WO2019174487A1 - 设备的唤醒方法、装置及电子设备 - Google Patents

设备的唤醒方法、装置及电子设备 Download PDF

Info

Publication number
WO2019174487A1
WO2019174487A1 PCT/CN2019/076804 CN2019076804W WO2019174487A1 WO 2019174487 A1 WO2019174487 A1 WO 2019174487A1 CN 2019076804 W CN2019076804 W CN 2019076804W WO 2019174487 A1 WO2019174487 A1 WO 2019174487A1
Authority
WO
WIPO (PCT)
Prior art keywords
infrared signal
wake
preset
detected
enter
Prior art date
Application number
PCT/CN2019/076804
Other languages
English (en)
French (fr)
Inventor
魏振宇
Original Assignee
阿里巴巴集团控股有限公司
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 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2019174487A1 publication Critical patent/WO2019174487A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/78—Detection of presence or absence of voice signals

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a method, an apparatus, and an electronic device for waking up a device.
  • the wake-up technology of the button that is, the device is woken up by the physical button switch
  • the voice wake-up technology that is, the voice command is preset for the AI voice device. That is, the wake-up word, when the wake-up word input is detected by the Voice Activity Detection (VAD) technology, wakes up the device.
  • VAD Voice Activity Detection
  • the button wake-up technology is a traditional physical button switch wake-up, which does not meet the artificial intelligence anthropomorphic dialogue experience, while the simple voice wake-up technology satisfies the anthropomorphic dialogue experience to a certain extent, but there are still limitations that the user must actively wake up.
  • the invention provides a method, a device and an electronic device for waking up a device, which can wake up the device without active operation of the user, and at the same time satisfy the user to enjoy the dialogue experience of the personification.
  • a method for waking up a device including:
  • the device If the detected infrared signal is greater than a preset infrared signal threshold, the device is controlled to enter an awake state.
  • a wake-up method of another device including:
  • the device If the detected infrared signal is greater than a preset infrared signal threshold, the device is controlled to enter a preliminary awake state.
  • a device wake-up device including:
  • the signal acquisition module detects the infrared signal near the device by using the location of the device as a detection point;
  • the wake-up control module is configured to control the device to enter an awake state if the detected infrared signal is greater than a preset infrared signal threshold.
  • a wake-up device for another device including:
  • the first signal acquisition module detects the infrared signal near the device by using the location of the device as a detection point;
  • the first wake-up control module is configured to control the device to enter a preliminary wake-up state if the detected infrared signal is greater than a preset infrared signal threshold.
  • an electronic device including:
  • a processor coupled to the memory for executing the program for:
  • the device If the detected infrared signal is greater than a preset infrared signal threshold, the device is controlled to enter an awake state.
  • another electronic device including:
  • a processor coupled to the memory for executing the program for:
  • the device If the detected infrared signal is greater than a preset infrared signal threshold, the device is controlled to enter a preliminary awake state.
  • the method, device and electronic device for waking up the device provided by the present invention, when the user approaches the device, and the infrared signal detected by the device is greater than the preset infrared signal threshold, the device enters or remains awake. In this way, the device can be automatically woken up without the user's active operation, and the user can enjoy the anthropomorphic conversation experience.
  • FIG. 1 is a schematic diagram of a wake-up logic of a device according to an embodiment of the present invention
  • FIG. 2 is a flowchart 1 of a method for waking up a device according to an embodiment of the present invention
  • FIG. 3 is a second flowchart of a wake-up method of a device according to an embodiment of the present invention.
  • 4a is a structural diagram 1 of a wake-up device of a device according to an embodiment of the present invention.
  • 4b is a structural diagram 2 of a wake-up device of a device according to an embodiment of the present invention.
  • 4c is a third structural diagram of a wake-up device of a device according to an embodiment of the present invention.
  • FIG. 5a is a flowchart 4 of a method for waking up a device according to an embodiment of the present invention.
  • FIG. 5b is a flowchart 5 of a method for waking up a device according to an embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram 1 of an electronic device according to an embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram 2 of an electronic device according to an embodiment of the present invention.
  • the device wakes up often using voice wake-up technology.
  • the device presets one or several voice commands, and keeps the device's microphone always in the listening state.
  • the device will receive the voice through the existing voice recognition technology.
  • the audio is converted to text and the device wakes up when the user issues a preset voice command and is detected by the device.
  • the voice wake-up technology provides users with a relatively intelligent human-machine conversation experience, there are still limitations that require the user to actively issue voice commands.
  • the embodiment of the present invention changes the limitation of the device in the prior art, which must be actively operated by the user to wake up the device.
  • the core idea is that by introducing a wake-up method for detecting the infrared signal, the device can be woken up without the user's active operation.
  • the detected infrared signal is greater than its preset threshold, that is, the control device enters an awake state.
  • FIG. 1 is a schematic diagram of a wake-up logic of a device according to an embodiment of the present invention.
  • the logic flow for controlling the wake-up of the device by detecting the infrared signal is proposed in the present embodiment.
  • the location of the device can be used as a detection point to detect the infrared signal of the device accessory, when detected.
  • the infrared signal is greater than the preset threshold, it can be considered that someone is in a relatively close position to the device, and the device may be controlled to operate.
  • the device can be controlled to enter or remain awake to actively perceive the user's intention and facilitate the user.
  • operations such as voice input at the same time, in the right part of FIG.
  • the device is controlled to enter the awake state by detecting whether there is an awake word in the voice input; when the device detects that there is an awake word input, the control device Enter the awake state.
  • the method of waking up the device by detecting the wake-up word can be used as an additional scheme of controlling whether to wake up the device by detecting an infrared signal.
  • the control mechanisms of the two schemes are independent of each other and can control the wake-up state of the device. When the detected infrared signal is not greater than the preset threshold and no wake-up words are input to the device, the device will remain in a sleep state.
  • the wake-up logic of the device shown in FIG. 1 is as shown in FIG. 2 , which is a flowchart 1 of a wake-up method of a device according to an embodiment of the present invention.
  • the execution body of the method may be controlled to wake up and have an infrared signal detection function.
  • the device is an infrared detecting device that is a detecting point at the location of the device, and the device is connected to the device and can be used to control the awake state of the device.
  • the method includes the following steps:
  • a detecting device capable of detecting an infrared signal such as an infrared sensor may be disposed at an inner step or an outer surface position of the device for detecting an infrared signal in the vicinity of the device.
  • the spatial range of the detection may be set, such as the infrared signal of the space around the device with the device as the center of the circle and the fixed distance as the radius, or only the direction of the detection device such as the front of the device may be set (considering that the user is usually located in the device)
  • the device is operated directly in front of the device.
  • the infrared signal of the fixed area may be set, such as the infrared signal of the space around the device with the device as the center of the circle and the fixed distance as the radius, or only the direction of the detection device such as the front of the device may be set (considering that the user is usually located in the device)
  • the device is operated directly in front of the device.
  • the infrared signal of the fixed area may be operated directly in front of the device
  • the above device may be an AI voice device, such as a smart speaker, a computer, or the like.
  • the control device If the detected infrared signal is greater than a preset infrared signal threshold, the control device enters an awake state.
  • an infrared signal threshold is set in advance, and the infrared signal threshold is an intensity value of the infrared signal that can be detected by the infrared signal detecting device when the user is located at a specified distance from the device.
  • the infrared signal detecting device that detects the location of the device detects that the infrared signal is continuously enhanced.
  • the infrared signal is greater than the preset infrared signal threshold, the user is compared with the device. The distance is less than the specified distance.
  • the user may have to perform voice control operations on the device. In this case, the user can automatically control the device to enter the awake state in order to facilitate the user to input the voice control command, so that the user can directly input the voice control command without actively executing the voice control command.
  • a device wake-up operation when the user approaches the device, the infrared signal detecting device that detects the location of the device detects that the infrared signal is continuously enhanced.
  • the infrared signal is greater than the preset infrared signal threshold, the user is compared with the device. The distance is less than the specified distance.
  • the user may have to perform voice control operations on the device.
  • the user can automatically control the device to enter the awake state in order to facilitate the user to input
  • the detected infrared signal will always trigger the device to remain awake.
  • the user may perform a continuous session with the device, that is, continuously input voice control commands. At this time, the device may remain in the awake state to satisfy the user's desire. The need to make continuous sessions.
  • the method further includes: after the device is woken up, if the detected infrared signal is not greater than a preset infrared signal threshold, the control device enters a sleep state after completing the session.
  • the device After the device is woken up by any of the above methods of infrared signal detection or wake-up word detection, the user can talk to the device. If the device is far away from the device, the infrared signal detected by the device is not greater than the infrared signal threshold preset by the device. After the current voice command is completed, the device is controlled to end the current session and automatically enters the sleep state.
  • directly controlling the device to enter the sleep state does not affect the operation of the wake-up word wake-up device, because when determining that the control device enters the sleep state, it will first determine Whether the current session ends or not, and controls the device to enter the sleep state after the session ends.
  • inputting the wake-up word is only a human-machine session process in which the device is adjusted from the sleep state to the awake state, and the device automatically enters the sleep state after a human-machine session. Therefore, controlling the device to enter the sleep state by detecting the infrared signal does not affect the wake-up mechanism that wakes up the device by the wake-up word.
  • the complete session process described in this embodiment mainly includes two parts, namely, a wake-up process and a voice input and session execution process.
  • the wake-up process controls the device to enter the awake state through an external trigger (infrared signal trigger, input wake-up word). After the device enters the awake state, it can receive a voice signal input by the user, and perform a corresponding session execution process based on the voice signal.
  • the end timing of a session can be set autonomously. For example, if no voice input is received within a specified time after receiving the voice input by the user and performing the session instruction operation, the control device considers that the session ends; or the device is woken up. After that, if no voice input is received within the specified time, the control device considers the session to end.
  • the method further includes: the infrared signal threshold may be an infrared signal detected by the infrared sensor when the human body is at a preset distance from the device.
  • the detected infrared signal is slightly increased, that is, the intensity of the infrared signal directly reflects the distance of the user from the device.
  • the preset distance can be set to 1 meter
  • the corresponding infrared signal threshold is The position of the human body one meter away from the device is that the infrared signal detecting device can detect the infrared signal of the corresponding intensity.
  • the infrared signal detecting device can detect that the user is in the space range of the controllable device through the detected infrared signal, and the device can be controlled to enter the awake state; when the user is more than 1 meter away from the device
  • the wake-up mechanism is turned off. If the user issues an wake-up word at this time, the device can be woken up again according to the wake-up mechanism of the wake-up word.
  • the method further includes: after the device is woken up, if the detected infrared signal is greater than a preset infrared signal threshold, and no voice signal is detected within a predetermined duration, the control device enters a sleep state.
  • the device When the device is in the awake state, the user may be located near the device, but there is no voice interaction with the device. Although a strong infrared signal can be detected at this time, this situation does not continue to keep the device in an awake state. Therefore, if no voice signal is detected within a predetermined length of time, the device can be controlled to enter a sleep state, thereby avoiding waste of power resources.
  • the above method may further include: detecting whether there is an wake-up word for waking up the device by voice input; if the wake-up word is detected and the current device is in a sleep state, the control device enters an awake state.
  • the user can still wake up the device actively.
  • another mode is shown to wake up by inputting a wake-up word to the device.
  • the manner of the device which can be used as an additional means of waking up the device by infrared signals in Figure 1. These two methods can perform wake-up operations on the device separately.
  • one or more voice commands may be preset in the device as wake-up words, such as “Hello, Xiaozhi”.
  • the device detects the voice input of the user and recognizes the wake-up word from the user. If the current device is in a sleep state, the device can be controlled to enter an awake state.
  • the device has been woken up by any means of infrared signal detection or wake-up word detection, that is, the device is already in the awake state, the user will issue the wake-up word again, the device will not execute the wake-up command, or send a voice feedback: the device is already awake status.
  • the method further includes: if the detected infrared signal is greater than a preset infrared signal threshold, acquiring image data in the preset area; and identifying the image data to determine whether the preset/target image is included in the recognition result. content;
  • the control device enters an awake state.
  • an image acquisition and recognition device may be installed near the device or inside the device, such as installing a built-in camera in the device to collect image data in a preset area,
  • the preset area may be a space area directly in front of the device.
  • the detected infrared signal is greater than the preset infrared signal threshold, and the image acquisition and recognition device can be triggered to collect and identify the image in the preset area, when determining the image.
  • the control device enters the awake state when the character is included.
  • the limited preset/target image content may also be an image of the pet. .
  • the device wake-up method provided by the embodiment of the present invention can detect an infrared signal through an infrared sensor when the user approaches the preset area, and if the infrared signal is greater than the preset infrared signal threshold, the device can automatically wake. Through such a device wake-up mechanism, the user can wake up the device without active operation, while satisfying the user's enjoyment of the anthropomorphic conversation experience.
  • an execution body of the method may be controlled to wake up and have an infrared signal detection function.
  • the device is an infrared detecting device that is a detecting point at the location of the device, and the device is connected to the device and can be used to control the awake state of the device.
  • the method includes the following steps:
  • This step is the same as the content of the above step S210.
  • the control device enters a preliminary awake state.
  • an infrared signal threshold is set in advance, and the infrared signal threshold is an intensity value of the infrared signal that can be detected by the infrared signal detecting device when the user is located at a specified distance from the device.
  • the infrared signal detecting device that detects the location of the device detects that the infrared signal is continuously enhanced.
  • the infrared signal is greater than the preset infrared signal threshold, the user is compared with the device. The distance is less than the specified distance. The user may need to perform voice control operations on the device.
  • the device in order to facilitate the user to input voice control commands, the device can automatically control the device to enter the preliminary wake-up state, so that the user may input voice control commands. Quickly enter the awake state to perform a device wake-up operation.
  • the power consumption of the device is between the sleep state and the formal wake state.
  • the session command cannot be directly executed.
  • the software network used to complete the wake-up operation is prepared to have a higher response rate than switching directly from the sleep state to the awake state. As soon as the user performs a wake-up operation in the preparatory wake-up state, the device will wake up immediately.
  • the user may only be close to the device but does not want to interact with the device. If the detected infrared signal is greater than the preset infrared signal threshold, the device may enter the awake state, which may cause a misoperation. ,a waste of resource. After the initial wake-up state is introduced as the intermediate state, the user can enter the awake state immediately after the user performs the wake-up operation, and the user can maintain low power consumption and save resources when the user does not perform the session interaction.
  • the detected infrared signal will always trigger the device to continue to maintain the preliminary wake-up. Status, the device will not wake up until the user performs an action to wake up the device.
  • the user may or may be in continuous session with the device, that is, continuously input voice control commands.
  • the device may remain in the preliminary awake state. (When the device is not woken up), after waiting for the user to perform the wake-up operation, quickly entering the awake state satisfies the user's desire to make a continuous session.
  • the method further includes:
  • the control device If an wake-up word is detected, the control device enters an awake state.
  • the user can perform a voice input wake-up word to control the device to enter the awake state.
  • one or more voice commands may be preset in the device as wake-up words, such as “Hello, Xiaozhi”.
  • the device detects the voice input of the user and recognizes the wake-up word from the user. If the current device is in the preliminary wake-up state, the device can be controlled to quickly enter the awake state.
  • the device If the device is already awake, the user will issue a wake-up word again, the device will no longer execute the wake-up command, or send a voice feedback: the device is already awake.
  • the above method further includes:
  • the control device After the device is woken up, if the detected infrared signal is not greater than the preset infrared signal threshold, the control device enters a sleep state after completing the session.
  • the user can talk to the device. If the device is far away from the device, the infrared signal detected by the device is not greater than the infrared signal threshold preset by the device. After the current voice command is completed, the device is controlled to end the current session and automatically enters the sleep state.
  • the complete session process described in this embodiment mainly includes two parts, namely, a wake-up process and a voice input and session execution process.
  • the wake-up process controls the device to enter the awake state through an external trigger (infrared signal trigger, input wake-up word). After the device enters the awake state, it can receive a voice signal input by the user, and perform a corresponding session execution process based on the voice signal.
  • the end timing of a session can be set autonomously. For example, if no voice input is received within a specified time after receiving the voice input by the user and performing the session instruction operation, the control device considers that the session ends; or the device is woken up. After that, if no voice input is received within the specified time, the control device considers the session to end.
  • the above method further includes:
  • the control device After the device is woken up, if the detected infrared signal is greater than the preset infrared signal threshold and no voice signal is detected within the predetermined length of time, the control device enters a sleep state.
  • the device When the device is in the awake state, the user may be located near the device, but there is no voice interaction with the device. Although a strong infrared signal can be detected at this time, this situation does not continue to keep the device in an awake state. Therefore, if no voice signal is detected within a predetermined length of time, the device can be controlled to enter a sleep state, thereby avoiding waste of power resources.
  • the device wake-up method provided by the embodiment of the present invention can detect an infrared signal through an infrared sensor when the user approaches the preset area, and if the infrared signal is greater than the preset infrared signal threshold, the device can automatically Enter the preliminary wake-up state.
  • the user can quickly enter the awake state by performing the operation of waking up the device at any time, and the low power consumption maintained by the standby awake state can reduce resource waste.
  • FIG. 4a is a structural diagram of a wake-up device of a device according to an embodiment of the present invention
  • the wake-up device of the device can be used to perform the method steps shown in FIG. 2, including:
  • the signal acquisition module 410 detects the infrared signal near the device by using the location of the device as a detection point;
  • the wake-up control module 420 is configured to control the device to enter an awake state if the detected infrared signal is greater than a preset infrared signal threshold.
  • the wake-up control module 420 is further configured to: after the device is woken up, if the detected infrared signal is not greater than a preset infrared signal threshold, the control device enters a sleep state after completing the session.
  • the wake-up control module 420 is further configured to: after the device is woken up, if the detected infrared signal is greater than a preset infrared signal threshold, and no voice signal is detected within a predetermined duration, the control device enters a sleep state.
  • the device for waking up the device may further include:
  • the wake-up word detecting module 430 is configured to detect whether there is an awakening word for waking up the device by voice input;
  • the wake-up control module 420 is further configured to: if the wake-up word is detected and the current device is in a sleep state, the control device enters an awake state.
  • the device for waking up the device may further include:
  • the image acquisition module 440 is configured to collect image data in a preset area if the detected infrared signal is greater than a preset infrared signal threshold;
  • the image recognition module 450 is configured to identify the image data to determine whether the preset/target image content is included in the recognition result;
  • the wake-up control module 420 is further configured to: if the preset result/target image content is included in the foregoing recognition result, the control device enters an awake state.
  • the device wake-up device provided by the embodiment of the present invention can detect the infrared signal through the infrared sensor when the user approaches the preset area, and if the infrared signal is greater than the preset infrared signal threshold, the device can automatically wake. Through such a device wake-up mechanism, the user can wake up the device without active operation, while satisfying the user's enjoyment of the anthropomorphic conversation experience.
  • FIG. 5a is a structural diagram of a wake-up device of a device according to an embodiment of the present invention
  • the wake-up device of the device can be used to perform the method steps shown in FIG.
  • the first signal acquisition module 510 detects the infrared signal near the device by using the location of the device as a detection point;
  • the first wake-up control module 520 is configured to control the device to enter a preliminary wake-up state if the detected infrared signal is greater than a preset infrared signal threshold.
  • the foregoing apparatus may further include:
  • the first wake-up word detecting module 530 is configured to detect whether there is an wake-up word for waking up the device by voice input;
  • the first wake-up control module 520 is further configured to control the device to enter an awake state if the wake-up word is detected.
  • first wake control module 520 is further configured to:
  • the control device After the device is woken up, if the detected infrared signal is not greater than the preset infrared signal threshold, the control device enters a sleep state after completing the session.
  • first wake control module 520 is further configured to:
  • the control device After the device is woken up, if the detected infrared signal is greater than the preset infrared signal threshold and no voice signal is detected within the predetermined length of time, the control device enters a sleep state.
  • the device wake-up device provided by the embodiment of the present invention can detect the infrared signal through the infrared sensor when the user approaches the preset area, and if the infrared signal is greater than the preset infrared signal threshold, the device can automatically Enter the preliminary wake-up state.
  • the user can quickly enter the awake state by performing the operation of waking up the device at any time, and the low power consumption maintained by the standby awake state can reduce resource waste.
  • the foregoing embodiment 3 describes the overall architecture of the device for waking up the device.
  • the function of the device can be implemented by using an electronic device.
  • FIG. 6 it is a schematic structural diagram of the electronic device according to the embodiment of the present invention. 610 and processor 620.
  • the memory 610 is configured to store a program.
  • memory 610 can also be configured to store various other data to support operation on the electronic device. Examples of such data include instructions for any application or method operating on an electronic device, contact data, phone book data, messages, pictures, videos, and the like.
  • the memory 610 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Disk or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM erasable Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Disk Disk or Optical Disk.
  • the processor 620 is coupled to the memory 610 for executing a program in the memory 610 for:
  • the control device If the detected infrared signal is greater than the preset infrared signal threshold, the control device enters an awake state.
  • the electronic device may further include: a communication component 630, a power component 640, an audio component 650, a display 660, and the like. Only some of the components are schematically illustrated in FIG. 6, and it is not meant that the electronic device includes only the components shown in FIG. 6.
  • Communication component 630 is configured to facilitate wired or wireless communication between the electronic device and other devices.
  • the electronic device can access a wireless network based on a communication standard such as WiFi, 2G or 3G, or a combination thereof.
  • communication component 630 receives broadcast signals or broadcast associated information from an external broadcast management system via a broadcast channel.
  • communication component 630 also includes a near field communication (NFC) module to facilitate short range communication.
  • NFC near field communication
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • a power supply component 640 provides power to various components of the electronic device.
  • Power component 640 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the electronic device.
  • the audio component 650 is configured to output and/or input an audio signal.
  • the audio component 650 includes a microphone (MIC) that is configured to receive an external audio signal when the electronic device is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode.
  • the received audio signal may be further stored in memory 610 or transmitted via communication component 630.
  • audio component 650 also includes a speaker for outputting an audio signal.
  • Display 660 includes a screen whose screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can sense not only the boundaries of the touch or sliding action, but also the duration and pressure associated with the touch or slide operation.
  • FIG. 7 it is a schematic structural diagram of the electronic device according to the embodiment of the present invention, and specifically includes: 710 and processor 720.
  • the memory 710 is configured to store a program.
  • memory 710 can also be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on an electronic device, contact data, phone book data, messages, pictures, videos, and the like.
  • Memory 710 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Disk or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM erasable Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Disk Disk or Optical Disk.
  • the processor 720 is coupled to the memory 710 for executing a program in the memory 710 for:
  • the control device enters a preliminary wake-up state.
  • the electronic device may further include: a communication component 730, a power component 740, an audio component 750, a display 760, and the like. Only some of the components are schematically illustrated in FIG. 7, and it is not meant that the electronic device includes only the components shown in FIG.
  • Communication component 730 is configured to facilitate wired or wireless communication between the electronic device and other devices.
  • the electronic device can access a wireless network based on a communication standard such as WiFi, 2G or 3G, or a combination thereof.
  • communication component 730 receives broadcast signals or broadcast associated information from an external broadcast management system via a broadcast channel.
  • communication component 730 also includes a near field communication (NFC) module to facilitate short range communication.
  • NFC near field communication
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • a power component 740 provides power to various components of the electronic device.
  • Power component 740 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the electronic device.
  • the audio component 750 is configured to output and/or input an audio signal.
  • the audio component 750 includes a microphone (MIC) that is configured to receive an external audio signal when the electronic device is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode.
  • the received audio signal may be further stored in memory 710 or transmitted via communication component 730.
  • audio component 750 also includes a speaker for outputting an audio signal.
  • the display 760 includes a screen whose screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can sense not only the boundaries of the touch or sliding action, but also the duration and pressure associated with the touch or slide operation.
  • the aforementioned program can be stored in a computer readable storage medium.
  • the program when executed, performs the steps including the foregoing method embodiments; and the foregoing storage medium includes various media that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.

Abstract

本发明实施例涉及一种设备的唤醒方法、装置及电子设备，其中方法包括：以设备所在位置为检测点，检测设备附近的红外信号；如果检测到的红外信号大于预置的红外信号阈值，则控制设备进入唤醒状态。本发明实施例的方案能够不需要用户主动操作就可唤醒设备，同时满足用户享受拟人的对话体验。

Description

设备的唤醒方法、装置及电子设备
本申请要求2018年03月14日递交的申请号为201810208016.X、发明名称为“设备的唤醒方法、装置及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信技术领域，尤其涉及一种设备的唤醒方法、装置及电子设备。
背景技术
目前，人工智能(Artificial Intelligence，AI)语音设备的唤醒存在两种实现方式，一是按键唤醒技术，即通过物理按键开关唤醒设备；二是语音唤醒技术，即对AI语音设备预先设置语音指令，即唤醒词，当通过语音活动检测(Voice Activity Detection，VAD)技术检测到有唤醒词输入时，唤醒设备。
上述设备唤醒的方式存在如下缺陷：
按键唤醒技术是传统的物理按键开关唤醒，不符合人工智能拟人的对话体验，而单纯的语音唤醒技术虽一定程度上满足了拟人的对话体验，但仍存在必须用户主动唤醒的局限性。
发明内容
本发明提供了一种设备的唤醒方法、装置及电子设备，不需要用户主动操作就可唤醒设备，同时满足用户享受拟人的对话体验。
为达到上述目的，本发明的实施例采用如下技术方案：
第一方面，提供了一种设备的唤醒方法，包括：
以设备所在位置为检测点，检测所述设备附近的红外信号；
如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入唤醒状态。
第二方面，提供了另一种设备的唤醒方法，包括：
以设备所在位置为检测点，检测所述设备附近的红外信号；
如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入预备唤醒状态。
第三方面，提供了一种设备的唤醒装置，包括：
信号采集模块，以设备所在位置为检测点，检测所述设备附近的红外信号；
唤醒控制模块，用于如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入唤醒状态。
第四方面，提供了另一种设备的唤醒装置，包括：
第一信号采集模块，以设备所在位置为检测点，检测所述设备附近的红外信号；
第一唤醒控制模块，用于如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入预备唤醒状态。
第五方面，提供了一种电子设备，包括：
存储器，用于存储程序；
处理器，耦合至所述存储器，用于执行所述程序，以用于：
以设备所在位置为检测点，检测所述设备附近的红外信号；
如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入唤醒状态。
第六方面，提供了另一种电子设备，包括：
存储器，用于存储程序；
处理器，耦合至所述存储器，用于执行所述程序，以用于：
以设备所在位置为检测点，检测所述设备附近的红外信号；
如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入预备唤醒状态。
本发明提供的设备的唤醒方法、装置及电子设备，当用户靠近设备，设备检测到的红外信号大于预置的红外信号阈值时，设备即进入或保持唤醒状态。如此，不需要用户主动操作，设备即可自动唤醒，同时满足用户享受拟人的对话体验。
上述说明仅是本申请技术方案的概述，为了能够更清楚了解本申请的技术手段，而可依照说明书的内容予以实施，并且为了让本申请的上述和其它目的、特征和优点能够更明显易懂，以下特举本申请的具体实施方式。
附图说明
通过阅读下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技 术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本申请的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：
图1为本发明实施例的设备的唤醒逻辑示意图；
图2为本发明实施例的设备的唤醒方法流程图一；
图3为本发明实施例的设备的唤醒方法流程图二；
图4a为本发明实施例的设备的唤醒装置结构图一；
图4b为本发明实施例的设备的唤醒装置结构图二；
图4c为本发明实施例的设备的唤醒装置结构图三；
图5a为本发明实施例的设备的唤醒方法流程图四；
图5b为本发明实施例的设备的唤醒方法流程图五；
图6为本发明实施例的电子设备的结构示意图一；
图7为本发明实施例的电子设备的结构示意图二。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。
在现有的人机会话场景中，设备的唤醒常采用语音唤醒技术，设备预置一个或数个语音指令，并保持设备的麦克始终处于监听状态，设备通过现有语音识别技术将接收到的音频转化为文字，当用户发出预置语音指令并被设备检测到时，设备即被唤醒。虽然语音唤醒技术为用户提供了相对智能的人机会话体验，但仍存在需要用户主动发出语音指令的局限性。
本发明实施例改变了现有技术中，必须由用户主动操作才能唤醒设备的局限性，其核心思想在于，通过引入红外信号检测的唤醒方法，实现无需用户主动操作，即可唤醒设备，当设备检测到红外信号大于其预置的阈值，即控制设备进入唤醒状态。
如图1所示，为本发明实施例提供的设备的唤醒逻辑示意图。在图1中左侧部分示出的为本方案中提出的通过检测红外信号来控制设备唤醒的逻辑流程，具体的，可以设备所在位置作为检测点，检测设备附件的红外信号，当检测到的红外信号大于预置的阈值时，可认为有人正处于距离设备的较近的位置，可能要对设备进行控制操作，此时可 控制设备进入或保持唤醒状态，以主动感知用户的意图，方便用户执行如语音输入的操作；同时在图1中右侧部分示，还示出了通过检测语音输入中是否存在唤醒词，来控制设备进入唤醒状态；当设备检测到有唤醒词输入后，控制设备进入唤醒状态。通过检测唤醒词唤醒设备的方法可作为通过检测红外信号来控制是否唤醒设备的附加方案。两个方案的控制机制相互独立，均可对设备的唤醒状态进行控制。当检测的红外信号不大于预置阈值，且也没有唤醒词输入至设备时，设备将保持休眠状态。
实施例一
基于图1所示的设备的唤醒逻辑，如图2所示，为本发明实施例提供的设备的唤醒方法流程图一，该方法的执行主体可以为被控制是否唤醒的且具有红外信号检测功能的设备或者是以设备所在位置为检测点的红外检测装置，且该装置与设备连接，可用于控制设备的唤醒状态。如图2所示，该包括如下步骤：
S210，以设备所在位置为检测点，检测设备附近的红外信号。
具体地，可以在设备的内步或外部表面位置设置如红外传感器等能够检测红外信号的检测装置，以用于检测设备附近的红外信号。当然，在检测过程中可以设置检测的空间范围，如以设备为圆心，固定距离为半径的设备周围空间的红外信号，也可以仅设置检测设备某一方向如设备正前方(考虑用户通常位于设备正前方对设备进行操作)固定区域的红外信号。
其中，上述的设备可以是AI语音设备，如智能音箱、电脑等。
S220，如果检测到的红外信号大于预置的红外信号阈值，则控制设备进入唤醒状态。
具体地，在检测红外信号的过程中，预先设置一个红外信号阈值，该红外信号阈值为用户位于距离设备指定距离的位置时，红外信号检测装置所能检测到的红外信号的强度值。
在实际应用场景中，当用户靠近设备时，以设备所在位置为检测点的红外信号检测装置检测到红外信号不断增强，当该红外信号大于上述预置的红外信号阈值时，则表征用户相对设备的距离已经小于指定距离，用户可能要对设备进行语音控制操作，此时为了方便用户输入语音控制指令，可自动控制设备进入唤醒状态，这样用户可直接输入语音控制指令，而不需要再主动执行一次设备唤醒操作。
如果用户在唤醒设备后始终与设备保持较近距离，并且使红外信号检测装置检测到的红外信号始终大于预置的红外信号阈值，则检测的红外信号会一直触发设备持续保持 唤醒状态。
在实际应用场景中，如果用户一直处于距离设备较近的位置，那么用户可能会与设备之间进行连续会话，即连续输入语音控制指令，此时，可保持设备一直处于唤醒状态，满足用户想要进行连续会话的需求。
进一步地，上述方法还包括：在设备被唤醒后，如果检测到的红外信号不大于预置的红外信号阈值，则控制设备在完成本次会话后进入休眠状态。
在设备通过上述红外信号检测或唤醒词检测之任一方式被唤醒后，用户可与设备会话。如果用户会话完成后远离设备，导致设备检测到的红外信号不大于设备预置的红外信号阈值，此时设备在完成当前语音指令后，被控制结束当前会话，自动进入休眠状态。这里需要说明的是，在判断红外信号不大于预置的红外信号阈值之后，直接控制设备进入休眠状态，并不影响唤醒词唤醒设备的操作，因为在确定控制设备进入休眠状态时，会先判断当前会话是否结束，当会话结束后才控制设备进入休眠状态。而通过唤醒词唤醒设备进行人机会话的过程中，输入一次唤醒词也只是将设备从休眠状态调整到唤醒状态完成一次的人机会话过程，一次人机会话后，设备还是自动进入休眠状态。因此，通过检测红外信号来控制设备进入休眠状态，并不会影响通过唤醒词唤醒设备的唤醒机制。
这里需要说明的是，本实施例中所述的一次完整的会话过程主要包括两部分，即唤醒过程和语音输入及会话执行过程。唤醒过程是通过外部触发(红外信号触发、输入唤醒词)来控制设备进入唤醒状态。设备进入唤醒状态后可以接收如用户输入的语音信号，并基于语音信号进行相应的会话执行过程。一次会话的结束时机可以自主设置，比如在连续接收到用户输入的语音并执行会话指令操作后的指定时间内没有再接收到任何语音输入，那么控制设备认为本次会话结束；或者在设备被唤醒后，如果在指定时间内没有接收到任何语音输入，那么控制设备认为本次会话结束。
进一步地，上述方法还包括：红外信号阈值可以为人体距设备在预置距离时，红外传感器所检测到的红外信号。
当用户靠近设备时，检测到的红外信号的轻度会增强，即该红外信号强弱直接反映用户距设备的距离，例如可设置该预置距离为1米，则相应的红外信号阈值即为人体距设备一米位置是，红外信号检测设备所能检测到相应强度的红外信号。当用户距离设备不大于1米时，红外信号检测设备可通过检测到的红外信号感知到用户已在可控制设备的空间范围内，此时可控制设备进入唤醒状态；当用户距离设备大于1米时，该唤醒机 制关闭，如果此时用户发出了唤醒词，设备可依据唤醒词的唤醒机制再次被唤醒。
进一步地，上述方法还包括：在设备被唤醒后，如果检测到的红外信号大于预置的红外信号阈值，且在预定时长内没有检测到语音信号，则控制设备进入休眠状态。
当设备处于唤醒状态时，用户可能位于设备附近，但是却没有任何与设备的语音交互，此时虽然能够检测到很强的红外信号，但这种情况确实没有继续保持设备处于唤醒状态的必要，因此如果在预定时长内没有检测到语音信号，则可控制设备进入休眠状态，从而避免电力资源浪费。
进一步地，上述方法还可包括：检测是否有通过语音输入的用于唤醒设备的唤醒词；如果检测到唤醒词且当前设备处于休眠状态，则控制设备进入唤醒状态。
为了满足用户在距离设备较远的位置，通过检测红外信号不能控制设备唤醒的情形下，仍能让用户主动唤醒设备，本实施例中示出了另外一种通过向设备语音输入唤醒词来唤醒设备的方式，该方式可作为图1中通过红外信号唤醒设备的方式的附加方式。这两种方式可以单独执行对设备的唤醒操作。
例如，在设备中可预先设置一个或多个语音指令为唤醒词，例如“你好，小智”，当用户发出该唤醒词，设备检测到用户的语音输入并从中识别到该唤醒词时，如果恰好当前设备处于休眠状态，则可以控制设备进入唤醒状态。
如果设备已经通过红外信号检测或唤醒词检测之任一方式被唤醒，即设备已经处于唤醒状态，此时用户再次发出唤醒词，设备将不再执行唤醒指令，或者发出语音反馈：设备已处于唤醒状态。
进一步地，上述方法还包括：如果检测到的红外信号大于预置的红外信号阈值，则采集预设区域内的图像数据；对图像数据进行识别，以确定识别结果中是否包含预设/目标图像内容；
如果识别结果中包含预设/目标图像内容，则控制设备进入唤醒状态。
为了确定通过红外信号检测到的红外信号确实为人体发出的红外信号，可以在设备附近或设备内部安装图像采集及识别装置，如在设备中安装内置照相机来采集预设区域内的图像数据，该预设区域可以是设备的正前方的空间区域。对采集的图像数据进行图像识别，确定图像数据中是否包含预设/目标图像内容。如果确定图像数据中包含预设/目标图像内容，则控制设备进入唤醒状态。
例如，当用户靠近设备到达预设区域时，检测到的红外信号大于预置的红外信号阈值，此时可触发图像采集及识别装置对预设区域内的图像进行采集和识别，当确定图像 中包含人物时控制设备进入唤醒状态。在某些应用场景下，比如在设备可以通过音乐、模仿动物叫声等方式，与宠物(猫、鸟)等尝试进行交流时，那么被限定的预设/目标图像内容也可以是宠物的图像。
本发明实施例提供的设备的唤醒方法，在用户靠近设备到达预置区域内时，设备可通过红外传感器检测到红外信号，如果该红外信号大于设备预置的红外信号阈值，此时设备可自动唤醒。通过这样的设备唤醒机制，用户无需主动操作就可唤醒设备，同时满足用户享受拟人的对话体验。
实施例二
基于图1所示的设备的唤醒逻辑，如图3所示，为本发明实施例提供的设备的唤醒方法流程图二，该方法的执行主体可以为被控制是否唤醒的且具有红外信号检测功能的设备或者是以设备所在位置为检测点的红外检测装置，且该装置与设备连接，可用于控制设备的唤醒状态。如图3所示，该包括如下步骤：
S310，以设备所在位置为检测点，检测设备附近的红外信号。
本步骤与上述步骤S210的内容相同。
S320，如果检测到的红外信号大于预置的红外信号阈值，则控制设备进入预备唤醒状态。
具体地，在检测红外信号的过程中，预先设置一个红外信号阈值，该红外信号阈值为用户位于距离设备指定距离的位置时，红外信号检测装置所能检测到的红外信号的强度值。
在实际应用场景中，当用户靠近设备时，以设备所在位置为检测点的红外信号检测装置检测到红外信号不断增强，当该红外信号大于上述预置的红外信号阈值时，则表征用户相对设备的距离已经小于指定距离，用户可能要对设备进行语音控制操作，此时为了方便用户输入语音控制指令，可自动控制设备进入预备唤醒状态，这样用户在可能输入语音控制指令的情况下，可以很快速的进入到唤醒状态，以执行一次设备唤醒操作。
这里需要说明的是，预备唤醒状态下，设备的功耗介于休眠状态和正式唤醒状态两者之间。虽然预备唤醒状态下，设备没有正式被唤醒，还不能直接执行会话指令，但是，用于完成唤醒操作的软件网络已做好一定准备，其反应速率高于直接从休眠状态切换到唤醒状态。只要用户在预备唤醒状态下执行唤醒操作，设备将立刻被唤醒。
在某些应用场景下，用户可能只是靠近设备但并不想与设备进行会话交互，如果直 接根据检测到的红外信号大于预置的红外信号阈值这一条件就控制设备进入唤醒状态，会造成误操作，浪费资源。引入预备唤醒状态作为中间状态后，既可以在用户执行唤醒操作后立刻进入到唤醒状态，又可以在用户不进行会话交互时，尽量维持较低的功耗，节省资源。
如果用户在设备进入预备唤醒状态后始终与设备保持较近距离，并且使红外信号检测装置检测到的红外信号始终大于预置的红外信号阈值，则检测的红外信号会一直触发设备持续保持预备唤醒状态，直到用户执行唤醒设备的操作后，设备才会被唤醒。
在实际应用场景中，如果用户一直处于距离设备较近的位置，那么用户可能会与设备之间正在或者将要进行连续会话，即连续输入语音控制指令，此时，可保持设备一直处于预备唤醒状态(在设备没有被唤醒的情况下)，以等待用户执行唤醒操作后，快速进入唤醒状态满足用户想要进行连续会话的需求。
进一步地，上述方法中，在控制设备进入预备唤醒状态之后还可包括：
检测是否有通过语音输入的用于唤醒设备的唤醒词；
如果检测到唤醒词，则控制设备进入唤醒状态。
在设备进入预备唤醒状态后，用户可以执行如语音输入唤醒词来控制设备进入到唤醒状态。
例如，在设备中可预先设置一个或多个语音指令为唤醒词，例如“你好，小智”，当用户发出该唤醒词，设备检测到用户的语音输入并从中识别到该唤醒词时，如果恰好当前设备处于预备唤醒状态，则可以控制设备快速进入唤醒状态。
如果设备已经处于唤醒状态，此时用户再次发出唤醒词，设备将不再执行唤醒指令，或者发出语音反馈：设备已处于唤醒状态。
进一步地，上述方法还包括：
在设备被唤醒后，如果检测到的红外信号不大于预置的红外信号阈值，则控制设备在完成本次会话后进入休眠状态。
在设备被唤醒后，用户可与设备进行会话。如果用户会话完成后远离设备，导致设备检测到的红外信号不大于设备预置的红外信号阈值，此时设备在完成当前语音指令后，被控制结束当前会话，自动进入休眠状态。
这里需要说明的是，本实施例中所述的一次完整的会话过程主要包括两部分，即唤醒过程和语音输入及会话执行过程。唤醒过程是通过外部触发(红外信号触发、输入唤醒词)来控制设备进入唤醒状态。设备进入唤醒状态后可以接收如用户输入的语音信号， 并基于语音信号进行相应的会话执行过程。一次会话的结束时机可以自主设置，比如在连续接收到用户输入的语音并执行会话指令操作后的指定时间内没有再接收到任何语音输入，那么控制设备认为本次会话结束；或者在设备被唤醒后，如果在指定时间内没有接收到任何语音输入，那么控制设备认为本次会话结束。
进一步地，上述方法还包括：
在设备被唤醒后，如果检测到的红外信号大于预置的红外信号阈值，且在预定时长内没有检测到语音信号，则控制设备进入休眠状态。
当设备处于唤醒状态时，用户可能位于设备附近，但是却没有任何与设备的语音交互，此时虽然能够检测到很强的红外信号，但这种情况确实没有继续保持设备处于唤醒状态的必要，因此如果在预定时长内没有检测到语音信号，则可控制设备进入休眠状态，从而避免电力资源浪费。
本发明实施例提供的设备的唤醒方法，在用户靠近设备到达预置区域内时，设备可通过红外传感器检测到红外信号，如果该红外信号大于设备预置的红外信号阈值，此时设备可自动进入预备唤醒状态。通过这样的设备唤醒机制，用户可以随时通过执行唤醒设备的操作使设备快速进入到唤醒状态，同时预备唤醒状态维持的低功耗可降低资源浪费。
实施例三
如图4a所示，为本发明实施例的设备的唤醒装置结构图，该设备的唤醒装置可用于执行如图2所示的方法步骤，其包括：
信号采集模块410，以设备所在位置为检测点，检测设备附近的红外信号；
唤醒控制模块420，用于如果检测到的上述红外信号大于预置的红外信号阈值，则控制设备进入唤醒状态。
进一步地，上述唤醒控制模块420还用于，在设备被唤醒后，如果检测到的红外信号不大于预置的红外信号阈值，则控制设备在完成本次会话后进入休眠状态。
进一步地，上述唤醒控制模块420还用于，在设备被唤醒后，如果检测到的红外信号大于预置的红外信号阈值，且在预定时长内没有检测到语音信号，则控制设备进入休眠状态。
进一步地，如图4b所示，上述设备的唤醒装置还可以包括：
唤醒词检测模块430，用于检测是否有通过语音输入的用于唤醒设备的唤醒词；
上述唤醒控制模块420，还用于如果检测到唤醒词且当前设备处于休眠状态，则控制设备进入唤醒状态。
进一步地，如图4c所示，上述设备的唤醒装置还可以包括：
图像采集模块440，用于如果检测到的红外信号大于预置的红外信号阈值，则采集预设区域内的图像数据；
图像识别模块450，用于对上述图像数据进行识别，以确定识别结果中是否包含预设/目标图像内容；
上述唤醒控制模块420，还用于如果上述识别结果中包含预设/目标图像内容，则控制设备进入唤醒状态。
本发明实施例提供的设备的唤醒装置，在用户靠近设备到达预置区域内时，设备可通过红外传感器检测到红外信号，如果该红外信号大于设备预置的红外信号阈值，此时设备可自动唤醒。通过这样的设备唤醒机制，用户无需主动操作就可唤醒设备，同时满足用户享受拟人的对话体验。
实施例四
如图5a所示，为本发明实施例的设备的唤醒装置结构图，该设备的唤醒装置可用于执行如图3所示的方法步骤，其包括：
第一信号采集模块510，以设备所在位置为检测点，检测设备附近的红外信号；
第一唤醒控制模块520，用于如果检测到的红外信号大于预置的红外信号阈值，则控制设备进入预备唤醒状态。
进一步地，如图5b所示，上述装置还可包括：
第一唤醒词检测模块530，用于检测是否有通过语音输入的用于唤醒设备的唤醒词；
第一唤醒控制模块520，还用于如果检测到唤醒词，则控制设备进入唤醒状态。
进一步地，上述第一唤醒控制模块520还可用于，
在设备被唤醒后，如果检测到的红外信号不大于预置的红外信号阈值，则控制设备在完成本次会话后进入休眠状态。
进一步地，上述第一唤醒控制模块520还可用于，
在设备被唤醒后，如果检测到的红外信号大于预置的红外信号阈值，且在预定时长内没有检测到语音信号，则控制设备进入休眠状态。
本发明实施例提供的设备的唤醒装置，在用户靠近设备到达预置区域内时，设备可 通过红外传感器检测到红外信号，如果该红外信号大于设备预置的红外信号阈值，此时设备可自动进入预备唤醒状态。通过这样的设备唤醒机制，用户可以随时通过执行唤醒设备的操作使设备快速进入到唤醒状态，同时预备唤醒状态维持的低功耗可降低资源浪费。
实施例五
前面实施例三描述了设备的唤醒装置的整体架构，该装置的功能可借助一种电子设备实现完成，如图6所示，其为本发明实施例的电子设备的结构示意图，具体包括：存储器610和处理器620。
存储器610，用于存储程序。
除上述程序之外，存储器610还可被配置为存储其它各种数据以支持在电子设备上的操作。这些数据的示例包括用于在电子设备上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。
存储器610可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
处理器620，耦合至存储器610，用于执行存储器610中的程序，以用于：
以设备所在位置为检测点，检测设备附近的红外信号；
如果检测到的红外信号大于预置的红外信号阈值，则控制设备进入唤醒状态。
上述的具体处理操作已经在前面实施例中进行了详细说明，在此不再赘述。
进一步，如图6所示，电子设备还可以包括：通信组件630、电源组件640、音频组件650、显示器660等其它组件。图6中仅示意性给出部分组件，并不意味着电子设备只包括图6所示组件。
通信组件630被配置为便于电子设备和其他设备之间有线或无线方式的通信。电子设备可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件630经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，通信组件630还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
电源组件640，为电子设备的各种组件提供电力。电源组件640可以包括电源管理系统，一个或多个电源，及其他与为电子设备生成、管理和分配电力相关联的组件。
音频组件650被配置为输出和/或输入音频信号。例如，音频组件650包括一个麦克风(MIC)，当电子设备处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器610或经由通信组件630发送。在一些实施例中，音频组件650还包括一个扬声器，用于输出音频信号。
显示器660包括屏幕，其屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与触摸或滑动操作相关的持续时间和压力。
实施例六
前面实施例四描述了设备的唤醒装置的整体架构，该装置的功能可借助一种电子设备实现完成，如图7所示，其为本发明实施例的电子设备的结构示意图，具体包括：存储器710和处理器720。
存储器710，用于存储程序。
除上述程序之外，存储器710还可被配置为存储其它各种数据以支持在电子设备上的操作。这些数据的示例包括用于在电子设备上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。
存储器710可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
处理器720，耦合至存储器710，用于执行存储器710中的程序，以用于：
以设备所在位置为检测点，检测设备附近的红外信号；
如果检测到的红外信号大于预置的红外信号阈值，则控制设备进入预备唤醒状态。
上述的具体处理操作已经在前面实施例中进行了详细说明，在此不再赘述。
进一步，如图7所示，电子设备还可以包括：通信组件730、电源组件740、音频 组件750、显示器760等其它组件。图7中仅示意性给出部分组件，并不意味着电子设备只包括图7所示组件。
通信组件730被配置为便于电子设备和其他设备之间有线或无线方式的通信。电子设备可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件730经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，通信组件730还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
电源组件740，为电子设备的各种组件提供电力。电源组件740可以包括电源管理系统，一个或多个电源，及其他与为电子设备生成、管理和分配电力相关联的组件。
音频组件750被配置为输出和/或输入音频信号。例如，音频组件750包括一个麦克风(MIC)，当电子设备处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器710或经由通信组件730发送。在一些实施例中，音频组件750还包括一个扬声器，用于输出音频信号。
显示器760包括屏幕，其屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与触摸或滑动操作相关的持续时间和压力。
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims (14)

  1. 一种设备的唤醒方法，其特征在于，包括：
    以设备所在位置为检测点，检测所述设备附近的红外信号；
    如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入唤醒状态。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    在所述设备被唤醒后，如果检测到的所述红外信号不大于预置的所述红外信号阈值，则控制所述设备在完成本次会话后进入休眠状态。
  3. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    在所述设备被唤醒后，如果检测到的所述红外信号大于预置的所述红外信号阈值，且在预定时长内没有检测到语音信号，则控制所述设备进入休眠状态。
  4. 根据权利要求2或3所述的方法，其特征在于，所述方法还包括：
    检测是否有通过语音输入的用于唤醒设备的唤醒词；
    如果检测到所述唤醒词且当前所述设备处于休眠状态，则控制所述设备进入唤醒状态。
  5. 根据权利要求1所述的方法，其特征在于，所述红外信号阈值为人体距所述设备在预置距离时，所述红外传感器所检测到的红外信号。
  6. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    如果检测到的所述红外信号大于预置的所述红外信号阈值，则采集预设区域内的图像数据；
    对所述图像数据进行识别，以确定识别结果中是否包含预设/目标图像内容；
    如果所述识别结果中包含所述预设/目标图像内容，则控制所述设备进入唤醒状态。
  7. 一种设备的唤醒方法，其特征在于，包括：
    以设备所在位置为检测点，检测所述设备附近的红外信号；
    如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入预备唤醒状态。
  8. 根据权利要求7所述的方法，其特征在于，所述控制所述设备进入预备唤醒状态之后还包括：
    检测是否有通过语音输入的用于唤醒设备的唤醒词；
    如果检测到所述唤醒词，则控制所述设备进入唤醒状态。
  9. 根据权利要求8所述的方法，其特征在于，所述方法还包括：
    在所述设备被唤醒后，如果检测到的所述红外信号不大于预置的所述红外信号阈值，则控制所述设备在完成本次会话后进入休眠状态。
  10. 根据权利要求8所述的方法，其特征在于，所述方法还包括：
    在所述设备被唤醒后，如果检测到的所述红外信号大于预置的所述红外信号阈值，且在预定时长内没有检测到语音信号，则控制所述设备进入休眠状态。
  11. 一种设备的唤醒装置，其特征在于，包括：
    信号采集模块，以设备所在位置为检测点，检测所述设备附近的红外信号；
    唤醒控制模块，用于如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入唤醒状态。
  12. 一种设备的唤醒装置，其特征在于，包括：
    第一信号采集模块，以设备所在位置为检测点，检测所述设备附近的红外信号；
    第一唤醒控制模块，用于如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入预备唤醒状态。
  13. 一种电子设备，其特征在于，包括：
    存储器，用于存储程序；
    处理器，耦合至所述存储器，用于执行所述程序，以用于：
    以设备所在位置为检测点，检测所述设备附近的红外信号；
    如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入唤醒状态。
  14. 一种电子设备，其特征在于，包括：
    存储器，用于存储程序；
    处理器，耦合至所述存储器，用于执行所述程序，以用于：
    以设备所在位置为检测点，检测所述设备附近的红外信号；
    如果检测到的所述红外信号大于预置的红外信号阈值，则控制所述设备进入预备唤醒状态。
PCT/CN2019/076804 2018-03-14 2019-03-04 设备的唤醒方法、装置及电子设备 WO2019174487A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810208016.XA CN110277094A (zh) 2018-03-14 2018-03-14 设备的唤醒方法、装置及电子设备
CN201810208016.X 2018-03-14

Publications (1)

Publication Number Publication Date
WO2019174487A1 true WO2019174487A1 (zh) 2019-09-19

Family

ID=67908522

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/076804 WO2019174487A1 (zh) 2018-03-14 2019-03-04 设备的唤醒方法、装置及电子设备

Country Status (3)

Country Link
CN (1) CN110277094A (zh)
TW (1) TW201939212A (zh)
WO (1) WO2019174487A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3799040A1 (en) * 2019-09-29 2021-03-31 Baidu Online Network Technology (Beijing) Co., Ltd. Speech recognition control method and apparatus, electronic device and readable storage medium

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111182385B (zh) * 2019-11-19 2021-08-20 广东小天才科技有限公司 一种语音交互控制方法及智能音箱
CN110933345B (zh) * 2019-11-26 2021-11-02 深圳创维－Rgb电子有限公司 一种降低电视待机功耗的方法、电视机及存储介质
CN111464992A (zh) * 2020-04-01 2020-07-28 蔚蓝计划(北京)科技有限公司 一种基于智能垃圾桶的节电控制方法、装置和系统
CN112735401A (zh) * 2020-12-11 2021-04-30 广州朗国电子科技有限公司 基于pir传感器的语音识别检测方法、装置及一体机
CN113488053A (zh) * 2021-08-10 2021-10-08 合肥美菱物联科技有限公司 一种茶吧机的语音模块唤醒控制方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201352430Y (zh) * 2009-02-13 2009-11-25 苏州双林塑胶电子有限公司 节能数码相框
CN103167160A (zh) * 2012-10-09 2013-06-19 深圳市金立通信设备有限公司 基于温度感应与人脸识别技术实现手机唤醒解锁的系统及方法
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
CN107450390A (zh) * 2017-07-31 2017-12-08 绵阳美菱软件技术有限公司 一种智能家电控制装置、控制方法及控制系统
CN107993656A (zh) * 2017-12-06 2018-05-04 海信（山东）空调有限公司 语音识别功能唤醒方法和装置
CN108231079A (zh) * 2018-02-01 2018-06-29 北京百度网讯科技有限公司 用于控制电子设备的方法、装置、设备以及计算机可读存储介质

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100737044B1 (ko) * 2003-04-17 2007-07-09 마츠시타 덴끼 산교 가부시키가이샤 기동 시간 단축 장치 및 전자 기기
US9779725B2 (en) * 2014-12-11 2017-10-03 Mediatek Inc. Voice wakeup detecting device and method
CN204463028U (zh) * 2015-01-16 2015-07-08 深圳市中控生物识别技术有限公司 一种具有红外唤醒功能的身份识别设备
CN104820556A (zh) * 2015-05-06 2015-08-05 广州视源电子科技股份有限公司 唤醒语音助手的方法及装置
CN205005206U (zh) * 2015-08-31 2016-01-27 广东九联科技股份有限公司 自动待机及唤醒的机顶盒
CN106125920A (zh) * 2016-06-21 2016-11-16 深圳市金立通信设备有限公司 一种终端及其控制方法
CN107291451B (zh) * 2017-05-25 2021-01-19 深圳市冠旭电子股份有限公司 语音唤醒方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201352430Y (zh) * 2009-02-13 2009-11-25 苏州双林塑胶电子有限公司 节能数码相框
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
CN103167160A (zh) * 2012-10-09 2013-06-19 深圳市金立通信设备有限公司 基于温度感应与人脸识别技术实现手机唤醒解锁的系统及方法
CN107450390A (zh) * 2017-07-31 2017-12-08 绵阳美菱软件技术有限公司 一种智能家电控制装置、控制方法及控制系统
CN107993656A (zh) * 2017-12-06 2018-05-04 海信（山东）空调有限公司 语音识别功能唤醒方法和装置
CN108231079A (zh) * 2018-02-01 2018-06-29 北京百度网讯科技有限公司 用于控制电子设备的方法、装置、设备以及计算机可读存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3799040A1 (en) * 2019-09-29 2021-03-31 Baidu Online Network Technology (Beijing) Co., Ltd. Speech recognition control method and apparatus, electronic device and readable storage medium

Also Published As

Publication number Publication date
CN110277094A (zh) 2019-09-24
TW201939212A (zh) 2019-10-01

Similar Documents

Publication Publication Date Title
WO2019174487A1 (zh) 设备的唤醒方法、装置及电子设备
WO2019007245A1 (zh) 一种处理方法、控制方法、识别方法及其装置和电子设备
US10366688B2 (en) Voice control user interface with multiple voice processing modules
US10381002B2 (en) Voice control user interface during low-power mode
US10381010B2 (en) Voice control user interface during low power mode
KR101837333B1 (ko) 전자 디바이스를 깨우기 위한 방법 및 장치
KR101787293B1 (ko) Ｍｃｕ칩을 웨이크업 시키기 위한 방법 및 디바이스
KR102438300B1 (ko) 청취 디바이스에 대한 디바이스 중재
JP6446548B2 (ja) 主ｍｃｕウェイクアップ回路、方法、及び装置
EP3136794B1 (en) Electronic equipment, method and device for waking up electronic equipment
US10373615B2 (en) Voice control user interface during low power mode
JP6284687B2 (ja) Ｍｃｕウェイクアップ方法及び装置
CN107919124B (zh) 设备唤醒方法及装置
US20140195235A1 (en) Remote control apparatus and method for controlling power
US20190304460A1 (en) Voice control user interface with progressive command engagement
EP3793202A1 (en) Method and device for voice control,terminal, and storage
WO2015131550A1 (zh) 一种控制播放器进入睡眠模式的方法、装置及终端设备
CN110727821A (zh) 防止设备被误唤醒的方法、装置、系统和计算机存储介质
WO2019007247A1 (zh) 人机会话的处理方法、装置及电子设备
CN110574355A (zh) 闹钟提醒方法、装置、存储介质及电子设备
CN112201242A (zh) 唤醒设备的方法、装置、电子设备及存储介质
CN105188112A (zh) 休眠状态的控制方法及装置
CN106341733A (zh) 智能电视电源控制方法及装置
CN117311836A (zh) 进程处理方法、装置、设备及存储介质

Legal Events

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

Ref document number: 19767996

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19767996

Country of ref document: EP

Kind code of ref document: A1