processing device is in the vicinity of the user), and further determines whether the processing device can receive the user's voice signal. When the distance between the physical location of the processing device and the physical location of the user is less than the first set distance threshold At this time, it can be determined that the user is in the vicinity of the processing device, so that the processing device can receive the user's voice signal.
  • the value of the first set distance threshold is generally a distance that can cause the speech signal to be lost, for example, 5 m, 3 m, and the like.
  • the second set distance threshold is used to determine whether the user is in the vicinity of the user positioning device, that is, whether the user can locate the physical location of the device as the physical location of the user.
  • the user positioning device determines that the distance between the physical location of the user and the physical location of the user positioning device is less than a second set distance threshold, the user positioning device is to the control device in the voice control system And/or the plurality of processing devices locate the indication information.
  • Multiple means two or more.
  • association relationship of the associated object indicating that there may be three relationships, for example, A and/or B, which may indicate that there are three cases where A exists separately, A and B exist at the same time, and B exists separately.
  • the character "/" generally indicates that the contextual object is an "or" relationship.
  • FIG. 1 shows an architecture of a possible system according to an embodiment of the present invention, which includes: a control device 101 and a plurality of processing devices 102, wherein
  • the control device 101 is configured to acquire an instruction corresponding to the voice signal of the user by using part or all of the processing devices 102 of the plurality of processing devices 102, and determine an execution object according to the instruction, when the execution object is itself The control device 101 performs an operation corresponding to the instruction; when the execution object is one of the plurality of processing devices 102, the control device 101 sends an instruction to the processing device 102, so that The processing device 102 performs an operation corresponding to the instruction, thereby implementing control of an execution object;
  • the processing device 102 is a device having a voice input function, that is, the processing device 102 can monitor a voice signal of the user. Listening to the user after a processing device 102 turns on the voice input function Optionally, the processing device 102 may send the monitored voice signal of the user to the control device 101; optionally, when the processing device 102 has a voice parsing function, the processing device 102 The voice signal of the user may be parsed, an instruction corresponding to the voice signal of the user is obtained, and the parsed instruction is sent to the control device 101. In the case that the processing device 102 can send the monitored voice signal of the user to the control device 101, the control device 101 also has a voice parsing function, after receiving the voice signal of the user. And parsing the voice signal of the user, and acquiring an instruction corresponding to the voice signal of the user.
  • the control device 101 may After receiving the instruction of the user, starting its own voice parsing function, or after receiving the instruction sent by the user through any one or more of the plurality of processing devices 102, starting its own voice parsing function, the control device 101 can also enable the voice parsing function within a set time.
  • each processing device 102 may also initiate its own voice resolution after receiving the user's instruction. a function; or the control device 101, when it is determined that some of the plurality of processing devices 102 are likely to receive a voice signal of the user at the current time, send a voice input enable command to the processing devices 102 to initiate the processing The voice input function of device 102.
  • the processing device 102 may enable the voice parsing function while turning on the voice input function in the foregoing manner.
  • control device 101 determines the processing device 102 that may receive the voice signal of the user at the current time, and includes the following two methods:
  • the first mode in the case where the control device 101 can determine the physical location of the user and the physical location of the plurality of processing devices 102, the control device 101 can be at the plurality of locations
  • the processing device 102 filters out the processing device 102 that the distance between the physical location and the physical location of the user is less than the first set distance threshold, as the processing device 102 that may receive the voice signal of the user at the current time;
  • the second mode when the control device 101 cannot determine the physical location of the user, the control device 101 may filter out the processing device 102 in the running state in the multiple processing devices 102, or process in the standby state.
  • the device 102, or the processing device 102 in the running state or the standby state is filtered out, and the filtered processing device 102 is used as the processing device 102 that may receive the voice signal of the user at the current time;
  • a third way in the case where the processing device 102 in the plurality of processing devices 102 can determine whether it can receive the user's voice signal at the current time, the plurality of processing devices 102 determine that they can be currently
  • the processing device 102 that receives the voice signal of the user at the moment sends a first message to the control device 101 to notify the control device 101, and the control device 101 can determine, by using the received first message, that it is likely to be received at the current time. Processing device 102 of the user's voice signal.
  • a processing device 102 can determine whether it can receive the user's voice signal at the current time by the following methods:
  • the processing device 102 determines the physical location of the user, the processing device 102 determines the distance between itself and the physical location of the user and the first set distance threshold; determines the physics of itself and the user The processing device 102, where the distance between the locations is less than the first set distance threshold, sends a first message to the control processing device 102, the first message being used to notify the control device that the language processing device 102 can be at the current moment Receiving a voice signal of the user;
  • the processing device 102 When the processing device 102 has functions such as infrared detection, imaging detection, and body temperature detection, it can be detected by the above function. If the user is detected, the first message is sent to the control processing device 102, and the first message is used for Notifying the control device 101 that the processing device 102 can receive the user's voice signal at the current time;
  • the user positioning device 103 is further included in the system.
  • the processing device 102 may further send the user positioning device 103 to the user positioning device 103.
  • Sending a wireless signal when the processing device 102 determines that the user positioning device 103 can receive the wireless signal, or determines that the signal strength of the wireless signal is greater than a set signal strength threshold, determining that the processing device 102 can be current Similarly, the processing device 102 can also determine that the processing device 102 can receive the user's voice signal at the current time by receiving the wireless signal sent by the user positioning device 103.
  • the user positioning device 103 may be a device that the user often carries, such as a mobile phone, a smart watch, a wristband, etc.
  • the control device 101 and any one of the processing devices 102 determine the physical location of the user, and generally also determine the user and The physical location of the user positioning device 103 is the same, that is, the current time, the user carries the user positioning device 103.
  • the user positioning device 103 when the user positioning device 103 has the functions of motion sensor detection, physiological detection (such as pulse rate, blood pressure, blood oxygen or blood sugar detection) or camera detection, the user positioning device 103 can be detected by the above function. It is carried on the user, thereby determining that the user is consistent with the physical location of the user positioning device 103.
  • the user positioning device 103 determines that the user is consistent with the physical location of the user positioning device 103, sending positioning indication information to the control device 101 and the plurality of processing devices 102, notifying the physical location and location of the user
  • the distance between the physical locations of the user positioning devices is less than a second set distance threshold, such that the control device 101 and the plurality of processing devices 102 can use the physical location of the user positioning device 103 as the user Physical location.
  • the control device 101 and the plurality of processing devices 102 can communicate directly with each other, and can also communicate through a bridging device or a routing device, and can also communicate through other networking modes, which is not limited by the present invention.
  • Various communication technologies used by the control device 101 to communicate with the plurality of processing devices 102 such as Wireless Fidelity (WiFi) technology, Bluetooth technology, Ethernet technology, ZigBee
  • WiFi Wireless Fidelity
  • Bluetooth technology Bluetooth technology
  • Ethernet technology ZigBee
  • ZigBee ZigBee
  • the present invention does not limit the technology, the Universal Plug and Play (UPnP) technology, and the Digital Living Network Alliance (DLNA) technology.
  • DLNA Digital Living Network Alliance
  • the routing device can communicate with each other through other networking modes, which is not limited by the present invention.
  • the communication technology used for communication between the control device 101 and the user positioning device 103, and the communication technology used for communication between the plurality of processing devices 102 and the user positioning device 103 may be, but not limited to, WiFi technology. Bluetooth technology and the like, the present invention does not limit this.
  • An embodiment of the present invention provides a voice control method, which is applicable to a voice control system as shown in FIG. 1 , where the voice control system includes a control device and multiple processing devices.
  • the specific process of the method includes:
  • Step 201 The control device acquires an instruction corresponding to the voice signal of the user by using at least one of the plurality of processing devices.
  • step 201 the control device acquires an instruction corresponding to the voice signal of the user by using the at least one first processing device, and therefore, the voice input function of the at least one first processing device is turned on.
  • all processing devices in the current voice control system turn on the voice input function when the power is connected.
  • some processing devices are unlikely to receive the user's voice signal at the current moment, so turning on the voice input function of these processing devices for a long time increases excessive power consumption.
  • control device determines a processing device in the current voice control system that may receive the voice signal of the user at the current time, and then the control device turns on the voice input function of the determined processing device, thereby preventing the processing device from being long. Time starts the power consumption caused by the voice resolution function.
  • the method further includes:
  • the control device determines the at least one first processing device
  • the control device sends a voice input open command to the at least one first processing device, the voice input open command is used to notify the at least one first processing device to start listening to the user's voice signal. After receiving the voice input enable command, the at least one processing device starts performing an operation of monitoring a voice signal of the user.
  • the control device can only determine n processing devices (ie, processing devices in the vicinity of the user) that are likely to receive the user's voice signal at the current time.
  • n processing devices ie, processing devices in the vicinity of the user
  • the processing device that can receive the voice signal of the user clearly and accurately can not determine the at least one first processing device that must receive the voice signal of the user, where n is a positive integer.
  • the at least one first processing device is included in the n devices, and therefore, the control device determines the at least one first processing device by determining the n processing devices.
  • the method for determining, by the control device, the n processing devices is the same as the method for determining the at least one first processing device, where only the at least one first processing device is determined as an example, the control The method for the device to determine the n processing devices is not described again.
  • control device may determine the at least one first processing device at a specified time or when a specified command is received.
  • control device determines the at least one first processing device, and includes the following manners:
  • the first mode the plurality of processing devices in the current voice control system can detect whether the user can receive the voice signal of the user at the current time, and the multiple processing devices detect that they can receive the current time. Sending a first message to the control device when the voice signal of the user is sent; the control device determines the at least one first processing device according to the received first message, the first message is the at least one The first processing device is sent when the user can receive the voice signal of the user at the current time;
  • a processing device detects that the user can receive the voice signal of the user at the current time, and can adopt the following methods:
  • the processing device can determine the physical location of the user, the device determines the distance between itself and the physical location of the user and the first set distance threshold; in determining the physical location of the user and the user When the distance between the two is less than the first set distance threshold, it is determined that the user can receive the voice signal of the user at the current time;
  • the processing device has functions such as infrared detection, imaging detection, body temperature detection, etc.
  • the user can be detected by the above function, and if the user is detected, it is determined that the user can receive the voice signal of the user at the current time;
  • a user positioning device is further included in the system, and the physical location of the user is determined by the user When the distance between the physical locations of the bit devices is less than a second set distance threshold (eg, the user carries the user positioning device), the processing device may further send a wireless signal to the user positioning device, where the processing device determines When the user positioning device is capable of receiving the wireless signal, or determining that the signal strength of the wireless signal is greater than a set signal strength threshold, the processing device determines that the user may receive the voice signal of the user at the current time; or the user positioning device Broadcasting the wireless signal, when the processing device receives the wireless signal, or determines that the received signal strength of the wireless signal is greater than a set signal strength threshold, the processing device determines that it can receive the user's voice signal at the current time.
  • a second set distance threshold eg, the user carries the user positioning device
  • the processing device can determine that it can receive the user's voice signal at the current time by determining that it is in the vicinity of the user, without being limited to the above-exemplified method.
  • the control device acquires a physical location of the user and a physical location of the multiple processing devices; the control device determines a physical location of each of the plurality of processing devices and the user The distance between the physical locations; the control device, in the plurality of processing devices, filtering out the at least one first distance between the physical location and the physical location of the user that is less than a first set distance threshold Processing equipment;
  • the physical location of the present invention may be latitude and longitude information, or may be coordinate information within a specified spatial range, which is not limited by the present invention.
  • control device acquires the physical location of the user, including:
  • the positioning indication information is sent to the control device, where the positioning indication information is used. Notifying that the distance between the physical location of the user of the control device and the physical location of the user positioning device is less than a second set distance threshold (ie, the physical location of the user positioning device may be used as the physical of the user) a location; after the control device acquires the location indication information sent by the user location device, the control device acquires a physical location of the user location device, and uses a physical location of the user location device as a physical location of the user; The user positioning device detects a physical location of the user and a physical location of the user positioning device.
  • a second set distance threshold ie, the physical location of the user positioning device may be used as the physical of the user
  • the detection may be performed by a function of motion sensor detection, physiological detection, and/or imaging detection.
  • the user positioning device detects the user.
  • the distance between the physical location and the physical location of the user positioning device is less than the second set distance threshold, not only the positioning indication information is sent to the control device, but also the processing device in the current voice control system may be sent.
  • the positioning indication information is used to notify the processing device that the user is consistent with the physical location of the user positioning device;
  • a third mode when the control device does not obtain the positioning indication information sent by the user positioning device, and the physical location of the user is not obtained, the control device filters the multiple processing devices.
  • the at least one first processing device in a standby state or an operating state.
  • step 201 the control device acquires the instruction, and includes the following two methods:
  • the first mode the at least one first processing device not only has a voice input function, but also has a voice parsing function. Therefore, after the at least one first processing device listens to the voice signal of the user, the user is The voice signal is parsed to obtain an instruction corresponding to the voice signal of the user, and the instruction is sent to the control device; the control device receives the instruction sent by the at least one first processing device.
  • the control device receives the voice signal of the user sent by the at least one first processing device, where the voice signal of the user is monitored by the at least one first processing device; Parsing the voice signal of the user to obtain the instruction.
  • the at least one first processing device has a voice parsing function, and the voice parsing function can perform voice parsing only after receiving the voice signal of the user, in order to reduce the at least one first processing device. Power consumption caused by the voice parsing function.
  • the at least one first processing device may start a voice parsing function while receiving a voice input start command of the control device, and start a voice input function; or the control The device sends a voice parsing open command to the at least one first processing device, and the at least one first processing device receives After the voice parsing on command is started, the voice parsing function is started.
  • the first processing device of the at least one first processing device parses the instruction, it is determined whether the execution object for the instruction includes itself, if it includes itself and other processing devices or the When the device is controlled, the first processing device may perform an operation corresponding to the instruction, and send the instruction to the control device, and after receiving the instruction, the control device determines execution of the instruction The object is excluded from the first processing device.
  • the method further includes: the control device starts a voice parsing function of the control device.
  • control device starts its own voice parsing function, which may be when the power is connected; or
  • the control device starts the voice parsing function after receiving the voice parsing open command.
  • Step 202 The control device determines, according to the instruction, an execution object for which the instruction is directed.
  • step 202 the control device determines an execution object, which may be, but is not limited to, the following method:
  • the control device determines execution object information included in the instruction, and determines the execution object according to the execution object information; for example, the instruction is “turn on an air conditioner”, and the control device may determine The execution object information is “air conditioning”, and the control device may determine, according to “air conditioning”, that the execution object is an air conditioner in the current voice control system.
  • the control device determines an operation corresponding to the instruction, and the control device determines the execution object having an operation function corresponding to the execution of the instruction; for example, the instruction is “cooking rice”,
  • the control device has an execution object of the "cooking rice” function in the current voice control system, such as a smart rice cooker.
  • the control device determines an operation corresponding to the instruction, and the control device determines the execution object having an operation function corresponding to the instruction and located within a set space, wherein the user The physical location is within the set space; for example, the command is "on", and when the room is too much, the control device selects the light of the room in which the user is located.
  • the control device needs to determine a physical location of the user when the control device determines the execution object by using a third method, and the control device acquires the physical location of the user has been described in step 201. , will not repeat them here.
  • Step 203 When the execution object is the control device, the control device performs an operation corresponding to the instruction; when the execution object is a second processing device of the plurality of processing devices, the controlling The device sends the instruction to the second processing device, the instruction for notifying the second processing device to perform an operation corresponding to the instruction.
  • the voice control system includes a control device, and the control device may acquire an instruction corresponding to the voice signal of the user by using at least one first processing device, thereby determining an execution object of the instruction, and implementing the execution object. control. Since the control device can acquire the instruction by the at least one first processing device, finally implementing the control device to control the execution object, and therefore, the voice control method can overcome the distance between the user and the execution object. The problem of speech loss can overcome the problem of speech loss caused by the distance between the user and the control device. Obviously, the voice control method can implement voice control on the execution object anytime and anywhere, and improve the flexibility of voice control. Sex.
  • An embodiment of the present invention provides a voice control method, which is applicable to a voice control system as described in FIG. 1 , where the voice control system includes a control device and multiple processing devices.
  • the specific process of the method includes:
  • Step 301 The first processing device of the plurality of processing devices acquires a voice signal of the user.
  • the first processing device is any one of the processing devices 102 in the system shown in FIG. 1, and the first processing device is one of the at least one first processing device in the foregoing embodiment. device.
  • the voice input function of the first processing device is turned on.
  • the first processing device turns on the voice input function when the power is connected, but this increases the power consumption of the first processing device.
  • the first processing device passes the control
  • the device is configured to enable the voice input function, that is, before the first processing device acquires the voice signal of the user, the method further includes:
  • the first processing device receives a voice input open command sent by the control device
  • the first processing device starts listening to the user's voice signal according to the voice input opening command.
  • Step 302 The first processing device sends the voice signal of the user to the control device, or the first processing device parses the voice signal of the user to obtain an instruction corresponding to the voice signal of the user, and The instructions are sent to the control device.
  • step 302 after the first processing device sends the voice signal of the user to the control device, the control device parses the voice signal of the user to obtain a corresponding instruction. And determining an execution object for the instruction, thereby implementing control of the execution object.
  • step 302 in a case where the first processing device has a voice parsing function, the first processing device directly parses the voice signal of the user after acquiring the voice signal of the user.
  • the work of voice parsing of the control device is shared, and the workload of the control device is reduced.
  • the method before the first processing device parses the voice signal of the user, the method further includes: the first processing device starts a voice parsing function of the first processing device.
  • the first processing device may start the voice parsing function of the first processing device when the voice input function is started.
  • the method further includes:
  • the first processing device determines, according to the instruction, at least two execution objects that the instruction is for, when determining that the at least two execution objects include the first processing device, the first processing device executes The operation corresponding to the instruction.
  • the first processing device parses the instruction corresponding to the voice signal of the user, it may continue to determine whether it is an execution object corresponding to the instruction, and if so, directly execute the instruction. Corresponding operation, avoiding sending the instruction to the control device, and the process of issuing the instruction to the first processing device by the control device, shortening the first processing device to execute the corresponding instruction The delay of the operation increases the user experience.
  • the instruction is required to be sent to the control device.
  • the control device determines other execution objects than the first processing device, thereby implementing control of the control device on other execution objects.
  • the first processing device sends the voice signal or the corresponding command of the user to the control device, so that the control device acquires an instruction corresponding to the voice signal of the user, thereby determining the command.
  • the execution object finally realizes the control of the execution object by the control device. Therefore, the voice control method can overcome the problem of voice loss caused by the distance between the user and the execution object, and can overcome the user and the control device. The problem of speech loss caused by the distance between the two, obviously, the voice control method can realize voice control of the execution object anytime and anywhere, and improve the flexibility of voice control.
  • an embodiment of the present invention further provides an example of a voice control method, where the example may be applied to the voice control system as described in FIG.
  • Step 401 The user positioning device determines whether the physical location of the user and the physical location of the user are less than a second set distance threshold. If yes, step 402 or step 405 is performed, otherwise step 407 or step 408 is performed.
  • the user positioning device When the user positioning device performs step 401, it can detect whether it is carried on the user, that is, the function can be detected by motion sensor detection, physiological detection, and/or camera detection. For example, when the user positioning device supports the motion sensor detection function, the user positioning device detects by the motion sensor that when the motion sensor detects the user positioning device for a set time (for example, 10 minutes) If it is in a static state, it means that the user positioning device is not carried on the user, because if the user positioning device is carried on the user, the user will not be in a static state all the time, even if the user is still or sleeping, there will be slight
  • the motion sensor can also detect motion.
  • the motion sensor may be an accelerometer, a gyroscope, or the like. When the user positioning device detects that it is carried on the user, it indicates that it is consistent with the physical location of the user.
  • the user positioning device not only sends the positioning indication information to the control device but also sends the positioning indication information to the device in the current voice control system when detecting that the user positioning device is carried on the user.
  • These devices can determine the location of the user by the physical location of the user location device.
  • Step 402 The user positioning device sends the positioning indication information to the processing device in the voice control system, where the positioning indication information is used to notify the processing device in the voice control system that the physical location of the user positioning device and the physical location of the user are smaller than the second. Set the distance threshold.
  • the processing device in the voice control system can determine that the physical location of the user positioning device is the physical location of the user, and each device can determine whether it is in the vicinity of the user according to the physical location or wireless signal.
  • the processing device in the vicinity of the user can receive the user's signal at the current time.
  • Step 403 Each processing device in the voice control system determines whether it is in the vicinity of the user according to the physical location or the wireless signal; and determines that the processing device in the vicinity of the user sends the first message to the control device, where the first message is used to notify The control device itself determines that the user's voice signal can be received at the current time.
  • any one of the processing devices determines that it is in the vicinity of the user according to the physical location:
  • the processing device determines a distance between itself and a physical location of the user and a first set distance threshold
  • the processing device determines to be in the vicinity of the user when determining that the distance between itself and the physical location of the user is less than the first set distance threshold.
  • any one of the processing devices determines that it is in the vicinity of the user according to the wireless signal:
  • the processing device transmits a wireless signal to the user positioning device; the processing device determines the When the user positioning device is capable of receiving the wireless signal, or determining that the signal strength of the wireless signal is greater than a set signal strength threshold, the processing device determines that it is in the vicinity of the user; or
  • the user positioning device broadcasts a wireless signal, and when the processing device receives the wireless signal or determines that the received signal strength of the wireless signal is greater than a set signal strength threshold, the processing device determines that it is in the vicinity of the user.
  • Step 404 The control device determines, according to the received first message, a processing device in the voice control system in the vicinity of the user.
  • the control device determines that the processing device that sends the first message is a processing device in the vicinity of the user.
  • Step 405 The user positioning device sends the positioning indication information to the control device, where the positioning indication information is used to notify the processing device in the voice control system that the physical location of the user positioning device and the physical location of the user are less than a second set distance threshold.
  • the control device can determine that the physical location of the user location device is the physical location of the user. After determining the physical location of the user, the control device can determine a device in the vicinity of the user.
  • Step 406 The control device determines a processing device in the voice control system in the vicinity of the user according to the physical location.
  • control device acquires a physical location of the user positioning device, and uses a physical location of the user positioning device as a physical location of the user;
  • the control device acquires physical locations of multiple processing devices in the voice control system
  • the control device determines a distance between a physical location of each of the plurality of processing devices and a physical location of the user;
  • the control device filters, in the plurality of devices, a processing device whose distance between the physical location and the physical location of the user is less than the set distance threshold, and the filtered processing device is a location near the user. .
  • Step 407 The control device determines all processing devices in the voice control system that are in an active state or a standby state.
  • the control device cannot determine the processing device in the vicinity of the user, and therefore, only all devices in the voice control system that can turn on the voice input function, that is, all running or standby State of the device.
  • Step 408 Each processing device in the voice control system detects a user by using functions such as infrared detection, camera detection, or body temperature detection; and detecting that the processing device of the user sends a first message to the control device, where the first message is used to notify the The control device itself determines that the user's voice signal can be received at the current moment.
  • functions such as infrared detection, camera detection, or body temperature detection
  • each processing device in the voice control system cannot determine whether it is in the vicinity of the user through the physical location or the wireless signal. Therefore, it is also possible to determine whether it is in the vicinity of the user by other means.
  • a processing device has an imaging function
  • the processing device captures a user, it is determined that the processing device is in the vicinity of the user.
  • Step 409 The control device sends a voice input open command to the determined n processing devices, and opens a voice input function of the n processing devices.
  • the control device opens the determined processing device that is likely to receive the voice signal of the user, avoids turning on the voice input function of all the processing devices in the voice control system, and reduces power consumption caused by the voice input function of other processing devices.
  • Step 410 The n devices start to listen to the user's voice signal, and at least one of the n processing devices monitors the user's voice signal.
  • Step 411 The at least one first processing device sends the voice signal of the user to the control device.
  • Step 412 The control device parses the voice signal of the user to obtain an instruction corresponding to the voice signal of the user.
  • Step 413 The at least one first processing device parses the voice signal of the user to obtain an instruction corresponding to the voice signal of the user.
  • Step 414 Each first processing device in the at least one first processing device determines at least two execution objects for which the instruction is directed, and determines, at any one of the first processing devices, the two execution objects. When the self is included, the first processing device performs an operation corresponding to the instruction.
  • Step 414 is an optional step.
  • step 420, step 421, and step 422 are also optional steps.
  • step 420, step 421, and step 422 also need to be performed.
  • Step 415 The at least one first processing device sends an instruction corresponding to the voice signal of the user to the control device.
  • Step 416 The control device determines, according to the obtained instruction, at least one execution object for which the instruction is directed.
  • the method for determining the execution object of the at least one execution object is the same as the method in the foregoing embodiment, and details are not described herein again.
  • Step 417 The control device determines that the number of the at least one execution object is 1, and when the execution object is the control device, the control device performs the instruction corresponding operation.
  • Step 418 The control device determines that the number of the at least one execution object is greater than 1, and when the execution object includes the control device and the at least one second processing device, the control device performs an operation corresponding to the instruction.
  • Step 419 The control device determines that the at least one execution object is at least one second processing device.
  • step 423 is directly executed after step 418 or step 419 is performed.
  • Step 420 The control device determines whether the at least one second processing device includes the first processing device that has performed the operation corresponding to the instruction, and if yes, performs step 421 or step 422, otherwise performs step 423.
  • Step 421 When the number of the at least one second processing device is 1, the process ends.
  • Step 422 When the number of the at least one second processing device is greater than 1, the control device sends the instruction to the second processing device other than the first processing device of the at least one second processing device.
  • Step 423 The control device sends the instruction to the at least one second processing device.
  • Step 424 Each second processing device that receives the instruction performs an operation corresponding to the instruction.
  • the control device in the voice control system can acquire an instruction corresponding to the voice signal of the user by using at least one first processing device, thereby determining an execution object of the instruction, and implementing control on the execution object. Since the control device can acquire the instruction by the at least one first processing device, finally implementing the control device to control the execution object, and therefore, the voice control method can overcome the distance between the user and the execution object.
  • the problem of speech loss can overcome the problem of speech loss caused by the distance between the user and the control device.
  • the voice control method can implement voice control on the execution object anytime and anywhere, and improve the flexibility of voice control. Sex.
  • the embodiment of the present invention further provides a control device, where the control device is applied to the voice control system shown in FIG. 1 , where the voice control system further includes multiple processing devices, as shown in FIG. 5 .
  • the control device 500 includes: an obtaining unit 501, a processing unit 502, and a sending unit 503, where
  • the obtaining unit 501 is configured to acquire, by using at least one of the plurality of processing devices, an instruction corresponding to the voice signal of the user;
  • the processing unit 502 is configured to determine, according to the instruction, an execution object that the instruction is for; and, when the execution object is the control device, perform an operation corresponding to the instruction;
  • the sending unit 503 is configured to: when the execution object is the second processing device of the multiple processing devices, send the instruction to the second processing device, where the instruction is used to notify the second processing device Execute the operation corresponding to the instruction.
  • processing unit 502 is further configured to:
  • the sending unit 503 is further configured to send a voice input open command to the at least one first processing device, where the voice input open command is used to notify the at least one first processing device to start monitoring a voice signal of the user.
  • the obtaining unit 501 is further configured to:
  • the processing unit 502 is specifically configured to: when determining the at least one first processing device:
  • the acquiring unit 501 After the acquiring unit 501 receives the first message sent by the at least one first processing device, determining, according to the first message, the at least one first processing device; or
  • the acquiring unit 501 acquires the physical location of the user and the physical location of the multiple processing devices, determining between a physical location of each of the plurality of processing devices and a physical location of the user And in the plurality of processing devices, the at least one first processing device that selects a distance between the physical location and the physical location of the user that is less than a first set distance threshold; or
  • the at least one first processing device in a standby state or an operating state is filtered out.
  • the acquiring unit 501 is specifically configured to: when acquiring the physical location of the user:
  • the positioning indication information is used to notify the control device that the distance between the physical location of the user and the physical location of the user positioning device is less than a second set distance threshold; Obtaining a physical location of the user positioning device, and using a physical location of the user positioning device as a physical location of the user; or
  • the acquiring unit 501 is specifically configured to: when acquiring, by using the at least one first processing device, an instruction corresponding to a voice signal of the user:
  • processing unit 502 is specifically configured to: when determining, according to the instruction, an execution object that the instruction is for:
  • Determining an operation corresponding to the instruction and determining the execution object having an operation function corresponding to the execution of the instruction and located within a set space, wherein a physical location of the user is within the set space.
  • the control device may acquire an instruction corresponding to the voice signal of the user by using at least one first processing device, thereby determining an execution object of the instruction, and implementing control on the execution object. Since the control device can acquire the instruction by the at least one first processing device, finally implementing control of the execution object by the control device, and therefore, implementing the voice control method by the control device can overcome the user and the execution object The problem of speech loss caused by the distance between the two can overcome the problem of speech loss caused by the distance between the user and the control device. Obviously, the voice control method can realize voice control of the execution object anytime and anywhere, and improve The flexibility of voice control.
  • the embodiment of the present invention further provides a first processing device, where the first processing device is applied to a voice control system as shown in FIG. 1 , where the voice control system includes a control device and multiple processes.
  • the first processing device is one of the plurality of processing devices, and the first processing device may have two structures.
  • the first processing device 600 in the first configuration, may include an obtaining unit 601, a first sending unit 602; as shown in FIG. 6B, in a second configuration, the first processing device 600 may include an obtaining unit 601, a processing unit 603, and a second sending unit 604, where ,
  • the obtaining unit 601 is configured to acquire a voice signal of the user.
  • the first sending unit 602 is configured to send a voice signal of the user to the control device;
  • the processing unit 603 is configured to parse the voice signal of the user, and obtain an instruction corresponding to the voice signal of the user;
  • the second sending unit 604 is configured to send the instruction to the control device.
  • the obtaining unit 601 is further configured to:
  • the user's voice signal is started to be monitored.
  • processing unit 603 is further configured to:
  • the first processing device sends a voice signal or a corresponding command of the user to the control device, so that the control device acquires an instruction corresponding to the voice signal of the user, thereby determining The execution object of the instruction finally realizes the control of the execution object by the control device. Therefore, the voice control method of the first processing device can overcome the problem of speech loss caused by the distance between the user and the execution object. At the same time, the problem of speech loss caused by the distance between the user and the control device can be overcome. Obviously, the voice control method can implement voice control on the execution object anytime and anywhere, and the flexibility of voice control is improved.
  • the division of the unit in the embodiment of the present invention is schematic, and is only a logical function division, and the actual implementation may have another division manner.
  • the functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit is implemented in the form of a software functional unit and sold as a standalone product Or when used, it can be stored in a computer readable storage medium.
  • the technical solution of the present application in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, and the program code can be stored. Medium.
  • the embodiment of the present invention further provides a control device, where the control device is applied to the voice control system shown in FIG. 1 , where the voice control system further includes multiple processing devices, as shown in FIG. 7 .
  • the control device 700 includes: a transceiver 701, a processor 702, a bus 703, and a memory 704, where
  • the transceiver 701, the processor 702 and the memory 704 are mutually connected by the bus 703; the bus 703 may be a peripheral component interconnect (PCI) bus or an extended industry standard structure (extended Industry standard architecture, referred to as EISA) bus.
  • PCI peripheral component interconnect
  • EISA extended Industry standard architecture
  • the bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in Figure 7, but it does not mean that there is only one bus or one type of bus.
  • the transceiver 701 is configured to perform communication interaction with the multiple processing devices in the voice control system.
  • the processor 702 is configured to implement the voice control method as shown in FIG. 2, including:
  • the execution object is the control device 700, performing an operation corresponding to the instruction; when the execution object is a second processing device of the plurality of processing devices, transmitting the location to the second processing device An instruction, the instruction is used to notify the second processing device to execute the corresponding instruction operating.
  • the processor 702 is further configured to: before acquiring, by using the at least one first processing device, the instruction corresponding to the voice signal of the user:
  • the processor 702 is specifically configured to: when determining the at least one first processing device:
  • the at least one first processing device in a standby state or an operating state is filtered out.
  • the processor 702 is specifically configured to: when acquiring the physical location of the user:
  • the positioning indication information is used to notify the control device 700 that the distance between the physical location of the user and the physical location of the user positioning device is less than a second set distance threshold; Obtaining a physical location of the user positioning device, and using a physical location of the user positioning device as a physical location of the user; or
  • the processor 702 when the processor 702 obtains an instruction corresponding to the voice signal of the user by using the at least one first processing device, the processor 702 is specifically configured to:
  • Receiving the instruction sent by the at least one first processing device the instruction being the at least After the first processing device listens to the voice signal of the user, and parses the voice signal of the user;
  • the processor 702 is specifically configured to: when determining, according to the instruction, an execution object that the instruction is for:
  • Determining an operation corresponding to the instruction determining the execution object having an operation function corresponding to the execution of the instruction and located within a set space, wherein a physical location of the user is within the set space.
  • the memory 704 is used to store programs and the like.
  • the program can include program code, the program code including computer operating instructions.
  • the memory 704 may include a random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage.
  • the processor 702 executes the application stored in the memory 704 to implement the above functions, thereby implementing the voice control method as shown in FIG. 2.
  • the control device may acquire an instruction corresponding to the voice signal of the user by using at least one first processing device, thereby determining an execution object of the instruction, and implementing control on the execution object. Since the control device can acquire the instruction by the at least one first processing device, finally implementing control of the execution object by the control device, and therefore, implementing the voice control method by the control device can overcome the user and the execution object The problem of speech loss caused by the distance between the two can overcome the problem of speech loss caused by the distance between the user and the control device. Obviously, the voice control method can realize voice control of the execution object anytime and anywhere, and improve The flexibility of voice control.
  • the embodiment of the present invention further provides a first processing device, where the first processing device is applied to a voice control system as shown in FIG. 1 , where the voice control system includes a control device and multiple processes.
  • the first processing device is one of the plurality of processing devices. Referring to FIG. 8, the first processing device includes: a transceiver 801, a processor 802, a bus 803, a memory 804, and a microphone 805. among them,
  • the transceiver 801, the processor 802, the memory 804, and the microphone 805 are connected to each other through the bus 803; the bus 803 may be a peripheral component interconnect (PCI) bus. Or extend the industry standard architecture (EISA) bus.
  • PCI peripheral component interconnect
  • EISA industry standard architecture
  • the bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in Figure 8, but it does not mean that there is only one bus or one type of bus.
  • the transceiver 801 is configured to perform communication interaction with the control device in the voice control system.
  • the microphone 805 is configured to acquire a voice signal of a user
  • the processor 802 is configured to implement the voice control method as shown in FIG. 3, including:
  • Parsing the voice signal of the user obtaining an instruction corresponding to the voice signal of the user, and transmitting the instruction to the control device.
  • the processor 802 is further configured to: before acquiring the voice signal of the user:
  • the user's voice signal is started to be monitored.
  • the processor 802 is further configured to:
  • the memory 804 is configured to store a program or the like.
  • the program may include a program code
  • the program code includes computer operating instructions.
  • the memory 804 may include a random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage.
  • the processor 802 executes the application stored in the memory 804 to implement the above functions, thereby implementing the voice control method as shown in FIG.
  • the first processing device sends a voice signal or a corresponding command of the user to the control device, so that the control device acquires an instruction corresponding to the voice signal of the user, thereby determining The execution object of the instruction finally realizes the control of the execution object by the control device. Therefore, the voice control method of the first processing device can overcome the problem of speech loss caused by the distance between the user and the execution object. At the same time, the problem of speech loss caused by the distance between the user and the control device can be overcome. Obviously, the voice control method can implement voice control on the execution object anytime and anywhere, and the flexibility of voice control is improved.
  • the embodiment of the present invention further provides a voice control system.
  • the voice control system includes a control device 901 and multiple processing devices 902.
  • the plurality of processing devices 902 include at least one first processing device 9021 for implementing a voice control method as shown in FIG. 3, that is, acquiring a voice signal for use, and transmitting the voice signal of the user to the The control device 901, or parsing the voice signal of the user, obtaining an instruction corresponding to the voice signal of the user, and transmitting the instruction to the control device 901;
  • the control device 901 is configured to implement a voice control method as shown in FIG. 2, that is, an instruction corresponding to a voice signal of a user is obtained by using at least one first processing device 9021 of the multiple processing devices 902; An instruction to determine an execution object for which the instruction is directed; and when the execution object is the control device 901, performing an operation corresponding to the instruction; and when the execution object is a second one of the plurality of processing devices.
  • the device 9022 sends the instruction to the second processing device 9022, the instruction for notifying the second processing device 9022 to perform an operation corresponding to the instruction.
  • At least one first processing device in the system sends a voice signal or a corresponding command of the user to the control device, so that the control device acquires an instruction corresponding to the voice signal of the user.
  • the voice control system can overcome the problem of voice loss caused by the distance between the user and the execution object, and can overcome the voice cancellation caused by the distance between the user and the control device.
  • the problem of loss obviously, the voice control system can realize voice control of the execution object anytime and anywhere, and improve the flexibility of voice control.
  • a voice control method, apparatus, and system provided by the embodiment of the present invention, at least one first processing device in the system sends a voice signal or a corresponding command of the user to the control device,
  • the control device acquires an instruction corresponding to the voice signal of the user, thereby determining an execution object of the instruction, and finally implementing control of the execution object by the control device. Therefore, the voice control method can be overcome between the user and the execution object.
  • the problem of speech loss caused by the distance can overcome the problem of speech loss caused by the distance between the user and the control device.
  • the voice control method can realize voice control of the execution object anytime and anywhere, and improve the voice. Control flexibility.
  • embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the computer readable memory is stored in the computer readable memory.
  • the instructions in the production result include an article of manufacture of the instruction device that implements the functions specified in one or more blocks of the flowchart or in a flow or block of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Selective Calling Equipment (AREA)

Abstract

一种语音控制设备的方法、装置及系统,用以解决现有技术中对处理设备进行语音控制,灵活性较差的问题。该方法为:语音控制系统中的控制设备可以通过至少一个第一处理设备获取用户的语音信号对应的指令,从而确定所述指令的执行对象,实现对该执行对象的控制。由于所述控制设备可以通过所述至少一个第一处理设备获取所述指令,最终实现所述控制设备对执行对象的控制,因此,该语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。

Description

一种语音控制方法、装置及系统 技术领域
本申请涉及通信技术领域,尤其涉及一种语音控制方法、装置及系统。
背景技术
随着科学技术的快速发展,用户需要各种处理设备更智能化、服务化,即用户需要与处理设备直接通过语音交互,实现对所述处理设备的控制,然而,在实现用户对某处理设备的语音控制时,由于用户和该处理设备之间的距离会导致该处理设备接收不到语音信号或接收到的语音信号较小,导致语音控制失败。
例如,在智能家居场景中的各种家庭设备,如电冰箱、洗衣机、电视机,均支持语音交互功能,若用户对电冰箱实现语音控制,则需要移动到电冰箱附近进行语音交互。
显然,传统的方法实现对处理设备的语音控制时,无法克服用户与处理设备之间的距离造成的语音信号消损的问题,灵活性较差。
发明内容
本发明实施例提供了一种语音控制方法、装置及系统,用以解决现有技术中对处理设备进行语音控制,灵活性较差的问题。
一方面,本发明实施例提供了一种语音控制方法,该方法应用于语音控制系统,所述语音控制系统中包括控制设备和多个处理设备,该方法包括:
所述控制设备通过所述多个处理设备中的至少一个第一处理设备获取用户的语音信号对应的指令;然后根据所述指令,确定所述指令针对的执行对象;当所述执行对象为所述控制设备时,所述控制设备执行所述指令对应的操作;当所述执行对象为所述多个处理设备中的第二处理设备时,所述控制设备向所述第二处理设备发送所述指令,所述指令用于通知所述第二处理设 备执行所述指令对应的操作。
采用上述方法,语音控制系统中的控制设备可以通过至少一个第一处理设备获取用户的语音信号对应的指令,从而确定所述指令的执行对象,实现对该执行对象的控制。由于所述控制设备可以通过所述至少一个第一处理设备获取所述指令,最终实现所述控制设备对执行对象的控制,因此,该语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
在一个可能的设计中,在所述控制设备通过至少一个第一处理设备获取用户的语音信号对应的指令之前,所述控制设备确定所述至少一个第一处理设备;并所述控制设备向所述至少一个第一处理设备发送语音输入开启指令,所述语音输入开启指令用于通知所述至少一个第一处理设备开始监听用户的语音信号。
采用上述方法,所述控制设备确定当前语音控制系统中有可能在当前时刻接收到用户的语音信号的所述至少一个第一处理设备,然后所述控制设备开启确定的处理设备的语音输入功能,避免了所述至少一个第一处理设备由于长时间启动语音解析功能造成的功耗,以及避免了所述语音控制系统中除所述至少一个处理设备以外的其他处理设备由于启动语音解析功能造成的功耗。
在一个可能的设计中,所述控制设备确定所述至少一个第一处理设备,包括:
所述控制设备根据接收到的所述至少一个第一处理设备发送的第一消息确定所述至少一个第一处理设备,所述第一消息是所述至少一个第一处理设备在当前时刻确定能够收到用户的语音信号时发送的;或者,
所述控制设备获取所述用户的物理位置以及所述多个处理设备的物理位置;所述控制设备确定所述多个处理设备中每个处理设备的物理位置与所述 用户的物理位置之间的距离;所述控制设备在所述多个处理设备中,筛选出物理位置与所述用户的物理位置之间的距离小于第一设定距离阈值的所述至少一个第一处理设备;或者,
所述控制设备在所述多个处理设备中,筛选出处于待机状态或运行状态的所述至少一个第一处理设备。
通过上述几种方式,所述控制设备可以确定所述至少一个第一处理设备,进而可以通知所述至少一个第一处理设备开始监听用户的语音信号。
可选的,所述控制设备获取所述用户的物理位置,包括:
所述控制设备获取用户定位设备发送的定位指示信息,所述定位指示信息用于通知所述控制设备所述用户的物理位置与所述用户定位设备的物理位置之间的距离小于第二设定距离阈值;所述控制设备获取所述用户定位设备的物理位置,将所述用户定位设备的物理位置作为所述用户的物理位置;或者,
所述控制设备接收所述多个处理设备中的第三处理设备发送的所述用户的物理位置,所述用户的物理位置为所述第三处理设备确定的。
通过上述方法,所述控制设备可以准确地确定所述用户的物理位置,进而可以保证所述控制设备可以确定所述至少一个第一处理设备。
可选的,所述控制设备通过所述至少一个第一处理设备获取用户的语音信号对应的指令,包括:
所述控制设备接收所述至少一个第一处理设备发送的所述指令,所述指令为所述至少一个第一处理设备监听到所述用户的语音信号后,对所述用户的语音信号进行解析获得的;或者
所述控制设备接收所述至少一个第一处理设备发送的所述用户的语音信号,所述用户的语音信号为所述至少一个第一处理设备监听到的;所述控制设备对所述用户的语音信号进行解析得到所述指令。
通过上述方法,所述控制设备才能得到所述用户的语音信号对应的指令,从而确定所述指令针对的执行对象,实现对对执行对象的控制。
可选的,所述控制设备根据所述指令,确定所述指令针对的执行对象,包括:
所述控制设备确定在所述指令中包含的执行对象信息,根据所述执行对象信息确定所述执行对象;或者
所述控制设备确定所述指令对应的操作,所述控制设备确定具有执行所述指令对应的操作功能的所述执行对象;或者
所述控制设备确定所述指令对应的操作,所述控制设备确定具有执行所述指令对应的操作功能、且位于设定空间范围内的所述执行对象,其中,所述用户的物理位置在所述设定空间范围(例如所述用户所在房间)内。
通过上述方法,所述控制设备可以准确地确定所述指令针对的执行对象。
另一方面,本发明实施例提供了一种语音控制方法,该方法应用于语音控制系统,所述语音控制系统中包括控制设备和多个处理设备,该方法包括:
所述多个处理设备中的第一处理设备获取用户的语音信号;
所述第一处理设备将所述用户的语音信号发送至所述控制设备;或者
所述第一处理设备将所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令,并将所述指令发送至所述控制设备。
采用上述方法,所述第一处理设备将用户的语音信号或对应的指令发送给控制设备,使所述控制设备获取所述用户的语音信号对应的指令,从而确定所述指令的执行对象,最终实现所述控制设备对执行对象的控制,因此,该语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
在一个可能的设计中,在所述第一处理设备获取用户的语音信号之前,所述第一处理设备接收所述控制设备发送的语音输入开启指令;并根据所述语音输入开启指令,开始监听用户的语音信号。
采用上述方法,所述第一处理设备在只有在接收到语音输入开启指令后, 才开始监听用户的语音信号,避免所述第一处理设备由于长时间启动语音解析功能造成的功耗。
在一个可能的设计中,在所述第一处理设备获得所述用户的语音信号对应的指令后,所述第一处理设备根据所述指令,确定所述指令针对的至少两个执行对象,在确定所述至少两个执行对象中包含所述第一处理设备时,所述第一处理设备执行所述指令对应的操作。
采用上述方法,所述第一处理设备在解析得到所述用户的语音信号对应的指令时,可以继续判定自身是否为所述指令对应一个执行对象,若是,则直接执行该指令对应的操作,避免将所述指令发送给所述控制设备,以及所述控制设备下发所述指令给所述第一处理设备这个过程,缩短了所述第一处理设备执行所述指令对应的操作的时延,提高了用户的体验。
又一方面,本发明实施例还提供了一种控制设备,该控制设备具有实现上述方法实例中控制设备行为的功能。所述功能可以通过硬件实现,也可以通过硬件执行相应的软件实现。所述硬件或软件包括一个或多个与上述功能相对应的模块。
在一种可能的设计中,所述控制设备的结构中包括获取单元、处理单元和发送单元,这些单元可以执行上述方法示例中的相应功能,具体参见方法示例中的详细描述,此处不做赘述。
在一种可能的设计中,所述控制设备的结构中包括收发器、处理器、总线以及存储器,所述收发器用于与语音控制系统中的处理设备进行通信交互,所述处理器被配置为支持控制设备执行上述方法中相应的功能。所述存储器与所述处理器耦合,其保存所述控制设备必要的程序指令和数据。
又一方面,本发明实施例还提供了一种第一处理设备,该第一处理设备具有实现上述方法实例中第一处理设备行为的功能。所述功能可以通过硬件实现,也可以通过硬件执行相应的软件实现。所述硬件或软件包括一个或多个与上述功能相对应的模块。
在一种可能的设计中,所述第一处理设备的结构中包括获取单元、第一 发送单元,或者包括获取单元、处理单元和第二发送单元,这些单元可以执行上述方法示例中的相应功能,具体参见方法示例中的详细描述,此处不做赘述。
在一种可能的设计中,所述第一处理设备的结构中包括收发器、处理器、总线、存储器以及麦克,所述收发器用于与语音控制系统中的控制设备进行通信交互,所述麦克用于获取用户的语音信号,所述处理器被配置为支持第一处理设备执行上述方法中相应的功能。所述存储器与所述处理器耦合,其保存所述第一处理设备必要的程序指令和数据。
又一方面,本发明实施例提供了一种语音控制系统,该系统包括控制设备和多个处理设备,所述多个处理设备中包括至少一个第一处理设备。
本发明实施例中,语音控制系统中的控制设备可以通过至少一个第一处理设备获取用户的语音信号对应的指令,从而确定所述指令的执行对象,实现对该执行对象的控制。由于所述控制设备可以通过所述至少一个第一处理设备获取所述指令,最终实现所述控制设备对执行对象的控制,因此,该语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
附图说明
图1为本发明实施例提供的一种语音控制系统的架构图;
图2为本发明实施例提供的一种语音控制方法的流程图;
图3为本发明实施例提供的另一种语音控制方法的流程图;
图4为本发明实施例提供的一种语音控制方法的示例流程图;
图5为本发明实施例提供的一种控制设备的结构图;
图6A为本发明实施例提供的一种第一处理设备的结构图;
图6B为本发明实施例提供的一种第一处理设备的结构图;
图7为本发明实施例提供的另一种控制设备的结构图;
图8为本发明实施例提供的另一种第一处理设备的结构图;
图9为本发明实施例提供的一种语音控制系统的示意图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚,下面将结合附图对本发明作进一步地详细描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例,都属于本发明保护的范围。
本发明实施例提供一种语音控制方法、装置及系统,用以解决现有技术中对处理设备进行语音控制,灵活性较差的问题。其中,方法和装置是基于同一发明构思的,由于方法及装置解决问题的原理相似,因此装置与方法的实施可以相互参见,重复之处不再赘述。
采用本发明技术方案,语音控制系统中包括控制设备,该控制设备可以通过至少一个第一处理设备获取用户的语音信号对应的指令,从而确定所述指令的执行对象,实现对该执行对象的控制。由于所述控制设备可以通过所述至少一个第一处理设备获取所述指令,最终实现所述控制设备对执行对象的控制,因此,该语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
以下,对本申请中的部分用语进行解释说明,以便与本领域技术人员理解。
语音控制系统,其中包括控制设备和多个处理设备,所述控制设备具有语音输入功能,和/或,语音解析功能,所述多个处理设备也具有语音输入功能,和/或,语音解析功能。用户可以通过发出的语音信号,实现对该语音控 制系统中的设备的控制。在不同的应用场景中,所述语音控制系统中的控制设备和处理设备可以不同。例如在智能家居场景中,处理设备可以为电冰箱、洗衣机、电视机、家居照明设备等各种智能家居,所述控制设备为家用计算机。
用户的语音信号,即用户发出的声音,本发明涉及的用户的语音信号是用户在控制所述语音控制系统中的设备时,发出的期望该设备执行某些操作的声音,用户的语音信号的物理实质为人类发出的声波,是一种连续变化的模拟信号。
语音输入功能,即可以监听用户的语音信号,并在监听到用户的语音信号时,提取该用户的语音信号的功能。所述语音控制系统中的控制设备或处理设备是通过麦克实现所述语音输入功能的。
语音解析功能,即可以对用户的语音信号进行识别解析,获得用户的语音信号对应的指令的功能。该指令即通知用户希望控制的设备(执行对象),执行用户期望的某些操作。所述语音控制系统中的控制设备或处理设备是通过语音识别模块实现所述语音输入功能的。
控制设备,可以对所述语音控制系统中的处理设备进行控制和管理,例如,向某处理设备发送用户的语音信号对应的指令,使该处理设备执行所述指令对应的操作;向该处理设备发送语音输入开启指令,控制该处理设备启动语音输入功能,开始监听用户的语音信号。
处理设备,可以接收控制设备的各种指令,并执行指令对应的操作,且具有语音输入功能(即包含麦克)的设备。
语音输入开启指令,为控制设备向所述语音控制系统中的处理设备发送的,可以控制该处理设备启动语音输入功能,开始监听用户的语音信号。
第一处理设备,为所述多个处理设备中接收到用户的语音信号的处理设备。
第二处理设备,为所述多个处理设备中用户希望控制的设备(执行对象)。
第三处理设备,为所述多个处理设备中可以确定用户的物理位置的处理 设备。
用户定位设备,为所述语音控制系统中携带在用户身上的便携式设备,用于对用户进行定位。所述用户定位设备可以是手机等用户经常会携带的设备,或者智能手表、手环等可穿戴设备,所述用户定位设备具有运动传感器检测、生理检测(如脉率、血压、血氧或血糖等检测)可以通过上述功能检测所述用户定位设备是否携带在用户身上,从而确定用户与所述用户定位设备的物理位置一致;所述用户定位设备还可以为放置到固定位置的检测设备,用来判定用户是否在附近,所述用户定位设备具有摄像检测或者红外线检测功能时,通过是否可以拍摄到用户,是否检测到用户,判定用户是否在附近,或者通过判定所述用户的物理位置与所述用户定位设备的物理位置之间的距离与设定第二距离阈值的大小,确定用户是否在附近。当所述用户定位设备确定用户与所述用户定位设备的物理位置一致或用户是在所述用户定位设备附近(所述用户的物理位置与所述用户定位设备的物理位置之间的距离小于设定第二距离阈值)时,向所述语音控制系统中的所述控制设备和/或所述多个处理设备发送定位指示信息。
定位指示信息,为所述用户定位设备确定用户的物理位置与所述用户定位设备的物理位置之间的距离小于设定第二距离阈值时,向所述语音控制系统中的所述控制设备和/或所述多个处理设备发送的,用于通知所述控制设备和/或所述多个处理设备可以将所述用户定位设备的物理位置作为用户的物理位置。
第一消息,为所述语音控制系统中的处理设备在判定自身在用户附近时,或者通过红外线检测、摄像检测或体温检测等功能检测到用户时,确定自身可以在当前时刻(即用户的物理位置不变的情况下)能够接收到用户的语音信号时发送的。
第一设定距离阈值,用于判定用户是否在处理设备的附近(或该处理设备在用户附近),进而判定该处理设备是否能够接收到用户的语音信号。当一处理设备的物理位置与用户的物理位置之间的距离小于第一设定距离阈值 时,可以判定用户在该处理设备附近,从而该处理设备能够接收到用户的语音信号。所述第一设定距离阈值的取值一般为可以造成语音信号消损的距离,例如5m、3m等。
第二设定距离阈值,用于判定用户是否在用户定位设备的附近,即是否可以用户定位设备的物理位置作为用户的物理位置。当所述用户定位设备确定用户的物理位置与所述用户定位设备的物理位置之间的距离小于第二设定距离阈值时,所述用户定位设备向所述语音控制系统中的所述控制设备和/或所述多个处理设备定位指示信息。
多个,是指两个或两个以上。
和/或,描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。
另外,需要理解的是,在本申请的描述中,“第一”、“第二”等词汇,仅用于区分描述的目的,而不能理解为指示或暗示相对重要性,也不能理解为指示或暗示顺序。
为了更加清晰的描述本发明实施例的技术方案,下面结合图1,对本发明实施例可能的语音控制系统的架构进行说明。图1示出了本发明实施例的一种可能的系统的架构,该系统中包括:控制设备101以及多个处理设备102,其中,
控制设备101,用于通过所述多个处理设备102中的部分或全部处理设备102,获取用户的语音信号对应的指令,并根据所述指令,确定执行对象,当所述执行对象是自身时,所述控制设备101执行所述指令对应的操作;当所述执行对象是所述多个处理设备102中的某个处理设备102时,所述控制设备101向该处理设备102发送指令,使该处理设备102执行所述指令对应的操作,从而实现对执行对象的控制;
所述处理设备102,为具有语音输入功能的设备,即处理设备102可以监听用户的语音信号。在一个处理设备102开启语音输入功能后监听到用户的 语音信号时,可选的,该处理设备102可以将监听到的所述用户的语音信号发送给所述控制设备101;可选的,在该处理设备102具有语音解析功能时,该处理设备102还可以对所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令,并将解析得到的所述指令发送给所述控制设备101。其中,当该处理设备102可以将监听到的所述用户的语音信号发送给所述控制设备101的情况下,所述控制设备101也具有语音解析功能,在接收到所述用户的语音信号后,对所述用户的语音信号进行解析,获取所述用户的语音信号对应的指令。
可选的,由于所述控制设备101启动语音解析功能后,会造成所述控制设备101功耗增加,为了减少控制设备101由于长时间开启语音解析功能造成的功耗,所述控制设备101可以在接收到用户的指令后,启动自身的语音解析功能,或者在接收到用户通过所述多个处理设备102中任意一个或多个处理设备102发送的指令后,启动自身的语音解析功能,所述控制设备101还可以在设定时间内开启语音解析功能。
同样的,为了降低所述多个处理设备102中每个处理设备102由于长时间启动语音输入功能造成的功耗,每个处理设备102也可以是接收到用户的指令后,启动自身的语音解析功能;或者所述控制设备101在确定所述多个处理设备102中某些处理设备102有可能在当前时刻接收到用户的语音信号时,向这些处理设备102发送语音输入开启指令,启动这些处理设备102的语音输入功能。
可选的,为了降低具有语音解析功能的处理设备102由于长时间启动语音解析功能造成的功耗,处理设备102可以在通过上述方式开启语音输入功能的同时开启语音解析功能。
可选的,所述控制设备101确定有可能在当前时刻接收到用户的语音信号的处理设备102,包括以下两种方式:
第一种方式:在所述控制设备101可以确定用户的物理位置以及所述多个处理设备102的物理位置的情况下,所述控制设备101可以在所述多个处 理设备102中筛选出物理位置与所述用户的物理位置之间的距离小于第一设定距离阈值的处理设备102,作为有可能在当前时刻接收到用户的语音信号的处理设备102;
第二种方式:在所述控制设备101无法确定用户的物理位置时,所述控制设备101可以在所述多个处理设备102中筛选出处于运行状态的处理设备102,或处于待机状态的处理设备102,或者筛选出处于运行状态或待机状态的处理设备102,将筛选出的处理设备102作为有可能在当前时刻接收到用户的语音信号的处理设备102;
第三种方式:在所述多个处理设备102中的处理设备102可以判定自身是否可以在当前时刻接收到用户的语音信号的情况下,所述多个处理设备102中,判定自身可以在当前时刻接收到用户的语音信号的处理设备102向所述控制设备101发送第一消息,通知所述控制设备101,所述控制设备101可以通过接收的第一消息,确定有可能在当前时刻接收到用户的语音信号的处理设备102。
在第三种方式中,一个处理设备102可以通过以下几种方法判定自身是否可以在当前时刻接收到用户的语音信号:
在该处理设备102可以确定用户的物理位置的情况下,该处理设备102判断自身与所述用户的物理位置之间的距离与第一设定距离阈值的大小;判定自身与所述用户的物理位置之间的距离小于第一设定距离阈值的处理设备102,向所述控制处理设备102发送第一消息,所述第一消息用于通知所述控制设备该语言处理设备102可以在当前时刻接收到用户的语音信号;
在该处理设备102具有红外线检测、摄像检测、体温检测等功能时,可以通过上述功能检测,若检测到用户时,即向所述控制处理设备102发送第一消息,所述第一消息用于通知所述控制设备101该处理设备102可以在当前时刻接收到用户的语音信号;
可选的,在该系统中还包括用户定位设备103,当用户与所述用户定位设备103的物理位置一致时,处理设备102还可以向所述用户定位设备103发 送无线信号,在所述处理设备102确定所述用户定位设备103能够接收到所述无线信号,或者确定所述无线信号的信号强度大于设定信号强度阈值时,判定该处理设备102可以在当前时刻接收到用户的语音信号;同理,所述处理设备102还可以通过接收所述用户定位设备103发送的无线信号,判定该处理设备102可以在当前时刻接收到用户的语音信号。
所述用户定位设备103可以是手机、智能手表、手环等用户经常会携带的设备,在以上描述中,所述控制设备101和任意一个处理设备102确定用户的物理位置,通常也是确定用户与所述用户定位设备103的物理位置一致,即当前时刻,用户携带了所述用户定位设备103。
可选的,所述用户定位设备103具有运动传感器检测、生理检测(如脉率、血压、血氧或血糖等检测)或者摄像检测等功能时,可以通过上述功能检测所述用户定位设备103是否携带在用户身上,从而确定用户与所述用户定位设备103的物理位置一致。当所述用户定位设备103判定用户与所述用户定位设备103的物理位置一致时,向所述控制设备101和所述多个处理设备102发送定位指示信息,通知所述用户的物理位置与所述用户定位设备的物理位置之间的距离小于第二设定距离阈值,这样,所述控制设备101和所述多个处理设备102可以将所述用户定位设备103的物理位置作为所述用户的物理位置。
所述控制设备101与所述多个处理设备102之间可以直接通信,也可以通过桥接设备或路由设备通信,还可以通过其他组网方式通信,本发明对此不做限定。所述控制设备101与所述多个处理设备102之间通信使用的各种通信技术,如无线保真(Wireless Fidelity,WiFi)技术、蓝牙(Bluetooth)技术、以太网技术、紫蜂(ZigBee)技术、通用即插即用(Universal Plug and Play,UPnP)技术,以及数字生活网络联盟(Digital Living Network Alliance,DLNA)技术等,本发明对此不做限定。
所述控制设备101与所述用户定位设备103之间,以及所述多个处理设备102与所述用户定位设备103之间,均可以直接通信,或通过桥接设备或 路由设备通信,还可以通过其他组网方式通信,本发明对此不做限定。所述控制设备101与所述用户定位设备103之间通信使用的通信技术,以及所述多个处理设备102与所述用户定位设备103之间通信使用的通信技术,可以但不限于WiFi技术、蓝牙技术等,本发明对此不做限定。
本发明实施例提供了一种语音控制方法,适用于如图1所示的语音控制系统中,该语音控制系统中包括控制设备和多个处理设备。参阅图2所示,该方法的具体流程包括:
步骤201:控制设备通过所述多个处理设备中的至少一个第一处理设备获取用户的语音信号对应的指令。
由于在步骤201中,所述控制设备是通过所述至少一个第一处理设备获取所述用户的语音信号对应的指令的,因此,所述至少一个第一处理设备的语音输入功能是开启的。
可选的,当前语音控制系统中的所有处理设备(包括所述至少一个第一处理设备)在连接电源时即开启语音输入功能。然而,在当前时刻某些处理设备不可能接收到用户的语音信号,因此长时间开启这些处理设备的语音输入功能,会增加过多的功耗。
可选的,所述控制设备确定当前语音控制系统中有可能在当前时刻接收到用户的语音信号的处理设备,然后所述控制设备开启确定的处理设备的语音输入功能,避免了处理设备由于长时间启动语音解析功能造成的功耗。
可选的,在步骤201之前,所述方法还包括:
所述控制设备确定所述至少一个第一处理设备;
所述控制设备向所述至少一个第一处理设备发送语音输入开启指令,所述语音输入开启指令用于通知所述至少一个第一处理设备开始监听用户的语音信号。所述至少一个处理设备接收到所述语音输入开启指令后,开始执行监听用户的语音信号的操作。
在实际场景中,所述控制设备在步骤201之前,只能确定有可能在当前时刻接收到用户的语音信号的n个处理设备(即在用户附近的处理设备,当 用户发送语音信号时,可以清楚准确地接收到用户的语音信号的处理设备),而无法确定一定会接收到用户的语音信号的所述至少一个第一处理设备,其中,n为正整数。然而,所述至少一个第一处理设备包含在所述n个设备中,因此,所述控制设备是通过确定所述n个处理设备,从而确定所述至少一个第一处理设备的。显然,所述控制设备确定所述n个处理设备的方法与确定所述至少一个第一处理设备的方法相同,此处仅以确定所述至少一个第一处理设备为例进行说明,所述控制设备确定所述n个处理设备的方法不再赘述。
可选的,在实际应用中,所述控制设备可以在指定时刻,或收到指定命令时,确定所述至少一个第一处理设备。
其中,可选的,所述控制设备确定所述至少一个第一处理设备,包括以下几种方式:
第一种方式:当前语音控制系统中的所述多个处理设备可以检测自身是否可以在当前时刻接收到用户的语音信号的情况下,所述多个处理设备中检测到自身可以在当前时刻接收到用户的语音信号时,向所述控制设备发送第一消息;所述控制设备根据接收到的所述第一消息确定所述至少一个第一处理设备,所述第一消息是所述至少一个第一处理设备在当前时刻能够收到用户的语音信号时发送的;
具体的,在第一种方式中,一个处理设备检测自身可以在当前时刻接收到用户的语音信号,可以通过以下方法:
在该处理设备可以确定用户的物理位置的情况下,该设备判断自身与所述用户的物理位置之间的距离与第一设定距离阈值的大小;在判定自身与所述用户的物理位置之间的距离小于第一设定距离阈值时,确定自身可以在当前时刻接收到用户的语音信号;
在该处理设备具有红外线检测、摄像检测、体温检测等功能时,可以通过上述功能检测用户,若检测到用户时,确定自身可以在当前时刻接收到用户的语音信号;
在该系统中还包括用户定位设备,且所述用户的物理位置与所述用户定 位设备的物理位置之间的距离小于第二设定距离阈值(例如用户携带所述用户定位设备)时,该处理设备还可以向所述用户定位设备发送无线信号,在该处理设备确定所述用户定位设备能够接收到所述无线信号,或者确定所述无线信号的信号强度大于设定信号强度阈值时,该处理设备确定自身可以在当前时刻接收到用户的语音信号;或者所述用户定位设备广播无线信号,在该处理设备接收到所述无线信号,或者确定接收的无线信号的信号强度大于设定信号强度阈值时,该处理设备确定自身可以在当前时刻接收到用户的语音信号。
总之,该处理设备通过不限于以上举例的方法,判定自身在用户附近,即可确定自身可以在当前时刻接收到用户的语音信号。
第二种方式:所述控制设备获取所述用户的物理位置以及所述多个处理设备的物理位置;所述控制设备确定所述多个处理设备中每个处理设备的物理位置与所述用户的物理位置之间的距离;所述控制设备在所述多个处理设备中,筛选出物理位置与所述用户的物理位置之间的距离小于第一设定距离阈值的所述至少一个第一处理设备;
其中,本发明涉及的物理位置可以为经纬度信息,也可以为指定空间范围内的坐标信息,本发明对此不做限定。
在第二种方式中,可选的,所述控制设备获取所述用户的物理位置,包括:
所述用户定位设备检测所述用户的物理位置与所述用户定位设备的物理位置之间的距离小于第二设定距离阈值时,向所述控制设备发送定位指示信息,所述定位指示信息用于通知所述控制设备所述用户的物理位置与所述用户定位设备的物理位置之间的距离小于第二设定距离阈值(即可以用所述用户定位设备的物理位置作为所述用户的物理位置;所述控制设备获取所述用户定位设备发送的定位指示信息后,所述控制设备获取所述用户定位设备的物理位置,将所述用户定位设备的物理位置作为所述用户的物理位置;其中,所述用户定位设备检测所述用户的物理位置与所述用户定位设备的物理位置 之间的距离小于第二设定距离阈值时,可以通过运动传感器检测、生理检测,和/或,摄像检测等功能,进行检测,通常情况下,所述用户定位设备在检测到所述用户的物理位置与所述用户定位设备的物理位置之间的距离小于第二设定距离阈值时,不仅向所述控制设备发送所述定位指示信息,还可以向当前语音控制系统中的处理设备发送所述定位指示信息,通知处理设备所述用户与所述用户定位设备的物理位置一致;
所述控制设备接收所述多个处理设备中的第三处理设备发送的所述用户的物理位置,所述用户的物理位置为所述第三处理设备确定的,所述第三处理设备可以在测量到用户的物理位置时,向所述控制设备上报。
第三种方式:在所述控制设备未获取到所述用户定位设备发送的定位指示信息,且未获取到所述用户的物理位置时,所述控制设备在所述多个处理设备中,筛选出处于待机状态或运行状态的所述至少一个第一处理设备。
在步骤201中,所述控制设备获取所述指令,包括以下两种方式:
第一种方式:所述至少一个第一处理设备不仅具有语音输入功能,还具有语音解析功能,因此,所述至少一个第一处理设备在监听到所述用户的语音信号后,对所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令,并将所述指令发送至所述控制设备;所述控制设备接收所述至少一个第一处理设备发送的所述指令。
第二种方式:所述控制设备接收所述至少一个第一处理设备发送的所述用户的语音信号,所述用户的语音信号为所述至少一个第一处理设备监听到的;所述控制设备对所述用户的语音信号进行解析,得到所述指令。
在第一种方式中,由于所述至少一个第一处理设备具有语音解析功能,且该语音解析功能只有在接收到用户的语音信号才可以进行语音解析,为了减少所述至少一个第一处理设备的语音解析功能造成的功耗,可选的,所述至少一个第一处理设备可以在接收到所述控制设备的语音输入开启指令,启动语音输入功能的同时启动语音解析功能;或者所述控制设备向所述至少一个第一处理设备发送语音解析开启指令,所述至少一个第一处理设备在接收 到所述语音解析开启指令后,启动语音解析功能。
可选的,在所述至少一个第一处理设备中任意一个第一处理设备解析获得所述指令后,会判定所述指令针对的执行对象是否包括自身,若包含自身和其他处理设备或所述控制设备时,则该第一处理设备可以执行所述指令对应的操作,并将所述指令发送至所述控制设备,所述控制设备在接收到所述指令后,确定所述指令针对的执行对象时,将该第一处理设备排除。
在第二种方式中,在所述控制设备对所述用户的语音信号进行解析之前,所述方法还包括:所述控制设备启动所述控制设备的语音解析功能。
可选的,所述控制设备启动自身的语音解析功能可以是连接电源时;或者
为了减少所述控制设备的语音解析功能造成的功耗,在接收到语音解析开启指令后,所述控制设备才启动语音解析功能。
步骤202:所述控制设备根据所述指令,确定所述指令针对的执行对象。
在步骤202中,所述控制设备确定一个执行对象,可以但不限于以下方法:
第一种方法:所述控制设备确定在所述指令中包含的执行对象信息,根据所述执行对象信息确定所述执行对象;例如,所述指令为“打开空调”,所述控制设备可以确定所述执行对象信息为“空调”,所述控制设备可以根据“空调”,确定执行对象为当前语音控制系统中的空调。
第二种方法:所述控制设备确定所述指令对应的操作,所述控制设备确定具有执行所述指令对应的操作功能的所述执行对象;例如,所述指令为“煮饭”,所述控制设备在当前语音控制系统中具有“煮饭”功能的执行对象,如智能电饭煲。
第三种方法:所述控制设备确定所述指令对应的操作,所述控制设备确定具有执行所述指令对应的操作功能、且位于设定空间范围内的所述执行对象,其中,所述用户的物理位置在所述设定空间范围内;例如,所述指令为“开灯”,而房间过多的时候,所述控制设备选择用户所在的房间的灯。
其中,在所述控制设备在通过第三种方法确定所述执行对象时,所述控制设备需要确定所述用户的物理位置,所述控制设备获取所述用户的物理位置已经在步骤201中描述,此处不再赘述。
步骤203:当所述执行对象为所述控制设备时,所述控制设备执行所述指令对应的操作;当所述执行对象为所述多个处理设备中的第二处理设备时,所述控制设备向所述第二处理设备发送所述指令,所述指令用于通知所述第二处理设备执行所述指令对应的操作。
采用本发明实施例的方法,语音控制系统中包括控制设备,该控制设备可以通过至少一个第一处理设备获取用户的语音信号对应的指令,从而确定所述指令的执行对象,实现对该执行对象的控制。由于所述控制设备可以通过所述至少一个第一处理设备获取所述指令,最终实现所述控制设备对执行对象的控制,因此,该语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
本发明实施例提供了一种语音控制方法,适用于如图1所述的语音控制系统中,该语音控制系统中包括控制设备和多个处理设备。参阅图3所示,该方法的具体流程包括:
步骤301:所述多个处理设备中的第一处理设备获取用户的语音信号。
其中,所述第一处理设备为图1所示的系统中的任意一个处理设备102,且该第一处理设备为上述实施例中,所述至少一个第一处理设备中的其中一个第一处理设备。
由于所述第一处理设备可以获取到用户的语音信号,因此,所述第一处理设备的语音输入功能的开启的。
可选的,所述第一处理设备在连接电源是即开启语音输入功能,但是这样会增加所述第一处理设备的功耗。
为了降低所述第一处理设备的功耗,可选的,所述第一处理设备通过控 制设备开启语音输入功能,即在所述第一处理设备获取用户的语音信号之前,所述方法还包括:
所述第一处理设备接收所述控制设备发送的语音输入开启指令;
所述第一处理设备根据所述语音输入开启指令,开始监听用户的语音信号。
步骤302:所述第一处理设备将所述用户的语音信号发送至控制设备;或者所述第一处理设备将所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令,并将所述指令发送至所述控制设备。
在步骤302的第一种方案中,在所述第一处理设备将所述用户的语音信号发送给所述控制设备后,所述控制设备对所述用户的语音信号进行解析,获得对应的指令,以及确定所述指令的针对的执行对象,从而实现对该执行对象的控制。
在步骤302的第二种方案中,在所述第一处理设备具有语音解析功能的情况下,所述第一处理设备获取所述用户的语音信号后,直接对所述用户的语音信号进行解析,分担了所述控制设备的语音解析的工作,降低了所述控制设备的工作负载。
在第二种方案中,在所述第一处理设备将所述用户的语音信号进行解析之前,所述方法还包括:所述第一处理设备启动所述第一处理设备的语音解析功能。可选的,所述第一处理设备可以在启动语音输入功能的时,启动所述第一处理设备的语音解析功能。
可选的,在第二种方案中,在所述第一处理设备获得所述用户的语音信号对应的指令后,所述方法还包括:
所述第一处理设备根据所述指令,确定所述指令针对的至少两个执行对象,在确定所述至少两个执行对象中包含所述第一处理设备时,所述第一处理设备执行所述指令对应的操作。
所述第一处理设备在解析得到所述用户的语音信号对应的指令时,可以继续判定自身是否为所述指令对应一个执行对象,若是,则直接执行该指令 对应的操作,避免将所述指令发送给所述控制设备,以及所述控制设备下发所述指令给所述第一处理设备这个过程,缩短了所述第一处理设备执行所述指令对应的操作的时延,提高了用户的体验。
当所述第一处理设备判定所述指令对应的执行对象除了所述第一处理设备以外还包括其他处理设备或所述控制设备时,则需要将所述指令发送给所述控制设备,使所述控制设备确定除所述第一处理设备以外的其他执行对象,进而实现所述控制设备对其他执行对象的控制。
采用本发明实施例提供的语音控制方法,第一处理设备将用户的语音信号或对应的指令发送给控制设备,使所述控制设备获取所述用户的语音信号对应的指令,从而确定所述指令的执行对象,最终实现所述控制设备对执行对象的控制,因此,该语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
基于以上实施例,参阅图4所示,本发明实施例还提供了一种语音控制方法的示例,该实例可以应用于如图1所述的语音控制系统中,该示例的流程包括:
步骤401:用户定位设备判断自身的物理位置与用户的物理位置是否小于第二设定距离阈值,若是,则执行步骤402或步骤405,否则执行步骤407或步骤408。
所述用户定位设备在执行步骤401时,可以检测自身是否携带在用户身上,即可以通过运动传感器检测、生理检测,和/或,摄像检测等功能,进行检测。例如,当所述用户定位设备支持支持运动传感器检测功能时,所述用户定位设备通过运动传感器来检测,当在设定时间内(例如10分钟)所述运动传感器检测到所述用户定位设备一直处于静止状态,则表示所述用户定位设备没有携带在用户身上,因为如果用户定位设备携带在用户身上时,用户不会一直处于静止状态,即使用户处于静止不动或者睡眠状态,也会有轻微 的动作,所述运动传感器也可以检测到运动。所述运动传感器可以为加速计、陀螺仪等。当所述用户定位设备检测到自身携带在用户身上时,则表示自身与用户的物理位置一致。
通常情况下,所述用户定位设备在检测到自身携带在用户身上时,不仅向所述控制设备发送所述定位指示信息,还可以向当前语音控制系统中的设备发送所述定位指示信息,通知这些设备可以通过所述用户定位设备的物理位置,确定所述用户的位置。
步骤402:用户定位设备向语音控制系统中的处理设备发送定位指示信息,所述定位指示信息用于通知语音控制系统中的处理设备所述用户定位设备的物理位置与用户的物理位置小于第二设定距离阈值。
通过步骤402,语音控制系统中的处理设备可以确定将所述用户定位设备的物理位置作为所述用户的物理位置,每个设备可以根据物理位置或无线信号判断自身是否在用户附近。
显然,在用户附近的处理设备在当前时刻能够接收到用户的信号。
步骤403:语音控制系统中每个处理设备根据物理位置或无线信号判断自身是否在用户附近;判定自身在用户附近的处理设备向所述控制设备发送第一消息,所述第一消息用于通知所述控制设备自身在当前时刻确定能够接收到用户的语音信号。
具体的,任意一个处理设备根据物理位置确定自身在用户附近:
该处理设备获取所述用户定位设备的物理位置,将所述用户定位设备的物理位置作为用户的物理位置;
该处理设备判断自身与所述用户的物理位置之间的距离与第一设定距离阈值的大小;
该处理设备在判定自身与所述用户的物理位置之间的距离小于第一设定距离阈值时,确定在用户附近。
具体的,任意一个处理设备根据无线信号确定自身在用户附近:
该处理设备向所述用户定位设备发送无线信号;在该处理设备确定所述 用户定位设备能够接收到所述无线信号,或者确定所述无线信号的信号强度大于设定信号强度阈值时,该处理设备确定自身在用户附近;或者
所述用户定位设备广播无线信号,在该处理设备接收到所述无线信号,或者确定接收的无线信号的信号强度大于设定信号强度阈值时,该处理设备确定自身在用户附近。
步骤404:控制设备根据接收的第一消息,确定语音控制系统中在用户附近的处理设备。
所述控制设备确定发送所述第一消息的处理设备为在用户附近的处理设备。
步骤405:用户定位设备向控制设备发送定位指示信息,所述定位指示信息用于通知语音控制系统中的处理设备所述用户定位设备的物理位置与用户的物理位置小于第二设定距离阈值。
通过步骤405,控制设备可以确定将所述用户定位设备的物理位置作为所述用户的物理位置。所述控制设备在确定所述用户的物理位置后,即可确定在所述用户附近的设备。
步骤406:所述控制设备根据物理位置确定语音控制系统中在用户附近的处理设备。
具体的,所述控制设备获取所述用户定位设备的物理位置,将所述用户定位设备的物理位置作为用户的物理位置;
所述控制设备获取语音控制系统中多个处理设备的物理位置;
所述控制设备确定所述多个处理设备中每个处理设备的物理位置与所述用户的物理位置之间的距离;
所述控制设备在所述多个设备中,筛选出物理位置与所述用户的物理位置之间的距离小于所述设定距离阈值的处理设备,筛选出的处理设备即为在用户附近的位置。
步骤407:控制设备确定语音控制系统中所有处于运行状态或待机状态的处理设备。
在用户定位设备与用户的物理位置不一致时,所述控制设备无法确定在用户附近的处理设备,因此,只能确定语音控制系统中所有可以打开语音输入功能的设备,即所有处于运行状态或待机状态的设备。
步骤408:语音控制系统中每个处理设备通过红外线检测、摄像检测或体温检测等功能检测用户;检测到用户的处理设备向所述控制设备发送第一消息,所述第一消息用于通知所述控制设备,自身在当前时刻确定能够接收到用户的语音信号。
在用户定位设备与用户的物理位置不一致时,语音控制系统中的每个处理设备无法通过物理位置或无线信号确定是否在用户附近,因此,还可以通过其他方式确定自身是否在用户附近。
例如,在某处理设备具有摄像功能,则在该处理设备拍摄到用户时,确定该处理设备在用户附近。
步骤409:所述控制设备向确定的n个处理设备发送语音输入开启指令,打开所述n个处理设备的语音输入功能。
所述控制设备打开确定的有可能接收到用户的语音信号的处理设备,避免将语音控制系统中所有的处理设备的语音输入功能打开,降低了其他处理设备开启语音输入功能造成的功耗。
步骤410:所述n个设备开始监听用户的语音信号,所述n个处理设备中至少一个第一处理设备监听到用户的语音信号。
步骤411:所述至少一个第一处理设备将所述用户的语音信号发送给所述控制设备。
步骤412:所述控制设备将所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令。
步骤413:所述至少一个第一处理设备将所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令。
步骤414:所述至少一个第一处理设备中每个第一处理设备确定所述指令针对的至少两个执行对象,在任意一个第一处理设备确定所述两个执行对象 中包含自身时,该第一处理设备执行所述指令对应的操作。
其中,步骤414为可选步骤,相应的,步骤420、步骤421以及步骤422也为可选步骤,当所述步骤414执行时,步骤420、步骤421以及步骤422也需要执行。
步骤415:所述至少一个第一处理设备将所述用户的语音信号对应的指令发送给所述控制设备。
步骤416:所述控制设备根据获得的所述指令,确定所述指令针对的至少一个执行对象。
所述控制设备确定所述至少一个执行对象中每个执行对象的方法,与以上实施例中的方法相同,此处不再赘述。
步骤417:所述控制设备确定所述至少一个执行对象的数目为1,且执行对象为所述控制设备时,所述控制设备执行所述指令对应操作。
步骤418:所述控制设备确定所述至少一个执行对象的数目大于1,且执行对象中包含所述控制设备以及至少一个第二处理设备时,所述控制设备执行所述指令对应的操作。
步骤419:所述控制设备确定所述至少一个执行对象为至少一个第二处理设备。
当步骤414不执行时,在执行完步骤418或步骤419后,直接执行步骤423。
步骤420:所述控制设备判断所述至少一个第二处理设备中是否包含已经执行所述指令对应的操作的第一处理设备,若包含,则执行步骤421或步骤422,否则执行步骤423。
步骤421:当所述至少一个第二处理设备的数目为1时,结束。
步骤422:当所述至少一个第二处理设备的数目大于1时,所述控制设备向所述至少一个第二处理设备中除该第一处理设备以外的其他第二处理设备发送所述指令。
步骤423:所述控制设备向所述至少一个第二处理设备发送所述指令。
步骤424:每个接收到所述指令的第二处理设备执行所述指令对应的操作。
采用本发明技术方案,语音控制系统中的控制设备可以通过至少一个第一处理设备获取用户的语音信号对应的指令,从而确定所述指令的执行对象,实现对该执行对象的控制。由于所述控制设备可以通过所述至少一个第一处理设备获取所述指令,最终实现所述控制设备对执行对象的控制,因此,该语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
基于以上实施例,本发明实施例还提供了一种控制设备,所述控制设备应用于如图1所示的语音控制系统,所述语音控制系统还包括多个处理设备,参阅图5所示,该控制设备500包括:获取单元501、处理单元502和发送单元503,其中,
获取单元501,用于通过所述多个处理设备中的至少一个第一处理设备获取用户的语音信号对应的指令;
处理单元502,用于根据所述指令,确定所述指令针对的执行对象;以及当所述执行对象为所述控制设备时,执行所述指令对应的操作;
发送单元503,用于当所述执行对象为所述多个处理设备中的第二处理设备时,向所述第二处理设备发送所述指令,所述指令用于通知所述第二处理设备执行所述指令对应的操作。
可选的,所述处理单元502还用于:
在所述获取单元501通过所述至少一个第一处理设备获取所述指令之前,确定所述至少一个第一处理设备;
所述发送单元503,还用于向所述至少一个第一处理设备发送语音输入开启指令,所述语音输入开启指令用于通知所述至少一个第一处理设备开始监听用户的语音信号。
可选的,所述获取单元501,还用于:
接收所述至少一个第一处理设备发送的第一消息,其中,所述第一消息是所述至少一个第一处理设备在当前时刻确定能够接收到用户的语音信号时发送的;或者
获取所述用户的物理位置以及所述多个处理设备的物理位置;
所述处理单元502,在确定所述至少一个第一处理设备时,具体用于:
在所述获取单元501接收所述至少一个第一处理设备发送的第一消息后,根据所述第一消息确定所述至少一个第一处理设备;或者,
在所述获取单元501获取所述用户的物理位置以及所述多个处理设备的物理位置后,确定所述多个处理设备中每个处理设备的物理位置与所述用户的物理位置之间的距离;并在所述多个处理设备中,筛选出物理位置与所述用户的物理位置之间的距离小于第一设定距离阈值的所述至少一个第一处理设备;或者,
在所述多个处理设备中,筛选出处于待机状态或运行状态的所述至少一个第一处理设备。
可选的,所述获取单元501,在获取所述用户的物理位置时,具体用于:
获取用户定位设备发送的定位指示信息,所述定位指示信息用于通知所述控制设备所述用户的物理位置与所述用户定位设备的物理位置之间的距离小于第二设定距离阈值;并获取所述用户定位设备的物理位置,将所述用户定位设备的物理位置作为所述用户的物理位置;或者,
接收所述多个处理设备中的第三处理设备发送的所述用户的物理位置,所述用户的物理位置为所述第三处理设备确定的。
可选的,所述获取单元501在通过所述至少一个第一处理设备获取用户的语音信号对应的指令时,具体用于:
接收所述至少一个第一处理设备发送的所述指令,所述指令为所述至少一个第一处理设备监听到所述用户的语音信号后,对所述用户的语音信号进行解析获得的;或者
接收所述至少一个第一处理设备发送的所述用户的语音信号,所述用户的语音信号为所述至少一个第一处理设备监听到的;以及对所述用户的语音信号进行解析得到所述指令。
可选的,所述处理单元502,在根据所述指令,确定所述指令针对的执行对象时,具体用于:
确定在所述指令中包含的执行对象信息,根据所述执行对象信息确定所述执行对象;或者
确定所述指令对应的操作,以及确定具有执行所述指令对应的操作功能的所述执行对象;或者
确定所述指令对应的操作,以及确定具有执行所述指令对应的操作功能、且位于设定空间范围内的所述执行对象,其中,所述用户的物理位置在所述设定空间范围内。
采用本发明实施例提供的控制设备,该控制设备可以通过至少一个第一处理设备获取用户的语音信号对应的指令,从而确定所述指令的执行对象,实现对该执行对象的控制。由于所述控制设备可以通过所述至少一个第一处理设备获取所述指令,最终实现所述控制设备对执行对象的控制,因此,通过所述控制设备实现语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
基于上述实施例,本发明实施例还提供了一种第一处理设备,所述第一处理设备应用于如图1所示的语音控制系统,所述语音控制系统中包括控制设备和多个处理设备,所述第一处理设备为所述多个处理设备中的一个,该第一处理设备的结构可以为两种,参阅图6A所示,在第一种结构中,所述第一处理设备600可以包括获取单元601、第一发送单元602;参阅如6B所示,在第二种结构中,所述第一处理设备600可以包括获取单元601,处理单元603和第二发送单元604,其中,
所述获取单元601,用于获取用户的语音信号;
所述第一发送单元602,用于将所述用户的语音信号发送至所述控制设备;
所述处理单元603,用于将所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令;
所述第二发送单元604,用于将所述指令发送至所述控制设备。
可选的,所述获取单元601,还用于:
在获取用户的语音信号之前,接收所述控制设备发送的语音输入开启指令;
根据所述语音输入开启指令,开始监听用户的语音信号。
可选的,所述处理单元603,还用于:
在获得所述用户的语音信号对应的指令后,根据所述指令,确定所述指令针对的至少两个执行对象,在确定所述至少两个执行对象中包含所述第一处理设备600时,执行所述指令对应的操作。
采用本发明实施例提供的第一处理设备,该第一处理设备将用户的语音信号或对应的指令发送给控制设备,使所述控制设备获取所述用户的语音信号对应的指令,从而确定所述指令的执行对象,最终实现所述控制设备对执行对象的控制,因此,采用所述第一处理设备的语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
需要说明的是,本发明实施例中对单元的划分是示意性的,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。在本申请的实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元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,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,简称ROM)、随机存取存储器(Random Access Memory,简称RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
基于以上实施例,本发明实施例还提供了一种控制设备,所述控制设备应用于如图1所示的语音控制系统,所述语音控制系统还包括多个处理设备,参阅图7所示,所述控制设备700包括:收发器701、处理器702、总线703以及存储器704,其中,
所述收发器701、所述处理器702和所述存储器704通过所述总线703相互连接;总线703可以是外设部件互连标准(peripheral component interconnect,简称PCI)总线或扩展工业标准结构(extended industry standard architecture,简称EISA)总线等。所述总线可以分为地址总线、数据总线、控制总线等。为便于表示,图7中仅用一条粗线表示,但并不表示仅有一根总线或一种类型的总线。
所述收发器701,用于与所述语音控制系统中的所述多个处理设备进行通信交互。
所述处理器702,用于实现如图2所示的语音控制方法,包括:
通过所述多个处理设备中的至少一个第一处理设备获取用户的语音信号对应的指令;
根据所述指令,确定所述指令针对的执行对象;
当所述执行对象为所述控制设备700时,执行所述指令对应的操作;当所述执行对象为所述多个处理设备中的第二处理设备时,向所述第二处理设备发送所述指令,所述指令用于通知所述第二处理设备执行所述指令对应的 操作。
可选的,所述处理器702,在通过至少一个第一处理设备获取用户的语音信号对应的指令之前,还用于:
确定所述至少一个第一处理设备;
向所述至少一个第一处理设备发送语音输入开启指令,所述语音输入开启指令用于通知所述至少一个第一处理设备开始监听用户的语音信号。
可选的,所述处理器702,在确定所述至少一个第一处理设备时,具体用于:
根据接收到的所述至少一个第一处理设备发送的第一消息确定所述至少一个第一处理设备,所述第一消息是所述至少一个第一处理设备在当前时刻确定能够收到用户的语音信号时发送的;或者,
获取所述用户的物理位置以及所述多个处理设备的物理位置;确定所述多个处理设备中每个处理设备的物理位置与所述用户的物理位置之间的距离;在所述多个处理设备中,筛选出物理位置与所述用户的物理位置之间的距离小于第一设定距离阈值的所述至少一个第一处理设备;或者,
在所述多个处理设备中,筛选出处于待机状态或运行状态的所述至少一个第一处理设备。
可选的,所述处理器702,在获取所述用户的物理位置时,具体用于:
获取用户定位设备发送的定位指示信息,所述定位指示信息用于通知所述控制设备700所述用户的物理位置与所述用户定位设备的物理位置之间的距离小于第二设定距离阈值;获取所述用户定位设备的物理位置,将所述用户定位设备的物理位置作为所述用户的物理位置;或者,
接收所述多个处理设备中的第三处理设备发送的所述用户的物理位置,所述用户的物理位置为所述第三处理设备确定的。
可选的,所述处理器702,在通过所述至少一个第一处理设备获取用户的语音信号对应的指令时,具体用于:
接收所述至少一个第一处理设备发送的所述指令,所述指令为所述至少 一个第一处理设备监听到所述用户的语音信号后,对所述用户的语音信号进行解析获得的;或者
接收所述至少一个第一处理设备发送的所述用户的语音信号,所述用户的语音信号为所述至少一个第一处理设备监听到的;对所述用户的语音信号进行解析得到所述指令。
可选的,所述处理器702,在根据所述指令,确定所述指令针对的执行对象时,具体用于:
确定在所述指令中包含的执行对象信息,根据所述执行对象信息确定所述执行对象;或者
确定所述指令对应的操作,确定具有执行所述指令对应的操作功能的所述执行对象;或者
确定所述指令对应的操作,确定具有执行所述指令对应的操作功能、且位于设定空间范围内的所述执行对象,其中,所述用户的物理位置在所述设定空间范围内。
存储器704,用于存放程序等。具体地,程序可以包括程序代码,该程序代码包括计算机操作指令。存储器704可能包含随机存取存储器(random access memory,简称RAM),也可能还包括非易失性存储器(non-volatile memory),例如至少一个磁盘存储器。处理器702执行存储器704所存放的应用程序,实现上述功能,从而实现如图2所示的语音控制方法。
采用本发明实施例提供的控制设备,该控制设备可以通过至少一个第一处理设备获取用户的语音信号对应的指令,从而确定所述指令的执行对象,实现对该执行对象的控制。由于所述控制设备可以通过所述至少一个第一处理设备获取所述指令,最终实现所述控制设备对执行对象的控制,因此,通过所述控制设备实现语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
基于以上实施例,本发明实施例还提供了一种第一处理设备,所述第一处理设备应用于如图1所示的语音控制系统,所述语音控制系统中包括控制设备和多个处理设备,所述第一处理设备为所述多个处理设备中的一个,参阅图8所示,所述第一处理设备包括:收发器801、处理器802、总线803、存储器804,麦克805,其中,
所述收发器801、所述处理器802、所述存储器804和所述麦克805通过所述总线803相互连接;所述总线803可以是外设部件互连标准(peripheral component interconnect,简称PCI)总线或扩展工业标准结构(extended industry standard architecture,简称EISA)总线等。所述总线可以分为地址总线、数据总线、控制总线等。为便于表示,图8中仅用一条粗线表示,但并不表示仅有一根总线或一种类型的总线。
所述收发器801,用于与所述语音控制系统中的所述控制设备进行通信交互。
所述麦克805,用于获取用户的语音信号;
所述处理器802,用于实现如图3所示的语音控制方法,包括:
获取用户的语音信号;
将所述用户的语音信号发送至所述控制设备;或者
将所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令,并将所述指令发送至所述控制设备。
可选的,所述处理器802在获取用户的语音信号之前,还用于:
接收所述控制设备发送的语音输入开启指令;
根据所述语音输入开启指令,开始监听用户的语音信号。
可选的,所述处理器802在获得所述用户的语音信号对应的指令后,还用于:
根据所述指令,确定所述指令针对的至少两个执行对象,在确定所述至少两个执行对象中包含所述第一处理设备800时,执行所述指令对应的操作。
所述存储器804,用于存放程序等。具体地,程序可以包括程序代码,该 程序代码包括计算机操作指令。存储器804可能包含随机存取存储器(random access memory,简称RAM),也可能还包括非易失性存储器(non-volatile memory),例如至少一个磁盘存储器。处理器802执行存储器804所存放的应用程序,实现上述功能,从而实现如图3所示的语音控制方法。
采用本发明实施例提供的第一处理设备,该第一处理设备将用户的语音信号或对应的指令发送给控制设备,使所述控制设备获取所述用户的语音信号对应的指令,从而确定所述指令的执行对象,最终实现所述控制设备对执行对象的控制,因此,采用所述第一处理设备的语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
基于以上实施例,本发明实施例还提供了一种语音控制系统,如图9所示,所述语音控制系统包括控制设备901和多个处理设备902,
其中所述多个处理设备902中包括至少一个第一处理设备9021,用于实现如图3所示的语音控制方法,即:获取用于的语音信号,将所述用户的语音信号发送至所述控制设备901,或将所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令,并将所述指令发送至所述控制设备901;
所述控制设备901,用于实现如图2所示的语音控制方法,即:通过所述多个处理设备902中的至少一个第一处理设备9021获取用户的语音信号对应的指令;根据所述指令,确定所述指令针对的执行对象;以及当所述执行对象为所述控制设备901时,执行所述指令对应的操作;当所述执行对象为所述多个处理设备中的第二处理设备9022时,向所述第二处理设备9022发送所述指令,所述指令用于通知所述第二处理设备9022执行所述指令对应的操作。
采用本发明实施例提供的语音控制系统,系统中的至少一个第一处理设备将用户的语音信号或对应的指令发送给控制设备,使所述控制设备获取所述用户的语音信号对应的指令,从而确定所述指令的执行对象,最终实现所 述控制设备对执行对象的控制,因此,该语音控制系统可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制系统可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
综上所述,通过本发明实施例中提供的一种语音控制方法、装置及系统,所述系统中的至少一个第一处理设备将用户的语音信号或对应的指令发送给控制设备,使所述控制设备获取所述用户的语音信号对应的指令,从而确定所述指令的执行对象,最终实现所述控制设备对执行对象的控制,因此,该语音控制方法可以克服由于用户与执行对象之间的距离造成的语音消损的问题,同时可以克服由于用户与控制设备之间的距离造成的语音消损的问题,显然,该语音控制方法可以实现随时随地对执行对象进行语音控制,提高了语音控制的灵活性。
本领域内的技术人员应明白,本发明的实施例可提供为方法、系统、或计算机程序产品。因此,本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器 中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本发明的优选实施例,但本领域内的技术人员一旦得知了基本创造性概念,则可对这些实施例做出另外的变更和修改。所以,所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。
显然,本领域的技术人员可以对本发明实施例进行各种改动和变型而不脱离本发明实施例的精神和范围。这样,倘若本发明实施例的这些修改和变型属于本发明权利要求及其等同技术的范围之内,则本发明也意图包含这些改动和变型在内。

Claims (21)

  1. 一种语音控制方法,该方法应用于语音控制系统,所述语音控制系统中包括控制设备和多个处理设备,其特征在于,包括:
    所述控制设备通过所述多个处理设备中的至少一个第一处理设备获取用户的语音信号对应的指令;
    所述控制设备根据所述指令,确定所述指令针对的执行对象;
    当所述执行对象为所述控制设备时,所述控制设备执行所述指令对应的操作;当所述执行对象为所述多个处理设备中的第二处理设备时,所述控制设备向所述第二处理设备发送所述指令,所述指令用于通知所述第二处理设备执行所述指令对应的操作。
  2. 如权利要求1所述的方法,其特征在于,在所述控制设备通过至少一个第一处理设备获取用户的语音信号对应的指令之前,所述方法还包括:
    所述控制设备确定所述至少一个第一处理设备;
    所述控制设备向所述至少一个第一处理设备发送语音输入开启指令,所述语音输入开启指令用于通知所述至少一个第一处理设备开始监听用户的语音信号。
  3. 如权利要求2所述的方法,其特征在于,所述控制设备确定所述至少一个第一处理设备,包括:
    所述控制设备根据接收到的所述至少一个第一处理设备发送的第一消息确定所述至少一个第一处理设备,所述第一消息是所述至少一个第一处理设备在当前时刻确定能够收到用户的语音信号时发送的;或者,
    所述控制设备获取所述用户的物理位置以及所述多个处理设备的物理位置;所述控制设备确定所述多个处理设备中每个处理设备的物理位置与所述用户的物理位置之间的距离;所述控制设备在所述多个处理设备中,筛选出物理位置与所述用户的物理位置之间的距离小于第一设定距离阈值的所述至少一个第一处理设备;或者,
    所述控制设备在所述多个处理设备中,筛选出处于待机状态或运行状态的所述至少一个第一处理设备。
  4. 如权利要求3所述的方法,其特征在于,所述控制设备获取所述用户的物理位置,包括:
    所述控制设备获取用户定位设备发送的定位指示信息,所述定位指示信息用于通知所述控制设备所述用户的物理位置与所述用户定位设备的物理位置之间的距离小于第二设定距离阈值;所述控制设备获取所述用户定位设备的物理位置,将所述用户定位设备的物理位置作为所述用户的物理位置;或者,
    所述控制设备接收所述多个处理设备中的第三处理设备发送的所述用户的物理位置,所述用户的物理位置为所述第三处理设备确定的。
  5. 如权利要求1-4任一项所述的方法,其特征在于,所述控制设备通过所述至少一个第一处理设备获取用户的语音信号对应的指令,包括:
    所述控制设备接收所述至少一个第一处理设备发送的所述指令,所述指令为所述至少一个第一处理设备监听到所述用户的语音信号后,对所述用户的语音信号进行解析获得的;或者
    所述控制设备接收所述至少一个第一处理设备发送的所述用户的语音信号,所述用户的语音信号为所述至少一个第一处理设备监听到的;所述控制设备对所述用户的语音信号进行解析得到所述指令。
  6. 如权利要求1-5任一项所述的方法,其特征在于,所述控制设备根据所述指令,确定所述指令针对的执行对象,包括:
    所述控制设备确定在所述指令中包含的执行对象信息,根据所述执行对象信息确定所述执行对象;或者
    所述控制设备确定所述指令对应的操作,所述控制设备确定具有执行所述指令对应的操作功能的所述执行对象;或者
    所述控制设备确定所述指令对应的操作,所述控制设备确定具有执行所述指令对应的操作功能、且位于设定空间范围内的所述执行对象,其中,所 述用户的物理位置在所述设定空间范围内。
  7. 一种语音控制方法,该方法应用于语音控制系统,所述语音控制系统中包括控制设备和多个处理设备,其特征在于,包括:
    所述多个处理设备中的第一处理设备获取用户的语音信号;
    所述第一处理设备将所述用户的语音信号发送至所述控制设备;或者
    所述第一处理设备将所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令,并将所述指令发送至所述控制设备。
  8. 如权利要求7所述的方法,其特征在于,在所述第一处理设备获取用户的语音信号之前,所述方法还包括:
    所述第一处理设备接收所述控制设备发送的语音输入开启指令;
    所述第一处理设备根据所述语音输入开启指令,开始监听用户的语音信号。
  9. 如权利要求7或8所述的方法,其特征在于,在所述第一处理设备获得所述用户的语音信号对应的指令后,所述方法还包括:
    所述第一处理设备根据所述指令,确定所述指令针对的至少两个执行对象,在确定所述至少两个执行对象中包含所述第一处理设备时,所述第一处理设备执行所述指令对应的操作。
  10. 一种控制设备,所述控制设备应用于语音控制系统,所述语音控制系统还包括多个处理设备,其特征在于,所述控制设备包括:
    获取单元,用于通过所述多个处理设备中的至少一个第一处理设备获取用户的语音信号对应的指令;
    处理单元,用于根据所述指令,确定所述指令针对的执行对象;以及当所述执行对象为所述控制设备时,执行所述指令对应的操作;
    发送单元,用于当所述执行对象为所述多个处理设备中的第二处理设备时,向所述第二处理设备发送所述指令,所述指令用于通知所述第二处理设备执行所述指令对应的操作。
  11. 如权利要求10所述的控制设备,其特征在于,所述处理单元还用于:
    在所述获取单元通过所述至少一个第一处理设备获取所述指令之前,确定所述至少一个第一处理设备;
    所述发送单元,还用于向所述至少一个第一处理设备发送语音输入开启指令,所述语音输入开启指令用于通知所述至少一个第一处理设备开始监听用户的语音信号。
  12. 如权利要求11所述的控制设备,其特征在于,所述获取单元,还用于:
    接收所述至少一个第一处理设备发送的第一消息,其中,所述第一消息是所述至少一个第一处理设备在当前时刻确定能够接收到用户的语音信号时发送的;或者
    获取所述用户的物理位置以及所述多个处理设备的物理位置;
    所述处理单元,在确定所述至少一个第一处理设备时,具体用于:
    在所述获取单元接收所述至少一个第一处理设备发送的第一消息后,根据所述第一消息确定所述至少一个第一处理设备;或者,
    在所述获取单元获取所述用户的物理位置以及所述多个处理设备的物理位置后,确定所述多个处理设备中每个处理设备的物理位置与所述用户的物理位置之间的距离;并在所述多个处理设备中,筛选出物理位置与所述用户的物理位置之间的距离小于第一设定距离阈值的所述至少一个第一处理设备;或者,
    在所述多个处理设备中,筛选出处于待机状态或运行状态的所述至少一个第一处理设备。
  13. 如权利要求12所述的控制设备,其特征在于,所述获取单元,在获取所述用户的物理位置时,具体用于:
    获取用户定位设备发送的定位指示信息,所述定位指示信息用于通知所述控制设备所述用户的物理位置与所述用户定位设备的物理位置之间的距离小于第二设定距离阈值;并获取所述用户定位设备的物理位置,将所述用户定位设备的物理位置作为所述用户的物理位置;或者,
    接收所述多个处理设备中的第三处理设备发送的所述用户的物理位置,所述用户的物理位置为所述第三处理设备确定的。
  14. 如权利要求10-13任一项所述的控制设备,其特征在于,所述获取单元在通过所述至少一个第一处理设备获取用户的语音信号对应的指令时,具体用于:
    接收所述至少一个第一处理设备发送的所述指令,所述指令为所述至少一个第一处理设备监听到所述用户的语音信号后,对所述用户的语音信号进行解析获得的;或者
    接收所述至少一个第一处理设备发送的所述用户的语音信号,所述用户的语音信号为所述至少一个第一处理设备监听到的;以及对所述用户的语音信号进行解析得到所述指令。
  15. 如权利要求10-14任一项所述的控制设备,其特征在于,所述处理单元,在根据所述指令,确定所述指令针对的执行对象时,具体用于:
    确定在所述指令中包含的执行对象信息,根据所述执行对象信息确定所述执行对象;或者
    确定所述指令对应的操作,以及确定具有执行所述指令对应的操作功能的所述执行对象;或者
    确定所述指令对应的操作,以及确定具有执行所述指令对应的操作功能、且位于设定空间范围内的所述执行对象,其中,所述用户的物理位置在所述设定空间范围内。
  16. 一种第一处理设备,所述第一处理设备应用于语音控制系统,所述语音控制系统中包括控制设备和多个处理设备,所述第一处理设备为所述多个处理设备中的一个,其特征在于,所述第一处理设备包括获取单元,第一发送单元,或者包括所述获取单元、处理单元和第二发送单元,其中,
    所述获取单元,用于获取用户的语音信号;
    所述第一发送单元,用于将所述用户的语音信号发送至所述控制设备;
    所述处理单元,用于将所述用户的语音信号进行解析,获得所述用户的 语音信号对应的指令;
    所述第二发送单元,用于将所述指令发送至所述控制设备。
  17. 如权利要求16所述的第一处理设备,其特征在于,所述获取单元,还用于:
    在获取用户的语音信号之前,接收所述控制设备发送的语音输入开启指令;
    根据所述语音输入开启指令,开始监听用户的语音信号。
  18. 如权利要求17或18所述的第一处理设备,其特征在于,所述处理单元,还用于:
    在获得所述用户的语音信号对应的指令后,根据所述指令,确定所述指令针对的至少两个执行对象,在确定所述至少两个执行对象中包含所述第一处理设备时,执行所述指令对应的操作。
  19. 一种控制设备,所述控制设备应用于语音控制系统,所述语音控制系统还包括多个处理设备,其特征在于,所述控制设备包括:处理器、总线以及存储器,所述处理器和所述存储器通过总线连接;
    所述处理器调用所述存储器中的指令,执行如权利要求1-6任一项所述的方法。
  20. 一种第一处理设备,所述第一处理设备应用于语音控制系统,所述语音控制系统中包括控制设备和多个处理设备,所述第一处理设备为所述多个处理设备中的一个,其特征在于,所述第一处理设备包括:麦克、处理器、总线以及存储器,所述麦克、所述处理器和所述存储器通过总线连接;
    所述麦克用于获取用户的语音信号;
    所述处理器调用所述存储器中的指令,执行如权利要求7-9任一项所述的方法。
  21. 一种语音控制系统,所述语音控制系统包括控制设备和多个处理设备,其特征在于,
    所述多个处理设备中的至少一个第一处理设备,用于获取用于的语音信 号,将所述用户的语音信号发送至所述控制设备,或将所述用户的语音信号进行解析,获得所述用户的语音信号对应的指令,并将所述指令发送至所述控制设备;
    所述控制设备,用于通过所述多个处理设备中的至少一个第一处理设备获取用户的语音信号对应的指令;根据所述指令,确定所述指令针对的执行对象;以及当所述执行对象为所述控制设备时,执行所述指令对应的操作;当所述执行对象为所述多个处理设备中的第二处理设备时,向所述第二处理设备发送所述指令,所述指令用于通知所述第二处理设备执行所述指令对应的操作。
PCT/CN2016/078440 2016-04-05 2016-04-05 一种语音控制方法、装置及系统 WO2017173566A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201680006596.3A CN107466458B (zh) 2016-04-05 2016-04-05 一种语音控制方法、装置及系统
PCT/CN2016/078440 WO2017173566A1 (zh) 2016-04-05 2016-04-05 一种语音控制方法、装置及系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/078440 WO2017173566A1 (zh) 2016-04-05 2016-04-05 一种语音控制方法、装置及系统

Publications (1)

Publication Number Publication Date
WO2017173566A1 true WO2017173566A1 (zh) 2017-10-12

Family

ID=60000802

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/078440 WO2017173566A1 (zh) 2016-04-05 2016-04-05 一种语音控制方法、装置及系统

Country Status (2)

Country Link
CN (1) CN107466458B (zh)
WO (1) WO2017173566A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109696833A (zh) * 2018-12-19 2019-04-30 歌尔股份有限公司 一种智能家居控制方法、可穿戴设备和音箱设备
WO2019184406A1 (en) * 2018-03-26 2019-10-03 Midea Group Co., Ltd. Voice-based user interface with dynamically switchable endpoints

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102111314A (zh) * 2010-12-30 2011-06-29 广州市聚晖电子科技有限公司 一种基于蓝牙传输的智能家居语音控制系统及方法
US20150162007A1 (en) * 2013-12-06 2015-06-11 Vivint, Inc. Voice control using multi-media rooms
CN105242556A (zh) * 2015-10-28 2016-01-13 小米科技有限责任公司 智能设备的语音控制方法、装置、控制设备及智能设备

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103578472A (zh) * 2012-08-10 2014-02-12 海尔集团公司 电器设备的控制方法和控制装置
CN103631211A (zh) * 2012-08-29 2014-03-12 三星电子(中国)研发中心 控制家电设备的方法、装置及系统
CN104580699B (zh) * 2014-12-15 2017-06-30 广东欧珀移动通信有限公司 一种待机时声控智能终端方法及装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102111314A (zh) * 2010-12-30 2011-06-29 广州市聚晖电子科技有限公司 一种基于蓝牙传输的智能家居语音控制系统及方法
US20150162007A1 (en) * 2013-12-06 2015-06-11 Vivint, Inc. Voice control using multi-media rooms
CN105242556A (zh) * 2015-10-28 2016-01-13 小米科技有限责任公司 智能设备的语音控制方法、装置、控制设备及智能设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019184406A1 (en) * 2018-03-26 2019-10-03 Midea Group Co., Ltd. Voice-based user interface with dynamically switchable endpoints
US10755706B2 (en) 2018-03-26 2020-08-25 Midea Group Co., Ltd. Voice-based user interface with dynamically switchable endpoints
CN109696833A (zh) * 2018-12-19 2019-04-30 歌尔股份有限公司 一种智能家居控制方法、可穿戴设备和音箱设备

Also Published As

Publication number Publication date
CN107466458A (zh) 2017-12-12
CN107466458B (zh) 2020-07-07

Similar Documents

Publication Publication Date Title
EP3379853B1 (en) Electronic device for transmitting audio data to multiple external devices
CN108022590B (zh) 语音接口设备处的聚焦会话
JP6247384B2 (ja) エアコン起動方法、エアコン起動装置、コンピュータプログラム及びコンピュータ読み取り可能な記憶媒体
US9578156B2 (en) Method and apparatus for operating an electronic device
JP6574316B2 (ja) 媒体アクセス制御(mac)アドレス識別
US10986573B2 (en) Bluetooth mesh network gateway and device data communication
KR102561414B1 (ko) 전자 장치 및 전자 장치의 동작 제어 방법
CN107409159B (zh) 无线对接系统中使用的主机、被对接机、主机方法、被对接机方法及计算机可读介质
US20200027469A1 (en) Content streaming apparatus and method
JP2017527924A (ja) ホームスマートソケット制御方法、装置、プログラム及び記録媒体
US20170033753A1 (en) Volume Control Methods and Devices, and Multimedia Playback Control Methods and Devices
WO2016150190A1 (zh) 音频播放控制方法、装置及音箱
US10516974B2 (en) Method for equipment networking and outputting by equipment, and equipment
WO2017173566A1 (zh) 一种语音控制方法、装置及系统
WO2023226625A1 (zh) 一种求救方法及终端设备
CN113940143B (zh) 用于协助用户配置照明系统的系统及方法
KR102385720B1 (ko) 데이터 처리 방법 및 그 전자 장치
EP3884625B1 (en) Selecting a destination for a sensor signal in dependence on an active light setting
EP4275458B1 (en) Adjusting a routine in dependence on a difference between current and expected states
CN107358956B (zh) 一种语音控制方法及其控制模组
CN117014547A (zh) 一种设备音量控制方法及相关装置
WO2016119188A1 (zh) 一种解决按键丢失的方法和蓝牙低功耗遥控器
KR20200003519A (ko) 원격 제어 장치, 그 제어 방법 및 전자 시스템
CN105744331A (zh) 一种控制影音播放设备运行状态的系统及方法

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 16897501

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16897501

Country of ref document: EP

Kind code of ref document: A1