WO2022033574A1 - 设备唤醒方法及装置 - Google Patents

设备唤醒方法及装置 Download PDF

Info

Publication number
WO2022033574A1
WO2022033574A1 PCT/CN2021/112410 CN2021112410W WO2022033574A1 WO 2022033574 A1 WO2022033574 A1 WO 2022033574A1 CN 2021112410 W CN2021112410 W CN 2021112410W WO 2022033574 A1 WO2022033574 A1 WO 2022033574A1
Authority
WO
WIPO (PCT)
Prior art keywords
wake
request
voice
target device
user
Prior art date
Application number
PCT/CN2021/112410
Other languages
English (en)
French (fr)
Inventor
孙敏刚
Original Assignee
北京京东尚科信息技术有限公司
北京京东世纪贸易有限公司
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 北京京东尚科信息技术有限公司, 北京京东世纪贸易有限公司 filed Critical 北京京东尚科信息技术有限公司
Publication of WO2022033574A1 publication Critical patent/WO2022033574A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/34—Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Definitions

  • the present disclosure relates to the field of control technologies, and more particularly, to a device wake-up method, a master device, an electronic device, and a computer-readable storage medium.
  • a voice wake-up function For a device with a voice wake-up function, after the user sends a preset wake-up voice around the device, the device can be woken up.
  • the inventors found that when multiple devices with the same wake-up word coexist, after the user sends out the preset wake-up voice, the multiple devices enter the wake-up state and respond to the wake-up voice, which may cause repeated device repetitions.
  • the present disclosure provides a device wake-up method and apparatus with low response interference, low response delay, and low data bandwidth consumption.
  • One aspect of the present disclosure provides a device wake-up method, applied to a master control device, including receiving a first wake-up request from the device, wherein the first wake-up request is the first wake-up request received by the master device; according to The above-mentioned first wake-up request determines the target device to be woken up; and triggers the above-mentioned target device to enter a wake-up state, so that the above-mentioned target device responds to the user's wake-up voice.
  • the above-mentioned determining the target device to be woken up according to the above-mentioned first wake-up request includes determining the first device that sends the above-mentioned first wake-up request as the above-mentioned target device.
  • the above-mentioned determining the target device to be woken up according to the above-mentioned first wake-up request includes receiving at least one second wake-up request within a preset time period after receiving the above-mentioned first wake-up request, wherein the above-mentioned first wake-up request and each above-mentioned second wake-up request contains the sound feature of the wake-up voice acquired by the device; determine the first sound feature in the above-mentioned first wake-up request and the second sound feature in each of the above-mentioned second wake-up requests; in the above-mentioned first sound Among the features and each of the above-mentioned second sound features, the sound feature with the highest priority is determined as the target sound feature, and the device associated with the above-mentioned target sound feature is used as the target device.
  • triggering the target device to enter the wake-up state includes sending a wake-up lock to the target device, so that the target device enters the wake-up state.
  • the above-mentioned method further includes, within a preset period of time after sending the above-mentioned wake-up lock to the above-mentioned target device, determining whether to receive a release wake-lock request sent by the above-mentioned target equipment; and, within the above-mentioned preset period of time.
  • the wake-up lock request is released, the above-mentioned wake-up lock is released.
  • the above method further includes generating a third wake-up request in response to the user's wake-up voice; the above-mentioned determining the target device to be woken up according to the above-mentioned first wake-up request includes determining whether the generation time of the above-mentioned third wake-up request is earlier than the reception time of the first wake-up request; and, in the case that the generation time of the third wake-up request is earlier than the reception time of the first wake-up request, determine that the master device is the target device.
  • the above method further includes receiving a probe signal sent by at least one device at a preset frequency; and returning a probe response signal to each of the above devices.
  • a master control device comprising a first receiving module configured to receive a first wake-up request from the device, wherein the first wake-up request is the first wake-up request received by the master control device ; a first determination module for determining a target device to be woken up according to the first wake-up request; a first processing module for triggering the target device to enter a wake-up state, so that the target device responds to the user's wake-up voice.
  • the above-mentioned first determining module includes a first determining sub-module, configured to determine the first device that sends the above-mentioned first wake-up request as the above-mentioned target device.
  • the above-mentioned first determination module includes a first receiving sub-module, configured to receive at least one second wake-up request within a preset time period after receiving the above-mentioned first wake-up request, wherein the first wake-up request and each of the second wake-up requests includes the sound feature of the wake-up voice acquired by the device; a second determination submodule is used to determine the first sound feature in the first wake-up request and each of the second wake-up requests the second sound feature; the third determination sub-module is used for determining the sound feature with the highest priority among the above-mentioned first sound feature and each of the above-mentioned second sound features as the target sound feature, and assigning the sound feature associated with the above-mentioned target sound feature device as the target device.
  • a first receiving sub-module configured to receive at least one second wake-up request within a preset time period after receiving the above-mentioned first wake-up request, wherein the first wake-up request and each of the second wake-up requests
  • the above-mentioned first processing module includes a first processing sub-module for sending a wake-up lock to the above-mentioned target device, so that the above-mentioned target device enters a wake-up state.
  • the above-mentioned device further includes a second determination module, configured to determine whether a request to release the wake-up lock sent by the above-mentioned target device is received within a preset time period after the above-mentioned wake-up lock is sent to the above-mentioned target device; a fourth processing module, It is used to release the wake-up lock in the case where the request for releasing the wake-up lock is not received within the preset time period.
  • a second determination module configured to determine whether a request to release the wake-up lock sent by the above-mentioned target device is received within a preset time period after the above-mentioned wake-up lock is sent to the above-mentioned target device
  • a fourth processing module It is used to release the wake-up lock in the case where the request for releasing the wake-up lock is not received within the preset time period.
  • the above-mentioned device further includes a fifth processing module for generating a third wake-up request in response to the above-mentioned user's wake-up voice;
  • the above-mentioned first determination module includes a fourth determination sub-module for determining the above-mentioned third wake-up request. Whether the generation time of the above-mentioned first wake-up request is earlier than the receiving time of the above-mentioned first wake-up request;
  • the master device is the above target device.
  • the above-mentioned device further includes a second receiving module, configured to receive a detection signal sent by at least one device at a preset frequency; and a sixth processing module, configured to return a detection response signal to each of the above-mentioned devices.
  • Another aspect of the present disclosure provides a device wake-up method, including generating a wake-up request after acquiring a user's wake-up voice, and sending the wake-up request to a main control device; in response to receiving the wake-up returned by the main control device command, enter the wake-up state and respond to the above-mentioned user's wake-up voice.
  • entering the wake-up state and responding to the user's wake-up voice in response to receiving the wake-up instruction returned by the above-mentioned main control device includes entering the wake-up state in response to receiving the wake-up lock returned by the above-mentioned main control device.
  • the above user's wake-up voice responds.
  • the method further includes sending a wake-up lock release request to the main control device within a preset time period after receiving the wake-up lock; and releasing the wake-up lock in response to receiving a response command returned by the main control device.
  • the method further includes receiving a detection signal sent by the above-mentioned main control device at a preset frequency; and returning a detection response signal to the above-mentioned main control device.
  • Another aspect of the present disclosure provides a device, comprising a second processing module configured to generate a wake-up request after acquiring a user's wake-up voice, and send the above-mentioned wake-up request to a main control device; a third processing module, using In response to receiving the wake-up instruction returned by the above-mentioned main control device, enter the wake-up state and respond to the above-mentioned user's wake-up voice.
  • Another aspect of the present disclosure provides an electronic device including one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more programs When executed by the processor, the one or more processors are caused to implement the methods of the embodiments of the present disclosure.
  • Another aspect of the present disclosure provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to implement the method of an embodiment of the present disclosure.
  • the master device receives the first wake-up request from the device, determines the target device to be woken up according to the first wake-up request, and triggers the target device to enter the wake-up state, so that the target device responds to the user's wake-up voice.
  • the target device to be woken up is determined according to the first wake-up request.
  • the first wake-up request is the first wake-up request received by the main control device. Therefore, for the user's wake-up voice, a single device is woken up, which can effectively solve the problem of repeated response and response interference.
  • Each device sends a wake-up request to the master device in the same local area network. Compared with the related art in which each device sends a wake-up request to the cloud server, this solution can effectively solve the problem of obvious response delay and large network bandwidth consumption. .
  • FIG. 1 schematically shows a system architecture of a device wake-up method according to an embodiment of the present disclosure
  • FIG. 2A schematically shows a flowchart of a method for waking up a device according to an embodiment of the present disclosure
  • FIG. 2B is a schematic diagram of a voice wake-up system in an embodiment of the present disclosure
  • FIG. 3A schematically shows a flowchart of a method for waking up a device according to another embodiment of the present disclosure
  • FIG. 3B schematically shows a schematic diagram of a voice wake-up system in yet another embodiment of the present disclosure
  • FIG. 4 schematically shows a flowchart of a device wake-up method according to still another embodiment of the present disclosure
  • FIG. 5 schematically shows a block diagram of a master device according to an embodiment of the present disclosure
  • FIG. 6 schematically shows a block diagram of an electronic device suitable for implementing the device wake-up method and apparatus according to an embodiment of the present disclosure.
  • At least one of the “systems” shall include, but not be limited to, systems with A alone, B alone, C alone, A and B, A and C, B and C, and/or A, B, C, etc. ).
  • the method may include receiving a first wake-up request from a device, wherein the first wake-up request is the first wake-up request received by the master device, and then determining a target device to be woken up according to the first wake-up request, and then triggering the target The device enters an awake state so that the target device responds to the user's wake-up speech.
  • the system architecture 100 includes at least one device (multiple devices are shown in the figure, such as devices 101 , 102 , and 103 ) and a master device 104 that are connected to the same local area network with a voice wake-up function.
  • the master device 104 receives the first wake-up request from the devices (eg, devices 101, 102, 103), wherein the first wake-up request is the first wake-up request received by the master device, and then according to the first wake-up request Upon a wake-up request, the target device to be woken up is determined, and then the target device is triggered to enter a wake-up state, so that the target device responds to the user's wake-up voice.
  • FIG. 2A schematically shows a flowchart of a method for waking up a device according to an embodiment of the present disclosure.
  • the method may include, for example, operations S210 to S230.
  • a first wake-up request from the device is received, wherein the first wake-up request is the first wake-up request received by the master device.
  • the master device receives a first wake-up request from the device, where the device may be a user terminal with a voice wake-up function, such as a mobile device (eg, a mobile phone, a personal digital assistant) , smart speakers, tablet computers, desktop computers, air conditioners and other equipment.
  • the main control device is used to determine, in at least one device, a target device that responds to the user's wake-up voice, and the main control device and other devices can be connected in a wired or wireless manner.
  • Each device in the voice wake-up system can detect other devices in the system in real time or periodically through mDNS or similar detection technology, and record the newly detected other devices (such as devices that can be newly connected to the local area network) in the In its own device list, or delete undetectable devices (for example, a device that can be disconnected or down) from its own device list.
  • each device in the voice wake-up system may elect a master device through a leader election algorithm, and then the master device controls the wake-up function of other devices, wherein the leader election algorithm may be, for example, raft protocol, Bully election algorithm, kafka election algorithm, or other election algorithms available in ZooKeeper.
  • the leader election algorithm may be, for example, raft protocol, Bully election algorithm, kafka election algorithm, or other election algorithms available in ZooKeeper.
  • the main control device After the main control device is elected, other devices send a detection signal to the main control device at a preset frequency to detect whether the main control device is working properly. After receiving the detection signal from other devices, the main control device returns to other devices. Probe response signal. At the same time, the main control device will also periodically send detection signals to other devices to determine whether the other devices are working properly. After receiving the detection signals from the main control device, each other device also needs to return a detection response to the main control device. Signal.
  • the main control device When the main control device does not return a detection response signal within the preset time, it is determined that the main control device is in an abnormal operation state, and the reason for the abnormal operation state may include the main control device being offline or down. At this time, other devices in the voice wake-up system need to re-elect a new master device, and then the new master device controls the wake-up function of other devices.
  • each device in the voice wake-up system After each device in the voice wake-up system obtains the wake-up voice from the user, it recognizes the wake-up word in the wake-up voice and generates a wake-up request, and then sends the wake-up request to the master device to request to respond to the user's wake-up voice and enter the wake-up state . Since different devices may be at different distances from the user, the closer the device is to the user, the earlier the user's wake-up voice is obtained, and the sound quality of the obtained wake-up voice is also better, and a wake-up request is generated and sent to the master device. Therefore, the master device can determine the distance relationship between each device and the user according to the time sequence of the received wake-up requests.
  • the main control device receives the first wake-up request from the device, the first wake-up request is the first wake-up request received by the main control device, and the target device to be woken up is determined according to the first wake-up request, which can effectively improve the device wake-up efficiency and reduce the number of devices Response time difference.
  • a target device to be woken up is determined according to the first wakeup request.
  • the device that sends the first wake-up request may be determined as the target device to be woken up according to the first wake-up request. For each device, compared to the process of acquiring the wake-up voice from the user, recognizing the wake-up words in the wake-up voice and generating the wake-up request, the time-consuming of sending the wake-up request to the master device is negligible. Since the first wake-up request is the first wake-up request received by the main control device, it can be determined that the device that sends the first wake-up request is the device that first obtains the user's wake-up voice, that is, the device closest to the user.
  • the device closest to the user can be determined as the target device to be woken up, and the first wake-up device can be sent to the user.
  • the requested device is determined as the target device to be woken up.
  • the first wake-up request includes the device identifier of the sending device.
  • the device indicated by the device identifier may be determined as the target according to the device identifier carried in the first wake-up request. equipment.
  • the device identification may include, for example, a device number, a device name, a device IP address, and the like.
  • the target device is triggered to enter a wake-up state, so that the target device responds to the user's wake-up voice.
  • the target device when the target device is triggered to enter the wake-up state, the target device can be controlled to enter the wake-up state by sending a wake-up lock to the target device.
  • the wake-up lock may be actively created by the master control device after acquiring the first wake-up request, and the method for creating the wake-up lock may be implemented by using the prior art, which will not be repeated here.
  • the target device After the target device enters the wake-up state, it can respond to the user's wake-up voice to prompt the user that the device is in the wake-up state. Specifically, the target device can respond to the user's wake-up voice through sound effects or lighting effects. For example, the target device can play the voice "I'm here" in response to the user's wake-up voice, or the target device can continuously emit light through its built-in light-emitting device. Or flashing light in response to the user's wake-up voice.
  • the target device in the awake state can receive the user's voice request and respond to the voice request.
  • the target device can send the received user's voice request to the cloud server, and the cloud server obtains response data according to the user's voice request, and returns the response data to the target device, so that the target device can play the obtained response data to user.
  • the user's voice request received by the target device is "how is the weather today"
  • the target device sends the received voice request to the cloud server, and the cloud server obtains the weather information of the day according to the voice request, and returns the weather information of the current day.
  • the target device plays the weather information of the day to the user to realize voice interaction with the user.
  • the method of the embodiment of the present disclosure may further include determining whether a request to release the wakelock sent by the target device is received within a preset period of time after the wake-up lock is sent to the target device, and no release is received within the preset period of time.
  • the wake lock is released. If no wakelock release request from the target device is received within a preset period of time, it means that the target device may be in an abnormal operating state. Specifically, the target device may be disconnected (for example, the power cord of the target device is unplugged) or downtime. In order to ensure that the normal wake-up of other devices is not affected, the wake-up lock sent to the target device needs to be released at this time.
  • the method of releasing the wake-up lock can be realized by setting the state of the wake-up lock to 0.
  • a wake-up lock release instruction is returned to the target device to instruct the target device to release the wake-up lock.
  • the method for the target device to release the wake-up lock can be determined by Status bit 0 is implemented. After the target device completes the voice interaction with the user, the wake-up lock is released in time, which is beneficial to ensure that the subsequent wake-up of other devices is not affected.
  • FIG. 2B schematically shows a schematic diagram of a voice wake-up system in an embodiment of the present disclosure.
  • the voice wake-up system includes a speaker 1, a speaker 2, and a speaker 3, wherein the speaker 1 is the main control.
  • Devices, Speaker 2 and Speaker 3 are other devices that are wirelessly connected to Speaker 1.
  • Speakers 2 and 3 are far away from the user, and the time to obtain the user's wake-up voice is different, and the time for speaker 2 and speaker 3 to send a wake-up request to speaker 1 is also different.
  • Speaker 1 first receives the first wake-up request from speaker 2, determines speaker 2 as the target speaker, and sends a wake-up lock to speaker 2.
  • the speaker 2 enters the wake-up state after receiving the wake-up lock, and responds to the user's wake-up voice by playing the voice "I am" to remind the user that the speaker 2 is in the wake-up state. At this time, if the speaker 1 continues to receive the wake-up request sent by the speaker 3, it does not respond to the wake-up request from the speaker 3, or sends a reminder message to the speaker 3 that the wake-up fails.
  • the master device receives the first wake-up request from the device, determines the target device to be woken up according to the first wake-up request, and triggers the target device to enter the wake-up state, so that the target device responds to the user's wake-up voice.
  • the target device to be woken up is determined according to the first wake-up request.
  • the first wake-up request is the first wake-up request received by the main control device. Therefore, for the user's wake-up voice, a single device is woken up, which can effectively solve the problem of repeated response and response interference.
  • Each device sends a wake-up request to the master device in the same local area network. Compared with the related art in which each device sends a wake-up request to the cloud server, this solution can effectively solve the problem of obvious response delay and large network bandwidth consumption. .
  • FIG. 3A schematically shows a flowchart of a method for waking up a device according to another embodiment of the present disclosure.
  • operation S220 may specifically include operations S310 to S330.
  • At least one second wake-up request is received, wherein the first wake-up request and each second wake-up request include sound features of the wake-up voice acquired by the device.
  • the second wake-up request is a wake-up request other than the first wake-up request.
  • Other wake-up requests When the second wake-up request is not received within the preset time period, it is determined that the device associated with the first wake-up request is the target device to be woken up; when at least one second wake-up request is received within the preset time period, according to the first wake-up request The wake-up request and the at least one second wake-up request determine the target device to be woken up. The following description will be given in the case where at least one second wake-up request is received within a preset time period.
  • the sound quality of the wake-up speech acquired by the devices may vary. For example, for the same wake-up voice sent by the user, the sound quality of the wake-up voice obtained by the devices located in front of and behind the user may be significantly different. Therefore, the device that sends the first wake-up request may not be the most suitable for voice interaction with the user. For the device, when the sound quality of the wake-up voice obtained by the first device is not optimal, this also affects the interaction efficiency and interaction quality between the device and the user, and affects the user experience.
  • the wake-up voice with the best sound quality can be screened out It can effectively improve the interaction efficiency and interaction quality, and improve the user experience.
  • the first sound feature can describe the sound quality of the wake-up voice obtained by the device that sends the first wake-up request
  • the second sound feature can describe the wake-up sound obtained by the device that sends each second wake-up request.
  • the first sound feature and the second sound feature may include, for example, sound volume, sound intensity, sound signal-to-noise ratio, sound sound pressure intensity, and the like.
  • the master control device may, among m wake-up requests received first, determine that the device targeted for the wake-up request with the maximum volume characteristic is the target device to be woken up, where m is an integer greater than 1.
  • the first sound feature may be acquired by the device sending the first wake-up request and integrated into the first wake-up request.
  • the device extracts the voice feature of the acquired wake-up voice through a voice feature extraction algorithm to obtain the first sound feature.
  • the second sound feature may also be acquired by the device sending the second wake-up request and integrated into the second wake-up request.
  • the sound feature with the highest priority is determined as the target sound feature, and the device associated with the target sound feature is used as the target device.
  • the first sound feature and each second sound feature may be compared to obtain a comparison result, and then based on Compare the results, determine the sound feature with the highest priority, and obtain the target sound feature.
  • the sound quality of the wake-up speech targeted by the sound feature with the highest priority is the best.
  • FIG. 3B schematically shows a schematic diagram of a voice wake-up system in another embodiment of the present disclosure.
  • the voice wake-up system includes a speaker 4, a speaker 5 and a speaker 6, wherein the speaker 4 is the main speaker.
  • the speaker 5 and the speaker 6 are other devices that are wirelessly connected to the speaker 4.
  • the speaker 5 and the speaker 6 send wake-up requests to the speaker 4 successively.
  • the speaker 4 first receives the first wake-up request from the speaker 5, and then within a preset time period (for example, it may be 50 ms), the speaker 4 receives the second wake-up request from the speaker 6.
  • the speaker 4 determines the first sound feature in the first wake-up request, and determines the second sound feature in the second wake-up request, and then compares the first sound feature with the second sound feature to determine the priority of the second sound feature higher than the first sound characteristic, so the loudspeaker 6 associated with the second sound characteristic is determined as the target device. After that, Speaker 4 creates a wakelock and sends the wakelock to Speaker 6. The speaker 6 enters the wake-up state after receiving the wake-up lock, and responds to the user's wake-up voice by playing the voice "I am" to remind the user that the speaker 6 is in the wake-up state and can continue to perform voice interaction.
  • the embodiment of the present disclosure may further include generating a third wake-up request in response to the user's wake-up voice.
  • Determining the target device to be woken up according to the first wake-up request may include determining whether the third wake-up request is generated earlier than the first wake-up request is received; the third wake-up request is generated earlier than the first wake-up request is received In the case of time, determine the master device as the target device.
  • the main control device While receiving the wake-up request sent by each device, the main control device can also obtain the user's wake-up voice as the device to be woken up. Specifically, the main control device generates a third wake-up request in response to the user's wake-up voice.
  • the main control device After receiving the first wake-up request from the device, determine whether the generation time of the third wake-up request is earlier than the reception time of the first wake-up request, in the case that the generation time of the third wake-up request is earlier than the reception time of the first wake-up request.
  • the main control device is determined as the target device, and the main control device enters the wake-up state and responds to the user's wake-up voice, which is conducive to further reducing the response delay of the device to the user's wake-up voice response, and is conducive to improving the user experience.
  • the master control device determines, among at least one wake-up request received first, the wake-up request with the highest priority sound feature as the target wake-up request, and takes the device that sends the target wake-up request as the target device to be woken up , which is conducive to improving the interaction efficiency between the device and the user, and improving the interaction effect between the device and the user, and also effectively solves the problem of response interference caused by the simultaneous wake-up of multiple devices. Since each device does not need to send a wake-up request to the cloud server, this solution is also beneficial to reduce the device response delay and network bandwidth consumption for device wake-up.
  • FIG. 4 schematically shows a flowchart of a method for waking up a device according to another embodiment of the present disclosure.
  • the method may include, for example, operations S410 to S420.
  • the main control device in response to receiving the wake-up lock returned by the main control device, enter the wake-up state and respond to the user's wake-up voice.
  • a wake-up lock release request to the main control device, and in response to receiving the response command returned by the main control device, actively Release the wakelock.
  • the method of actively releasing the wakelock can be realized by setting the status bit of the wakelock to 0.
  • a detection signal sent by the main control device at a preset frequency is received, and in response to the received detection signal, a detection response signal is returned to the main control device to indicate that the device operates normally.
  • FIG. 5 schematically shows a block diagram of a master device according to an embodiment of the present disclosure.
  • the main control device includes a first receiving module 501 , a first determining module 502 and a first processing module 503 .
  • the first receiving module 501 is configured to receive a first wake-up request from the device, wherein the first wake-up request is the first wake-up request received by the main control device; the first determining module 502 is configured to, according to the first wake-up request, Determine the target device to be woken up; the first processing module 503 is configured to trigger the target device to enter the wake-up state, so that the target device responds to the user's wake-up voice.
  • the master device receives the first wake-up request from the device, determines the target device to be woken up according to the first wake-up request, and triggers the target device to enter the wake-up state, so that the target device responds to the user's wake-up voice.
  • the target device to be woken up is determined according to the first wake-up request.
  • the first wake-up request is the first wake-up request received by the main control device. Therefore, a single device is woken up for the user's wake-up voice, which can effectively solve the problem of repeated response and response interference.
  • Each device sends a wake-up request to the master device in the same local area network. Compared with the related art in which each device sends a wake-up request to the cloud server, this solution can effectively solve the problem of obvious response delay and large network bandwidth consumption. .
  • the first determination module includes a first determination submodule, configured to determine the first device that sends the first wake-up request as the target device.
  • the first determining module includes a first receiving sub-module, configured to receive at least one second wake-up request within a preset time period after receiving the first wake-up request; the first obtaining sub-module, Used to obtain the first voice parameter in the first wake-up request, and obtain the second voice parameter in each second wake-up request, wherein the first voice parameter is the voice of the wake-up voice received by the first device that sent the first wake-up request parameter, the second voice parameter is the voice parameter of the wake-up voice received by the second device that sends each second wake-up request; the second determination submodule is used to determine the voice parameter with the highest priority among the first voice parameter and the second voice parameter is the target voice parameter, and the device that receives the wake-up voice targeted by the target voice parameter is determined as the target device.
  • the first voice parameter is the voice of the wake-up voice received by the first device that sent the first wake-up request parameter
  • the second voice parameter is the voice parameter of the wake-up voice received by the second device that sends each second wake-up
  • the first processing module includes a first processing submodule, configured to send a wake-up lock to the target device, so that the target device enters a wake-up state.
  • the master control device further includes a second determination module, configured to determine whether a request to release the wake-up lock sent by the target device is received within a preset time period after the wake-up lock is sent to the target device; the second The processing module is used for releasing the wake-up lock when the request for releasing the wake-up lock is not received within a preset time period.
  • the main control device further includes a third processing module for generating a third wake-up request in response to the user's wake-up voice; the first determination module includes a third determination sub-module for determining the third wake-up request. Whether the generation time of the third wake-up request is earlier than the reception time of the first wake-up request; and a fourth determination sub-module for determining the main The control device is the target device.
  • the main control device further includes a second receiving module, configured to receive a detection signal sent by at least one device at a preset frequency; and a fourth processing module, configured to return a detection response signal to each device.
  • the master control device determines, among at least one wake-up request received first, the wake-up request with the highest priority sound feature as the target wake-up request, and takes the device sending the target wake-up request as the target device to be woken up , which is conducive to improving the interaction efficiency between the device and the user, and improving the interaction effect between the device and the user, and also effectively solves the problem of response interference caused by the simultaneous wake-up of multiple devices. Since each device does not need to send a wake-up request to the cloud server, this solution is also beneficial to reduce the device response delay and network bandwidth consumption for device wake-up.
  • any of the modules, sub-modules, or at least part of the functions of any of the modules according to the embodiments of the present disclosure may be implemented in one module. Any one or more of the modules according to the embodiments of the present disclosure may be split into multiple modules for implementation. Any one or more of the modules according to embodiments of the present disclosure may be implemented, at least in part, as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, A system-on-package, an application specific integrated circuit (ASIC), or any other reasonable hardware or firmware implementation that integrates or encapsulates a circuit, or any one of software, hardware, and firmware implementations or It can be realized by any suitable combination of any of them. Alternatively, one or more of the modules according to embodiments of the present disclosure may be implemented at least in part as computer program modules that, when executed, may perform corresponding functions.
  • FPGAs field programmable gate arrays
  • PLAs programmable logic arrays
  • any one of the first receiving module 501 , the first determining module 502 and the first processing module 503 may be combined into one module for implementation, or any one of the modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module.
  • At least one of the first receiving module 501, the first determining module 502, and the first processing module 503 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array ( PLA), system-on-chip, system-on-substrate, system-on-package, application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuits, such as hardware or firmware, or in software, hardware and any one of the three implementation manners of firmware or an appropriate combination of any of them.
  • FPGA field programmable gate array
  • PLA programmable logic array
  • ASIC application-specific integrated circuit
  • at least one of the first receiving module 501 , the first determining module 502 and the first processing module 503 may be implemented at least partially as a computer program module, and when executed, the computer program module may perform corresponding functions.
  • FIG. 6 schematically shows a block diagram of a computer system suitable for a device wake-up method and system according to an embodiment of the present disclosure.
  • the computer system shown in FIG. 6 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.
  • a computer system 600 includes a processor 601 that can be loaded into a random access memory (RAM) 603 according to a program stored in a read only memory (ROM) 602 or from a storage portion 608 program to perform various appropriate actions and processes.
  • the processor 601 may include, for example, a general-purpose microprocessor (eg, a CPU), an instruction set processor and/or a related chipset, and/or a special-purpose microprocessor (eg, an application-specific integrated circuit (ASIC)), among others.
  • the processor 601 may also include on-board memory for caching purposes.
  • the processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiments of the present disclosure.
  • the processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604.
  • the processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the programs in the ROM 602 and/or the RAM 603.
  • the program may also be stored in one or more memories other than ROM 602 and RAM 603.
  • the processor 601 may also perform various operations of the method flow according to the embodiments of the present disclosure by executing programs stored in the one or more memories.
  • the system 600 may also include an input/output (I/O) interface 606 , which is also connected to the bus 604 .
  • the system 600 may also include one or more of the following components connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc; An output section 607 including a hard disk, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, and the like.
  • the communication section 609 performs communication processing via a network such as the Internet.
  • a drive 610 is also connected to the I/O interface 605 as needed.
  • a removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.
  • the method flow according to the embodiment of the present disclosure may be implemented as a computer software program.
  • embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via the communication portion 609 and/or installed from the removable medium 611 .
  • the computer program is executed by the processor 601
  • the above-described functions defined in the system of the embodiment of the present disclosure are performed.
  • the systems, apparatuses, apparatuses, modules, units, etc. described above may be implemented by computer program modules.
  • the present disclosure also provides a computer-readable storage medium.
  • the computer-readable storage medium may be included in the device/apparatus/system described in the above embodiments; it may also exist alone without being assembled into the device/system. device/system.
  • the above-mentioned computer-readable storage medium carries one or more programs, and when the above-mentioned one or more programs are executed, implement the method according to the embodiment of the present disclosure.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as, but not limited to, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • the computer-readable storage medium may optionally include one or more memories other than ROM 602 and/or RAM 603 and/or ROM 602 and RAM 603 described above.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Selective Calling Equipment (AREA)

Abstract

本公开提供了一种设备唤醒方法，该方法可以包括以下操作：接收来自设备的第一唤醒请求，其中，所述第一唤醒请求为所述主控设备接收到的首个唤醒请求；根据所述第一唤醒请求，确定待唤醒的目标设备；触发所述目标设备进入唤醒状态，以使所述目标设备响应用户的唤醒语音。本公开还提供了一种主控设备、一种电子设备及一种计算机可读存储介质。

Description

设备唤醒方法及装置
本申请要求于2020年8月13日提交的、申请号为202010815397.5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
本公开涉及控制技术领域，更具体地，涉及一种设备唤醒方法、一种主控设备、一种电子设备以及一种计算机可读存储介质。
背景技术
随着语音识别技术的迅速发展，越来越多的设备设置了语音唤醒功能。针对具有语音唤醒功能的设备，用户在设备周围发出预设的唤醒语音后，即可实现对设备进行唤醒。
在实现本公开构思过程中，发明人发现当具有相同唤醒词的多个设备共存时，在用户发出预设的唤醒语音后，多个设备进入唤醒状态并对唤醒语音进行响应，这存在设备重复响应、响应干扰的问题；或者，多个设备向云端服务器发送唤醒请求，由云端服务器根据唤醒请求确定待唤醒的目标设备，然后触发目标设备进入唤醒状态并对唤醒语音进行响应，这存在响应延迟、数据带宽消耗高的问题。
发明内容
有鉴于此，本公开提供了一种响应干扰小、响应延迟低、数据带宽消耗低的设备唤醒方法及装置。
本公开的一个方面提供了一种设备唤醒方法，应用于主控设备，包括接收来自设备的第一唤醒请求，其中，上述第一唤醒请求为上述主控设备接收到的首个唤醒请求；根据上述第一唤醒请求，确定待唤醒的目标设备；以及触发上述目标设备进入唤醒状态，以使上述目标设备响应用户的唤醒语音。
可选地，上述根据上述第一唤醒请求，确定待唤醒的目标设备，包括确定发送上述第一唤醒请求的第一设备，以作为上述目标设备。
可选地，上述根据上述第一唤醒请求，确定待唤醒的目标设备，包括在接收到上述第一唤醒请求后的预设时长内，接收至少一个第二唤醒请求，其中，上述第一唤醒请求和各上述第二唤醒请求中包含设备所获取的唤醒语音的声音 特征；确定上述第一唤醒请求中的第一声音特征和各上述第二唤醒请求中的第二声音特征；在上述第一声音特征和各上述第二声音特征中，确定优先级最高的声音特征为目标声音特征，并将与上述目标声音特征关联的设备作为目标设备。
可选地，上述触发上述目标设备进入唤醒状态，包括向上述目标设备发送唤醒锁，以使上述目标设备进入唤醒状态。
可选地，上述方法还包括在向上述目标设备发送上述唤醒锁后的预设时长内，确定是否接收到上述目标设备发送的释放唤醒锁请求；以及，在上述预设时长内未接收到上述释放唤醒锁请求的情况下，对上述唤醒锁进行释放处理。
可选地，上述方法还包括响应于上述用户的唤醒语音，生成第三唤醒请求；上述根据上述第一唤醒请求，确定待唤醒的目标设备，包括确定上述第三唤醒请求的生成时间是否早于上述第一唤醒请求的接收时间；以及，在上述第三唤醒请求的生成时间早于上述第一唤醒请求的接收时间的情况下，确定上述主控设备为上述目标设备。
可选地，上述方法还包括接收至少一个设备以预设频率发送的探测信号；向各上述设备返回探测响应信号。
本公开的另一个方面提供了一种主控设备，包括第一接收模块，用于接收来自设备的第一唤醒请求，其中，上述第一唤醒请求为上述主控设备接收到的首个唤醒请求；第一确定模块，用于根据上述第一唤醒请求，确定待唤醒的目标设备；第一处理模块，用于触发上述目标设备进入唤醒状态，以使上述目标设备响应用户的唤醒语音。
可选地，上述第一确定模块，包括第一确定子模块，用于确定发送上述第一唤醒请求的第一设备，以作为上述目标设备。
可选地，上述第一确定模块，包括第一接收子模块，用于在接收到上述第一唤醒请求后的预设时长内，接收至少一个第二唤醒请求，其中，所述第一唤醒请求和各所述第二唤醒请求中包含设备所获取的唤醒语音的声音特征；第二确定子模块，用于确定所述第一唤醒请求中的第一声音特征和各所述第二唤醒请求中的第二声音特征；第三确定子模块，用于在上述第一声音特征和各上述第二声音特征中，确定优先级最高的声音特征为目标声音特征，并将与上述目标声音特征关联的设备作为目标设备。
可选地，上述第一处理模块，包括第一处理子模块，用于向上述目标设备发送唤醒锁，以使上述目标设备进入唤醒状态。
可选地，上述设备还包括第二确定模块，用于在向上述目标设备发送上述唤醒锁后的预设时长内，确定是否接收到上述目标设备发送的释放唤醒锁请求；第四处理模块，用于在上述预设时长内未接收到上述释放唤醒锁请求的情况下，对上述唤醒锁进行释放处理。
可选地，上述设备还包括第五处理模块，用于响应于上述用户的唤醒语音，生成第三唤醒请求；上述第一确定模块，包括第四确定子模块，用于确定上述第三唤醒请求的生成时间是否早于上述第一唤醒请求的接收时间；以及，第五确定子模块，用于在上述第三唤醒请求的生成时间早于上述第一唤醒请求的接收时间的情况下，确定上述主控设备为上述目标设备。
可选地，上述设备还包括第二接收模块，用于接收至少一个设备以预设频率发送的探测信号；第六处理模块，用于向各上述设备返回探测响应信号。
本公开的另一个方面提供了一种设备唤醒方法，包括在获取到用户的唤醒语音后，生成唤醒请求，并将上述唤醒请求发送给主控设备；响应于接收到上述主控设备返回的唤醒指令，进入唤醒状态并对上述用户的唤醒语音进行响应。
可选地，上述响应于接收到上述主控设备返回的唤醒指令，进入唤醒状态并对上述用户的唤醒语音进行响应，包括响应于接收到上述主控设备返回的唤醒锁，进入唤醒状态并对上述用户的唤醒语音进行响应。
可选地，还包括在接收到上述唤醒锁后的预设时长内，向上述主控设备发送释放唤醒锁请求；响应于接收到上述主控设备返回的应答指令，释放上述唤醒锁。
可选地，还包括接收上述主控设备以预设频率发送的探测信号；向上述主控设备返回探测响应信号。
本公开的另一个方面提供了一种设备，包括第二处理模块，用于在获取到用户的唤醒语音后，生成唤醒请求，并将上述唤醒请求发送给主控设备；第三处理模块，用于响应于接收到上述主控设备返回的唤醒指令，进入唤醒状态并对上述用户的唤醒语音进行响应。
本公开的另一个方面提供了一种电子设备，包括一个或多个处理器；以及存储器，用于存储一个或多个程序，其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现本公开实施例的方法。
本公开的另一个方面提供了一种计算机可读存储介质，其上存储有可执行指令，该指令被处理器执行时使处理器实现本公开实施例的方法。
在本公开实施例中，主控设备接收来自设备的第一唤醒请求，根据第一唤醒请求，确定待唤醒的目标设备，并触发目标设备进入唤醒状态，以使目标设备响应用户的唤醒语音。根据第一唤醒请求确定待唤醒的目标设备，第一唤醒请求为主控设备接收到的首个唤醒请求，因此，针对用户的唤醒语音存在单个设备被唤醒，这能够有效解决响应重复、响应干扰的问题；各设备向处于同一局域网中的主控设备发送唤醒请求，相比于相关技术中的各设备向云端服务器发送唤醒请求，本方案能够有效解决响应延时明显，网络带宽消耗大的问题。
附图说明
为了更完整地理解本公开及其优势，现在将参考结合附图的以下描述，其中：
图1示意性示出了根据本公开实施例的设备唤醒方法的系统架构；
图2A示意性示出了根据本公开一实施例的设备唤醒方法的流程图；
图2B本公开一实施例中的语音唤醒系统的示意图；
图3A示意性示出了根据本公开另一实施例的设备唤醒方法的流程图；
图3B示意性示出了本公开又一实施例中的语音唤醒系统的示意图；
图4示意性示出了根据本公开再一实施例的设备唤醒方法的流程图；
图5示意性示出了根据本公开实施例的主控设备的框图；
图6示意性示出了根据本公开实施例的适于实现设备唤醒方法和装置的电子设备的框图。
具体实施方式
以下，将参照附图来描述本公开的实施例。但是应该理解，这些描述只是示例性地，而并非要限制本公开的范围。在下面的详细描述中，为便于解释，阐述了许多具体的细节以提供对本公开实施例的全面理解。然而，明显地，一个或多个实施例在没有这些具体细节的情况下也可以被实施。此外，在以下说明中，省略了对公知结构和技术的描述，以避免不必要地混淆本公开的概念。
在此使用的术语仅仅是为了描述具体实施例，而并非意在限制本公开。在此使用的术语“包括”、“包含”等表明了所述特征、步骤、操作和/或部件的存在，但是并不排除存在或添加一个或多个其他特征、操步骤、操作或部件。
在此使用的所有术语(包括技术和科学术语)具有本领域技术人员通常所理解的含义，除非另外定义。应注意，这里使用的术语应解释为具有与本说明书的上下文相一致的含义，而不应以理想化或过于刻板的方式来解释。
在使用类似于“A、B和C等中至少一个”这样的表述的情况下，一般来说应该按照本领域技术人员通常理解该表述的含义来予以解释(例如，“具有A、B和C中至少一个的系统”应包括但不限于单独具有A、单独具有B、单独具有C、具有A和B、具有A和C、具有B和C、和/或具有A、B、C的系统等)。
本公开的各个实施例提供了一种设备唤醒方法以及能够应用该方法的主控设备。其中，该方法可以包括接收来自设备的第一唤醒请求，其中，第一唤醒请求为主控设备接收到的首个唤醒请求，然后根据第一唤醒请求，确定待唤醒的目标设备，之后触发目标设备进入唤醒状态，以使目标设备响应用户的唤醒语音。
如图1所示，该系统架构100包括接入同一局域网中的至少一个具有语音唤醒功能的设备(图中示出了多个，如设备101、102、103)和主控设备104。在该系统架构100中，主控设备104接收来自设备(如设备101、102、103)的第一唤醒请求，其中，第一唤醒请求为主控设备接收到的首个唤醒请求，然后根据第一唤醒请求，确定待唤醒的目标设备，之后触发目标设备进入唤醒状态，以使目标设备响应用户的唤醒语音。
以下将结合附图和具体实施例详细阐述本公开。
图2A示意性示出了根据本公开一实施例的设备唤醒方法的流程图。
如图2A所示，该方法例如可以包括操作S210～S230。
在操作S210，接收来自设备的第一唤醒请求，其中，第一唤醒请求为主控设备接收到的首个唤醒请求。
在本公开实施例中，具体地，主控设备接收来自设备的第一唤醒请求，其中，设备可以是具有语音唤醒功能的用户终端，例如可以是移动设备(例如，移动电话、个人数字助理)、智能音箱、平板电脑、台式计算机、空调等设备。主控设备用于在至少一个设备中，确定出对用户的唤醒语音进行响应的目标设备，主控设备与其他设备之间可以通过有线或无线方式连接。
具有相同或相似唤醒词的多个设备通过局域网互相关联，构成语音唤醒系统。语音唤醒系统中的每个设备可以通过mDNS或类似的探测技术，实时或定时地探测系统中的其他设备，并将新探测到的其他设备(例如可以是新接入局域网中的设备)记录在自身的设备列表中，或者将无法探测到的设备(例如可以是掉线或者宕机的设备)从自身的设备列表中删除。
在执行本公开实施例的方法之前，语音唤醒系统中的各设备可以通过Leader选举算法，选举出主控设备，然后由主控设备控制其他设备的唤醒功能，其中，leader选举算法例如可以是raft协议、Bully选举算法、kafka选举算法或ZooKeeper中提供的其他选举算法。在选举出主控设备后，其他设备以预设频率向主控设备发送探测信号，用于探测主控设备是否工作正常，主控设备在接收到来自其他设备的探测信号后，向其他设备返回探测响应信号。同时，主控设备也会定期向各其他设备发送探测信号，用于确定各其他设备是否工作正常，各其他设备在接收到来自主控设备的探测信号后，也需向主控设备返回探测响应信号。
当主控设备未在预设时间内返回探测响应信号时，确定主控设备运行状态异常，运行状态异常的原因可以包括主控设备掉线或者发生宕机等。此时，语音唤醒系统中的其他设备需要重新选举新的主控设备，然后由新的主控设备控制其他设备的唤醒功能。
当语音唤醒系统中的各设备获取到来自用户的唤醒语音后，识别唤醒语音中的唤醒词并生成唤醒请求，然后将唤醒请求发送给主控设备，以请求响应用户的唤醒语音并进入唤醒状态。由于不同设备距离用户的远近可能不同，距离用户越近的设备，越先获取到用户的唤醒语音，获取到的唤醒语音的声音质量也较佳，生成唤醒请求并将唤醒请求发送至主控设备的速度也越快，因此，主控设备可以根据接收到的唤醒请求的时间顺序，确定各个设备距离用户的远近关系。主控设备接收来自设备的第一唤醒请求，第一唤醒请求为主控设备接收到的首个唤醒请求，根据第一唤醒请求确定待唤醒的目标设备，可以有效提高设备唤醒效率，和减少设备响应时差。
接下来，在操作S220，根据第一唤醒请求，确定待唤醒的目标设备。
在本公开实施例中，具体地，在根据第一唤醒请求，确定待唤醒的目标设备时，可以根据第一唤醒请求，确定发送第一唤醒请求的设备，以作为待唤醒的目标设备。对于各设备而言，相比于获取来自用户的唤醒语音、识别唤醒语 音中的唤醒词并生成唤醒请求的过程，将唤醒请求发送给主控设备的耗时可以忽略不计。由于第一唤醒请求为主控设备接收到的首个唤醒请求，因此可确定发送第一唤醒请求的设备为最先获取到用户的唤醒语音的设备，也即为距离用户最近的设备。距离用户最近的设备获取到的用户语音的声音质量较佳，对用户响应的耗时也较短，因此，可将距离用户最近的设备确定为待唤醒的目标设备，即可将发送第一唤醒请求的设备确定为待唤醒的目标设备。
第一唤醒请求中包括发送设备的设备标识，在根据第一唤醒请求，确定发送第一唤醒请求的设备时，可以根据第一唤醒请求中携带的设备标识，确定设备标识所指示的设备为目标设备。其中，设备标识例如可以包括设备编号、设备名称、设备IP地址等。
接下来，在操作S230，触发目标设备进入唤醒状态，以使目标设备响应用户的唤醒语音。
在本公开实施例中，具体地，在触发目标设备进入唤醒状态时，可通过向目标设备发送唤醒锁的方式，控制目标设备进入唤醒状态。其中，唤醒锁可以由主控设备在获取到第一唤醒请求后主动创建，唤醒锁的创建方法可以采用现有技术实现，此处不再赘述。
目标设备进入唤醒状态后，可以针对用户的唤醒语音做出响应，以提示用户本设备已处于唤醒状态。具体地，目标设备可以通过音效或灯效方式来响应用户的唤醒语音，例如，目标设备可以播放语音“我在”来响应用户的唤醒语音，或者，目标设备可以通过自带的发光装置持续发光或闪烁发光来响应用户的唤醒语音。
处于唤醒状态的目标设备能够接收用户的语音请求，并对语音请求做出响应。具体地，目标设备可以将接收到的用户的语音请求发送给云端服务器，云端服务器根据用户的语音请求获取响应数据，并将响应数据返回给目标设备，以供目标设备将获取的响应数据播放给用户。示例性地，目标设备接收到的用户的语音请求为“今天天气怎么样”，目标设备将接收到的语音请求发送给云端服务器，云端服务器根据语音请求获取当日天气信息，并将当日天气信息返回给目标设备，目标设备向用户播放当日天气信息，实现与用户的语音交互。
可选地，本公开实施例的方法还可以包括在向目标设备发送唤醒锁后的预设时长内，确定是否接收到目标设备发送的释放唤醒锁请求，并且在预设时长内未接收到释放唤醒锁请求的情况下，对唤醒锁进行释放处理。在预设时长内 未接收到目标设备的释放唤醒锁请求，说明目标设备运行状态可能异常，具体可能是目标设备掉线(例如，目标设备电源线被拔)或发生宕机等。为保证不对其他设备的正常唤醒造成影响，此时需要对发送至目标设备的唤醒锁进行释放处理，对唤醒锁进行释放处理的方法可通过对唤醒锁的状态位置0来实现。
此外，若在预设时长内接收到来自目标设备的释放唤醒锁请求，则向目标设备返回释放唤醒锁指示，以指示目标设备释放唤醒锁，目标设备释放唤醒锁的方法可通过对唤醒锁的状态位置0来实现。在目标设备完成与用户的语音交互后，及时释放唤醒锁，有利于保证不对其他设备的后续唤醒造成影响。
示例性地，图2B示意性示出了本公开一实施例中的语音唤醒系统的示意图，如图2B所示，该语音唤醒系统包括音箱1、音箱2和音箱3，其中音箱1为主控设备，音箱2和音箱3为与音箱1无线连接的其他设备。音箱2、音箱3距离用户远近不同，获取到用户的唤醒语音的时间不同，音箱2、音箱3向音箱1发送唤醒请求的时间也不同。音箱1最先接收到来自音箱2的第一唤醒请求，将音箱2确定为目标音箱并向音箱2发送唤醒锁。音箱2在接收到唤醒锁后进入唤醒状态，通过播放语音“我在”来响应用户的唤醒语音，以提醒用户音箱2已处于唤醒状态。此时，音箱1若继续接收到音箱3发送的唤醒请求，不对音箱3的唤醒请求做出响应，或者向音箱3发送唤醒失败的提示消息。
在本公开实施例中，主控设备接收来自设备的第一唤醒请求，根据第一唤醒请求，确定待唤醒的目标设备，并触发目标设备进入唤醒状态，以使目标设备响应用户的唤醒语音。根据第一唤醒请求确定待唤醒的目标设备，第一唤醒请求为主控设备接收到的首个唤醒请求，因此，针对用户的唤醒语音存在单个设备被唤醒，这能够有效解决响应重复、响应干扰的问题；各设备向处于同一局域网中的主控设备发送唤醒请求，相比于相关技术中的各设备向云端服务器发送唤醒请求，本方案能够有效解决响应延时明显，网络带宽消耗大的问题。
图3A示意性示出了根据本公开另一实施例的设备唤醒方法的流程图。
如图3A所示，操作S220具体可以包括操作S310～S330。
在操作S310，在接收到第一唤醒请求后的预设时长内，接收至少一个第二唤醒请求，其中，第一唤醒请求和各第二唤醒请求中包含设备所获取的唤醒语音的声音特征。
在本公开实施例中，具体地，在接收到首个唤醒请求后的预设时长内，确定是否接收到来自其他设备的第二唤醒请求，第二唤醒请求即为除首个唤醒请 求以外的其他唤醒请求。当未在预设时长内接收到第二唤醒请求时，确定与第一唤醒请求关联的设备为待唤醒的目标设备；当在预设时长内接收到至少一个第二唤醒请求时，根据第一唤醒请求和至少一个第二唤醒请求，确定待唤醒的目标设备。以下以在预设时长内接收到至少一个第二唤醒请求的情况进行说明。
由于各设备所处的位置不同，与用户间的距离不同，这导致各设备获取的唤醒语音的声音质量可能存在差异。例如，针对用户发出的同一唤醒语音，位于用户前、后方的设备所获取的唤醒语音的声音质量可能存在显著差异，因此，发送第一唤醒请求的设备不一定是最适合与用户进行语音交互的设备，当第一设备获取的唤醒语音的声音质量不是最佳时，这同样会影响设备和用户间的交互效率与交互质量，影响用户体验。
在接收到第一唤醒请求后的预设时长内，接收至少一个第二唤醒请求，通过将第一唤醒请求和各第二唤醒请求进行比对，能够筛选出接收到声音质量最佳的唤醒语音的设备，将该设备作为目标设备与用户进行语音交互，能够有效提升交互效率和交互质量，改善用户体验。
接下来，在操作S320，确定第一唤醒请求中的第一声音特征和各第二唤醒请求中的第二声音特征。
在本公开实施例中，具体地，第一声音特征能够描述发送第一唤醒请求的设备所获取的唤醒语音的声音质量，第二声音特征能够描述发送各第二唤醒请求的设备所获取的唤醒语音的声音质量。其中，第一声音特征和第二声音特征例如可以包括声音音量、声音强度、声音信噪比、声音声压强度等。示例性地，主控设备可以在最先接收到的m个唤醒请求中，确定具有最大音量特征的唤醒请求所针对的设备为待唤醒的目标设备，其中，m为大于1的整数。
第一声音特征可以由发送第一唤醒请求的设备获取并整合入第一唤醒请求中，设备通过语音特征提取算法，对获取的唤醒语音进行语音特征提取，得到第一声音特征。同理，第二声音特征也可以由发送第二唤醒请求的设备获取并整合入第二唤醒请求中。
接下来，在操作S330，在第一声音特征和各第二声音特征中，确定优先级最高的声音特征为目标声音特征，并将与目标声音特征关联的设备作为目标设备。
在本公开实施例中，具体地，在确定第一声音特征和各第二声音特征的优先级时，可以将第一声音特征及各第二声音特征进行比对，得到比对结果，然 后基于比对结果，确定优先级最高的声音特征，得到目标声音特征。其中，优先级最高的声音特征所针对的唤醒语音的声音质量最好。
示例性地，图3B示意性示出了本公开又一实施例中的语音唤醒系统的示意图，如图3B所示，该语音唤醒系统包括音箱4、音箱5和音箱6，其中音箱4为主控设备，音箱5和音箱6为与音箱4无线连接的其他设备。当获取到用户发出的唤醒语音时，音箱5和音箱6先后向音箱4发送唤醒请求。音箱4首先接收到来自音箱5的第一唤醒请求，然后在预设时长内(例如可以是50ms)，音箱4接收到来自音箱6的第二唤醒请求。音箱4确定第一唤醒请求中的第一声音特征，和确定第二唤醒请求中的第二声音特征，然后将第一声音特征和第二声音特征进行比对，确定第二声音特征的优先级高于第一声音特征，因此将与第二声音特征关联的音箱6确定为目标设备。之后，音箱4创建唤醒锁并将唤醒锁发送至音箱6。音箱6在接收到唤醒锁后进入唤醒状态，通过播放语音“我在”来响应用户的唤醒语音，以提醒用户音箱6已处于唤醒状态，可以继续进行语音交互。
可选地，本公开实施例还可以包括响应于用户的唤醒语音，生成第三唤醒请求。根据第一唤醒请求，确定待唤醒的目标设备，可以包括确定第三唤醒请求的生成时间是否早于第一唤醒请求的接收时间；在第三唤醒请求的生成时间早于第一唤醒请求的接收时间的情况下，确定主控设备为目标设备。
主控设备在接收各设备发送的唤醒请求的同时，还能作为待唤醒设备获取用户的唤醒语音，具体地，主控设备响应于用户的唤醒语音，生成第三唤醒请求。在接收到来自设备的第一唤醒请求后，确定第三唤醒请求的生成时间是否早于第一唤醒请求的接收时间，在第三唤醒请求的生成时间早于第一唤醒请求的接收时间的情况下，确定主控设备为目标设备，主控设备进入唤醒状态并对用户的唤醒语音做出响应，这有利于进一步降低设备对用户唤醒语音响应的响应延迟，有利于提升用户使用体验。
在本公开实施例中，主控设备在最先接收到的至少一个唤醒请求中，确定具有最高优先级声音特征的唤醒请求为目标唤醒请求，将发送目标唤醒请求的设备作为待唤醒的目标设备，这有利于提高设备与用户间的交互效率，和改善设备与用户间的交互效果，同时也有效解决了多设备同时唤醒造成的响应干扰的问题。由于各设备不需向云端服务器发送唤醒请求，因此本方案还有利于减小设备响应延迟，减少设备唤醒的网络带宽消耗。
图4示意性示出了根据本公开另一实施例的设备唤醒方法的流程图。
如图4所示，该方法例如可以包括操作S410～S420。
在操作S410，在获取到用户的唤醒语音后，生成唤醒请求，并将唤醒请求发送给主控设备；
在操作S420，响应于接收到主控设备返回的唤醒指令，进入唤醒状态并对用户的唤醒语音进行响应。
可选地，响应于接收到主控设备返回的唤醒锁，进入唤醒状态并对用户的唤醒语音进行响应。在接收到唤醒锁后的预设时长内，或者在对用户的语音请求完成响应的预设时长内，向主控设备发送释放唤醒锁请求，响应于接收到主控设备返回的应答指令，主动释放唤醒锁。主动释放唤醒锁的方法可通过将唤醒锁的状态位置0实现。
作为一种可选的方式，接收主控设备以预设频率发送的探测信号，并响应于接收到的探测信号，向主控设备返回探测响应信号，以表征设备运行正常。
需要说明的是，在本公开实施例中，本实施例与前述实施例方法对应类似，并且所达到的技术效果也对应类似，在此不再赘述。
图5示意性示出了根据本公开实施例的主控设备的框图。
如图5所示，主控设备包括第一接收模块501、第一确定模块502和第一处理模块503。
具体地，第一接收模块501用于接收来自设备的第一唤醒请求，其中，第一唤醒请求为主控设备接收到的首个唤醒请求；第一确定模块502用于根据第一唤醒请求，确定待唤醒的目标设备；第一处理模块503用于触发目标设备进入唤醒状态，以使目标设备响应用户的唤醒语音。
在本公开实施例中，主控设备接收来自设备的第一唤醒请求，根据第一唤醒请求，确定待唤醒的目标设备，并触发目标设备进入唤醒状态，以使目标设备响应用户的唤醒语音。根据第一唤醒请求确定待唤醒的目标设备，第一唤醒请求为主控设备接收到的首个唤醒请求，因此，针对用户的唤醒语音存在单个设备被唤醒，这能够有效解决响应重复、响应干扰的问题；各设备向处于同一局域网中的主控设备发送唤醒请求，相比于相关技术中的各设备向云端服务器发送唤醒请求，本方案能够有效解决响应延时明显，网络带宽消耗大的问题。
作为一种可选的实施例，第一确定模块包括第一确定子模块，用于确定发送第一唤醒请求的第一设备，以作为目标设备。
作为一种可选的实施例，第一确定模块包括第一接收子模块，用于在接收到第一唤醒请求后的预设时长内，接收至少一个第二唤醒请求；第一获取子模块，用于获取第一唤醒请求中的第一语音参数，和获取各第二唤醒请求中的第二语音参数，其中，第一语音参数为发送第一唤醒请求的第一设备接收的唤醒语音的语音参数，第二语音参数为发送各第二唤醒请求的第二设备接收的唤醒语音的语音参数；第二确定子模块，用于确定第一语音参数和第二语音参数中优先级最高的语音参数为目标语音参数，并将接收到目标语音参数所针对的唤醒语音的设备确定为目标设备。
作为一种可选的实施例，第一处理模块包括第一处理子模块，用于向目标设备发送唤醒锁，以使目标设备进入唤醒状态。
作为一种可选的实施例，主控设备还包括第二确定模块，用于在向目标设备发送唤醒锁后的预设时长内，确定是否接收到目标设备发送的释放唤醒锁请求；第二处理模块，用于在预设时长内未接收到释放唤醒锁请求的情况下，对唤醒锁进行释放处理。
作为一种可选的实施例，主控设备还包括第三处理模块，用于响应于用户的唤醒语音，生成第三唤醒请求；第一确定模块，包括第三确定子模块，用于确定第三唤醒请求的生成时间是否早于第一唤醒请求的接收时间；以及，第四确定子模块，用于在第三唤醒请求的生成时间早于第一唤醒请求的接收时间的情况下，确定主控设备为目标设备。
作为一种可选的实施例，主控设备还包括第二接收模块，用于接收至少一个设备以预设频率发送的探测信号；第四处理模块，用于向各设备返回探测响应信号。
在本公开实施例中，主控设备在最先接收到的至少一个唤醒请求中，确定具有最高优先级声音特征的唤醒请求为目标唤醒请求，将发送目标唤醒请求的设备作为待唤醒的目标设备，这有利于提高设备与用户间的交互效率，和改善设备与用户间的交互效果，同时也有效解决了多设备同时唤醒造成的响应干扰的问题。由于各设备不需向云端服务器发送唤醒请求，因此本方案还有利于减小设备响应延迟，减少设备唤醒的网络带宽消耗。
根据本公开实施例的模块、子模块中的任意多个、或其中任意多个的至少部分功能可以在一个模块中实现。根据本公开实施例的模块中的任意一个或多个可以被拆分成多个模块来实现。根据本公开实施例的模块中的任意一个或多 个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC)，或可以通过对电路进行集成或封装的任何其他的合理方式的硬件或固件来实现，或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者根据本公开实施例的模块中的一个或多个可以至少被部分地实现为计算机程序模块，当该计算机程序模块被运行时，可以执行相应的功能。
例如，第一接收模块501、第一确定模块502和第一处理模块503中的任意多个可以合并在一个模块中实现，或者其中的任意一个模块可以被拆分成多个模块。或者，这些模块中的一个或多个模块的至少部分功能可以与其他模块的至少部分功能相结合，并在一个模块中实现。可选地，第一接收模块501、第一确定模块502和第一处理模块503中的至少一个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC)，或可以通过对电路进行集成或封装的任何其他的合理方式等硬件或固件来实现，或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者，第一接收模块501、第一确定模块502和第一处理模块503中的至少一个可以至少被部分地实现为计算机程序模块，当该计算机程序模块被运行时，可以执行相应的功能。
图6示意性示出了根据本公开实施例的适于设备唤醒方法和系统的计算机系统的方框图。图6示出的计算机系统仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图6所示，根据本公开实施例的计算机系统600包括处理器601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储部分608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。处理器601例如可以包括通用微处理器(例如CPU)、指令集处理器和/或相关芯片组和/或专用微处理器(例如，专用集成电路(ASIC))，等等。处理器601还可以包括用于缓存用途的板载存储器。处理器601可以包括用于执行根据本公开实施例的方法流程的不同动作的单一处理单元或者是多个处理单元。
在RAM 603中，存储有系统600操作所需的各种程序和数据。处理器601、ROM 602以及RAM 603通过总线604彼此相连。处理器601通过执行ROM 602 和/或RAM 603中的程序来执行根据本公开实施例的方法流程的各种操作。需要注意，所述程序也可以存储在除ROM 602和RAM 603以外的一个或多个存储器中。处理器601也可以通过执行存储在所述一个或多个存储器中的程序来执行根据本公开实施例的方法流程的各种操作。
可选地，系统600还可以包括输入/输出(I/O)接口606，输入/输出(I/O)接口605也连接至总线604。系统600还可以包括连接至I/O接口605的以下部件中的一项或多项：包括键盘、鼠标等的输入部分606；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分607；包括硬盘等的存储部分608；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分609。通信部分609经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口605。可拆卸介质611，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器610上，以便于从其上读出的计算机程序根据需要被安装入存储部分608。
可选地，根据本公开实施例的方法流程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读存储介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分609从网络上被下载和安装，和/或从可拆卸介质611被安装。在该计算机程序被处理器601执行时，执行本公开实施例的系统中限定的上述功能。可选地，上文描述的系统、设备、装置、模块、单元等可以通过计算机程序模块来实现。
本公开还提供了一种计算机可读存储介质，该计算机可读存储介质可以是上述实施例中描述的设备/装置/系统中所包含的；也可以是单独存在，而未装配入该设备/装置/系统中。上述计算机可读存储介质承载有一个或者多个程序，当上述一个或者多个程序被执行时，实现根据本公开实施例的方法。
可选地，计算机可读存储介质可以是非易失性的计算机可读存储介质，例如可以包括但不限于：便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。 例如，可选地，计算机可读存储介质可以包括上文描述的ROM 602和/或RAM 603和/或ROM 602和RAM 603以外的一个或多个存储器。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，上述模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图或流程图中的每个方框、以及框图或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
本领域技术人员可以理解，本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合，即使这样的组合或结合没有明确记载于本公开中。特别地，在不脱离本公开精神和教导的情况下，本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合。所有这些组合和/或结合均落入本公开的范围。
以上对本公开的实施例进行了描述。但是，这些实施例仅仅是为了说明的目的，而并非为了限制本公开的范围。尽管在以上分别描述了各实施例，但是这并不意味着各个实施例中的措施不能有利地结合使用。本公开的范围由所附权利要求及其等同物限定。不脱离本公开的范围，本领域技术人员可以做出多种替代和修改，这些替代和修改都应落在本公开的范围之内。

Claims (15)

  1. 一种设备唤醒方法，应用于主控设备，包括：
    接收来自设备的第一唤醒请求，其中，所述第一唤醒请求为所述主控设备接收到的首个唤醒请求；
    根据所述第一唤醒请求，确定待唤醒的目标设备；以及
    触发所述目标设备进入唤醒状态，以使所述目标设备响应用户的唤醒语音。
  2. 根据权利要求1所述的方法，其中，所述根据所述第一唤醒请求，确定待唤醒的目标设备，包括：
    确定发送所述第一唤醒请求的设备，以作为所述目标设备。
  3. 根据权利要求1所述的方法，其中，所述根据所述第一唤醒请求，确定待唤醒的目标设备，包括：
    在接收到所述第一唤醒请求后的预设时长内，接收至少一个第二唤醒请求，其中，所述第一唤醒请求和各所述第二唤醒请求中包含设备所获取的唤醒语音的声音特征；
    确定所述第一唤醒请求中的第一声音特征和各所述第二唤醒请求中的第二声音特征；
    在所述第一声音特征和各所述第二声音特征中，确定优先级最高的声音特征为目标声音特征，并将与所述目标声音特征关联的设备作为目标设备。
  4. 根据权利要求1至3中任一项所述的方法，其中，所述触发所述目标设备进入唤醒状态，包括：
    向所述目标设备发送唤醒锁，以使所述目标设备进入唤醒状态。
  5. 根据权利要求4所述的方法，还包括：
    在向所述目标设备发送所述唤醒锁后的预设时长内，确定是否接收到所述目标设备发送的释放唤醒锁请求；以及
    在所述预设时长内未接收到所述释放唤醒锁请求的情况下，对所述唤醒锁进行释放处理。
  6. 根据权利要求1至3中任一项所述的方法，还包括：
    响应于所述用户的唤醒语音，生成第三唤醒请求；
    所述根据所述第一唤醒请求，确定待唤醒的目标设备，包括：
    确定所述第三唤醒请求的生成时间是否早于所述第一唤醒请求的接收时间；以及
    在所述第三唤醒请求的生成时间早于所述第一唤醒请求的接收时间的情况下，确定所述主控设备为所述目标设备。
  7. 根据权利要求1所述的方法，还包括：
    接收至少一个设备以预设频率发送的探测信号；
    向各所述设备返回探测响应信号。
  8. 一种设备唤醒方法，包括：
    在获取到用户的唤醒语音后，生成唤醒请求，并将所述唤醒请求发送给主控设备；
    响应于接收到所述主控设备返回的唤醒指令，进入唤醒状态并对所述用户的唤醒语音进行响应。
  9. 根据权利要求8所述的方法，其中，所述响应于接收到所述主控设备返回的唤醒指令，进入唤醒状态并对所述用户的唤醒语音进行响应，包括：
    响应于接收到所述主控设备返回的唤醒锁，进入唤醒状态并对所述用户的唤醒语音进行响应。
  10. 根据权利要求9所述的方法，还包括：
    在接收到所述唤醒锁后的预设时长内，向所述主控设备发送释放唤醒锁请求；
    响应于接收到所述主控设备返回的应答指令，释放所述唤醒锁。
  11. 根据权利要求8至10任一项所述的方法，还包括：
    接收所述主控设备以预设频率发送的探测信号；
    向所述主控设备返回探测响应信号。
  12. 一种主控设备，包括：
    第一接收模块，用于接收来自设备的第一唤醒请求，其中，所述第一唤醒请求为所述主控设备接收到的首个唤醒请求；
    第一确定模块，用于根据所述第一唤醒请求，确定待唤醒的目标设备；
    第一处理模块，用于触发所述目标设备进入唤醒状态，以使所述目标设备响应用户的唤醒语音。
  13. 一种设备，包括：
    第二处理模块，用于在获取到用户的唤醒语音后，生成唤醒请求，并将所述唤醒请求发送给主控设备；
    第三处理模块，用于响应于接收到所述主控设备返回的唤醒指令，进入唤醒状态并对所述用户的唤醒语音进行响应。
  14. 一种电子设备，包括：
    一个或多个处理器；以及
    存储器，用于存储一个或多个程序，
    其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现：
    根据权利要求1至7中任一项所述的方法；或者，
    根据权利要求8至11中任一项所述的方法。
  15. 一种计算机可读存储介质，其上存储有可执行指令，该指令被处理器执行时使处理器实现：
    根据权利要求1至7中任一项所述的方法；或者，
    根据权利要求8至11中任一项所述的方法。
PCT/CN2021/112410 2020-08-13 2021-08-13 设备唤醒方法及装置 WO2022033574A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010815397.5A CN112331214A (zh) 2020-08-13 2020-08-13 设备唤醒方法及装置
CN202010815397.5 2020-08-13

Publications (1)

Publication Number Publication Date
WO2022033574A1 true WO2022033574A1 (zh) 2022-02-17

Family

ID=74303747

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/112410 WO2022033574A1 (zh) 2020-08-13 2021-08-13 设备唤醒方法及装置

Country Status (2)

Country Link
CN (1) CN112331214A (zh)
WO (1) WO2022033574A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114974308A (zh) * 2022-06-20 2022-08-30 宁波奥克斯电气股份有限公司 一种语音模块自动测试方法及系统
CN115457955A (zh) * 2022-07-29 2022-12-09 青岛海尔科技有限公司 分布式唤醒的决策方法、装置、存储介质及电子装置
CN116456441A (zh) * 2023-06-16 2023-07-18 荣耀终端有限公司 声音处理装置、方法和电子设备
WO2023221062A1 (zh) * 2022-05-19 2023-11-23 北京小米移动软件有限公司 电子设备的语音唤醒方法、装置、存储介质及芯片

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112331214A (zh) * 2020-08-13 2021-02-05 北京京东尚科信息技术有限公司 设备唤醒方法及装置
CN113241068A (zh) * 2021-03-26 2021-08-10 青岛海尔科技有限公司 语音信号的响应方法和装置、存储介质及电子装置
CN113157240A (zh) * 2021-04-27 2021-07-23 百度在线网络技术（北京）有限公司 语音处理方法、装置、设备、存储介质及计算机程序产品
CN114465837B (zh) * 2022-01-30 2024-03-08 云知声智能科技股份有限公司 一种智能语音设备协同唤醒处理方法及装置
CN115827075B (zh) * 2022-11-21 2024-02-23 小米汽车科技有限公司 设备控制方法、装置、设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109036428A (zh) * 2018-10-31 2018-12-18 广东小天才科技有限公司 一种语音唤醒设备、方法及计算机可读存储介质
CN109215663A (zh) * 2018-10-11 2019-01-15 北京小米移动软件有限公司 设备唤醒方法及装置
CN109391528A (zh) * 2018-08-31 2019-02-26 百度在线网络技术（北京）有限公司 语音智能设备的唤醒方法、装置、设备及存储介质
CN109473110A (zh) * 2018-12-29 2019-03-15 深圳市慧声信息科技有限公司 一种防止语音交互设备被误唤醒的方法、装置、系统及使用方法
CN109658927A (zh) * 2018-11-30 2019-04-19 北京小米移动软件有限公司 智能设备的唤醒处理方法、装置及管理设备
CN111276139A (zh) * 2020-01-07 2020-06-12 百度在线网络技术（北京）有限公司 语音唤醒方法及装置
CN112331214A (zh) * 2020-08-13 2021-02-05 北京京东尚科信息技术有限公司 设备唤醒方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105183137B (zh) * 2015-09-09 2018-06-01 厦门美图移动科技有限公司 一种移动终端及其唤醒锁控制方法和控制系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109391528A (zh) * 2018-08-31 2019-02-26 百度在线网络技术（北京）有限公司 语音智能设备的唤醒方法、装置、设备及存储介质
CN109215663A (zh) * 2018-10-11 2019-01-15 北京小米移动软件有限公司 设备唤醒方法及装置
CN109036428A (zh) * 2018-10-31 2018-12-18 广东小天才科技有限公司 一种语音唤醒设备、方法及计算机可读存储介质
CN109658927A (zh) * 2018-11-30 2019-04-19 北京小米移动软件有限公司 智能设备的唤醒处理方法、装置及管理设备
CN109473110A (zh) * 2018-12-29 2019-03-15 深圳市慧声信息科技有限公司 一种防止语音交互设备被误唤醒的方法、装置、系统及使用方法
CN111276139A (zh) * 2020-01-07 2020-06-12 百度在线网络技术（北京）有限公司 语音唤醒方法及装置
CN112331214A (zh) * 2020-08-13 2021-02-05 北京京东尚科信息技术有限公司 设备唤醒方法及装置

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023221062A1 (zh) * 2022-05-19 2023-11-23 北京小米移动软件有限公司 电子设备的语音唤醒方法、装置、存储介质及芯片
CN114974308A (zh) * 2022-06-20 2022-08-30 宁波奥克斯电气股份有限公司 一种语音模块自动测试方法及系统
CN115457955A (zh) * 2022-07-29 2022-12-09 青岛海尔科技有限公司 分布式唤醒的决策方法、装置、存储介质及电子装置
CN116456441A (zh) * 2023-06-16 2023-07-18 荣耀终端有限公司 声音处理装置、方法和电子设备
CN116456441B (zh) * 2023-06-16 2023-10-31 荣耀终端有限公司 声音处理装置、方法和电子设备

Also Published As

Publication number Publication date
CN112331214A (zh) 2021-02-05

Similar Documents

Publication Publication Date Title
WO2022033574A1 (zh) 设备唤醒方法及装置
US10601599B2 (en) Voice command processing in low power devices
US10115397B2 (en) Low power detection of a voice control activation phrase
US10783364B2 (en) Method, apparatus and device for waking up voice interaction function based on gesture, and computer readable medium
KR102018152B1 (ko) 항상-온-항상-청취 음성 인식 시스템을 위한 위치 인식 전력 관리 스킴
EP2959474B1 (en) Hybrid performance scaling for speech recognition
US9142215B2 (en) Power-efficient voice activation
US20160196838A1 (en) Utilizing Digital Microphones for Low Power Keyword Detection and Noise Suppression
WO2020048222A1 (zh) 音效调整方法、装置、电子设备以及存储介质
WO2020038010A1 (zh) 智能设备、语音唤醒方法、语音唤醒装置及存储介质
CN106030699A (zh) 多个设备上的热词检测
US9899034B2 (en) Technologies for robust crying detection using temporal characteristics of acoustic features
US11264049B2 (en) Systems and methods for capturing noise for pattern recognition processing
WO2022027982A1 (zh) 电子设备的响应方法、响应装置、计算机系统及存储介质
WO2020048216A1 (zh) 音效调整方法、装置、电子设备以及存储介质
CN108766438A (zh) 人机交互方法、装置、存储介质及智能终端
CN111402877A (zh) 基于车载多音区的降噪方法、装置、设备和介质
JP2022504668A (ja) 表示制御方法および関連製品
CN110853644B (zh) 语音唤醒方法、装置、设备及存储介质
US11437031B2 (en) Activating speech recognition based on hand patterns detected using plurality of filters
US10693944B1 (en) Media-player initialization optimization
CN115862604B (zh) 语音唤醒模型训练及语音唤醒方法、装置及计算机设备
KR20140035845A (ko) 에너지 보존을 갖는 연속적인 데이터 전달
US10817246B2 (en) Deactivating a display of a smart display device based on a sound-based mechanism
KR102669100B1 (ko) 전자 장치 및 그 제어 방법

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: 21855624

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: 21855624

Country of ref document: EP

Kind code of ref document: A1