WO2023005844A1

WO2023005844A1 - Device wake-up method, related apparatus, and communication system

Info

Publication number: WO2023005844A1
Application number: PCT/CN2022/107411
Authority: WO
Inventors: 闻琛; 李明雨; 赵伟; 冯晓兵; 陈航; 曾旺; 刘杰
Original assignee: 华为技术有限公司
Priority date: 2021-07-26
Filing date: 2022-07-22
Publication date: 2023-02-02
Also published as: CN115691485A

Abstract

A device wake-up method, a related apparatus, and a communication system (10). In the method, when it is detected that a user needs to wake up other electronic devices (100), smart glasses (101) may acquire an image, the image being an image within the field of view of the user; the smart glasses (101) may determine, according to the image, a target device to be woken up and send a wake-up instruction to the target device to be woken up; an electronic device (100) receiving the wake-up instruction may enter a wake-up state. The method can effectively reduce false wake-up, and bring better use experience for the user to use the voice interaction functions of the electronic devices (100).

Description

Equipment wake-up method, related device and communication system

This application claims the priority of the Chinese patent application with the application number 202110844001.4 and the application name "equipment wake-up method, related device and communication system" submitted to the China Patent Office on July 26, 2021, the entire contents of which are incorporated herein by reference. Applying.

technical field

The present application relates to the field of terminal technology, and in particular to a method for waking up a device, a related device and a communication system.

Background technique

With the intelligentization of electronic devices, more and more electronic devices have voice interaction functions. The user can wake up the electronic device without touching the electronic device through the wake-up word, and instruct the electronic device to complete corresponding tasks through voice commands. However, in the scenario where there are multiple electronic devices with voice interaction functions (especially multiple electronic devices of the same brand) in a room, if the user speaks the wake-up word, these multiple electronic devices may all hear the wake-up word and are all awakened. The above-mentioned false wake-up will cause interference to the user and reduce user experience.

Contents of the invention

The present application provides a method for waking up a device, a related device, and a communication system, which can effectively reduce the situation of false waking up, and bring better user experience for users using the voice interaction function of electronic devices.

In a first aspect, the present application provides a system for waking up a device. The device wake-up system includes an image acquisition device and multiple electronic devices. Wherein, the image acquisition device can be used to detect the first user input, and when the first user input is detected, acquire the first image. The image acquisition device can also be used to select a target electronic device included in the first image from multiple electronic devices, and send a wake-up instruction to the target electronic device; the wake-up command is used to trigger the target electronic device to enter a wake-up state. The target electronic device may be configured to enter a wake-up state in response to the received wake-up instruction.

The above-mentioned multiple electronic devices may be electronic devices with a voice interaction function, and the voice interaction function is turned on. Having a voice interaction function may mean that the electronic device can recognize a user's voice command and perform an operation corresponding to the voice command.

From the above device wake-up system, it can be seen that the image acquisition device can determine the target electronic device through the image collected by itself, and instruct the target electronic device to enter the wake-up state. The above-mentioned target electronic equipment is the electronic equipment determined by the image acquisition device that the user wishes to wake up. That is to say, the user can use the image acquisition device to wake up the electronic device he wants to wake up. In a scenario where the user speaks a wake-up word to wake up the device, the target electronic device may enter a wake-up state to respond to the user's voice command. In this way, false wakeups can be reduced, and a better user experience can be brought to the user when using the voice interaction function of the electronic device.

With reference to the first aspect, in some embodiments, the image acquisition device may be smart glasses.

Understandably, when a user wishes to wake up an electronic device, he usually looks at the electronic device and speaks a voice command. Then, if the user wears smart glasses, the images collected by the smart glasses are the images within the user's field of vision. The smart glasses can more accurately determine which electronic device the user wishes to wake up based on the images collected by themselves.

With reference to the first aspect, in some embodiments, the above-mentioned first user input may be voice input including a wake-up word. Alternatively, the above-mentioned first user input may be a user operation acting on the first position of the image capture device.

Wherein, when the wake-up word is monitored, the image acquisition device may perform image acquisition to obtain the above-mentioned first image, and determine the target electronic device according to the above-mentioned first image. When the user speaks the wake-up word, in addition to the wake-up word that can be monitored by the image acquisition device, the above-mentioned multiple electronic devices can also monitor the wake-up word. When the wake-up word is detected, the above-mentioned multiple electronic devices may detect whether the above-mentioned image acquisition device exists in the device wake-up system. In a possible implementation manner, the electronic devices that exist in the above device wake-up system may exist in the local device list. The local device list may be stored in one or more electronic devices in the device wake-up system. Optionally, the local device list may also be stored in a cloud server. All electronic devices in the local device list can obtain the local device list. That is, all the electronic devices in the local device list can determine which electronic devices are contained in the wake-up system of the above-mentioned devices.

The plurality of electronic devices may determine whether the image capture device exists in the wake-up system of the device by determining whether the image capture device is included in the local device list. If the above-mentioned local device list includes the above-mentioned image collection device, the above-mentioned multiple electronic devices may determine that the above-mentioned image collection device exists in the above-mentioned device wake-up system. If it is determined that the image capture device exists in the wake-up system of the device, the multiple electronic devices may further determine whether the image capture device is in a wearing state. If it is determined that the image capture device is in the wearing state, the above-mentioned multiple electronic devices may wait for a wake-up instruction instead of entering the wake-up state immediately. When an electronic device among the plurality of electronic devices receives a wake-up instruction, this electronic device may enter a wake-up state. During the process of waiting for the wake-up instruction, the plurality of electronic devices may not respond to the monitored wake-up words, voice instructions, and the like. Wherein, the above-mentioned image acquisition device may be smart glasses.

In some embodiments, before receiving the above-mentioned wake-up instruction, the target electronic device listens to the wake-up word but does not listen to the voice command (for example, in a scenario where the user only speaks the wake-up word). Then, when entering the wake-up state, the above-mentioned target electronic device may output a voice response to the above-mentioned wake-up word. The voice response to the wake word may be, for example, "I am". Or, before receiving the above-mentioned wake-up instruction, the target electronic device neither listens to the wake-up word nor the voice command (such as the user does not say the wake-up word, but the user operation acting on the first position above realizes in scenarios where the device wakes up). Then, when entering the wake-up state, the target electronic device may also output a voice response to the wake-up word. That is to say, when entering the wake-up state but no voice command is heard, the target electronic device can output a voice response to the above-mentioned wake-up word to remind the user that the target electronic device has entered the wake-up state. In this way, the user can know which electronic device is awakened, and then instructs the electronic device in the awakened state to perform corresponding operations through voice instructions. When entering the wake-up state, the target electronic device can recognize the voice command and execute the user operation corresponding to the voice command.

In some embodiments, if the target electronic device listens to the voice command before receiving the above-mentioned wake-up command, then the target electronic device may directly output a voice response to the voice command after entering the wake-up state, and execute the corresponding voice command. operation. For example, in the scenario where the user speaks the wake-up word and the voice command at one time, or in the scenario where the user speaks the voice command while performing the user operation on the above-mentioned first position or before performing the user operation on the first position, The target electronic device may have listened to the voice command before receiving the wake-up command. Wherein, the target electronic device may detect whether the sound signal collected during the first time period before receiving the wake-up instruction and after receiving the wake-up instruction contains the voice instruction. In this way, when the user speaks the voice command before the target electronic device receives the wake-up command, the target electronic device does not respond to the voice command because it does not detect the user's voice command.

In some embodiments, if the above-mentioned multiple electronic devices determine that the above-mentioned image capture device does not exist in the device wake-up system (that is, the image capture device is not included in the local device list), or determine that the above-mentioned image capture device exists in the device wake-up system However, the image acquisition device is not in the wearing state, and the above-mentioned multiple electronic devices can negotiate to select one electronic device. An electronic device selected through the above negotiation may enter a wake-up state. Other electronic devices may not enter the wake-up state. In a possible implementation manner, the plurality of electronic devices may negotiate and select an electronic device that receives the sound signal containing the wake-up word with the highest intensity according to the strength of the received sound signal containing the wake-up word. The electronic device that receives the sound signal containing the wake-up word with the highest intensity may enter the wake-up state.

It can be seen from the above embodiments that when multiple electronic devices with voice interaction function enabled monitor the wake-up word, these multiple electronic devices can determine whether the user will wake up the device through the image acquisition device. When it is determined that the user will wake up the device through the image acquisition device, the plurality of electronic devices may wait for a wake-up instruction, and enter into a wake-up state after receiving the wake-up instruction. In this way, the plurality of electronic devices will not all enter the wake-up state after listening to the wake-up word, and false wake-up will occur. In addition, the electronic device that has received the wake-up instruction is most likely to be the electronic device that the user wishes to wake up. This can bring a better user experience for the user to use the voice interaction function of the electronic device.

In some embodiments, the above-mentioned image acquisition device may be smart glasses. The above-mentioned first position may be a position on the temple of the smart glasses.

With reference to the first aspect, in some embodiments, the specific implementation manner of selecting the target electronic device contained in the first image by the above-mentioned image acquisition device from multiple electronic devices may be: determining the type of the electronic device contained in the first image, identifying At least one of accuracy rate and viewing angle deviation; the recognition accuracy rate is used to indicate the accuracy rate of the recognition result of the type of electronic device contained in the first image, and the viewing angle deviation is used to indicate that the position of the electronic device in the first image is different from the first the distance from the center of the image;

Determining the electronic device with the highest priority among the multiple electronic devices included in the first image as the target electronic device; the priority is determined according to one or more of the type, recognition accuracy and viewing angle deviation; the electronic device's The priority of the type in the wake-up sort determined by type is positively correlated with the priority of the electronic device, the recognition accuracy of the electronic device is positively correlated with the priority of the electronic device, and the viewing angle deviation of the electronic device is negatively correlated with the priority of the electronic device.

It can be understood that, considering the relationship between the type of electronic device and the priority of the above-mentioned electronic device, if the values of the above-mentioned features such as recognition accuracy and viewing angle deviation remain unchanged, the type of electronic device will be in the wake-up order determined according to the type. The higher the center, the higher the priority of the electronic device. Considering the relationship between the recognition accuracy rate of the electronic device and the priority of the above-mentioned electronic device, if the values of the characteristics such as the type of the above-mentioned electronic device and the viewing angle deviation remain unchanged, the higher the recognition accuracy rate of the electronic device, the higher the electronic device's The higher the priority. Considering the relationship between the recognition accuracy rate of the electronic device and the priority of the above-mentioned electronic device, if the type of the above-mentioned electronic device and the value of the characteristics such as the recognition accuracy rate remain unchanged, the smaller the deviation of the viewing angle of the electronic device is, the greater the The higher the priority.

It can be known from the above embodiments that the higher the identification accuracy of the electronic device is, the higher the probability that the electronic device can match the electronic device in the local device list, and the higher the probability that the electronic device is successfully awakened. The smaller the viewing angle deviation of the television device is, and the closer the position of the electronic device is to the center of the user's field of vision, the greater the probability that the electronic device is the electronic device that the user wishes to wake up. The electronic device that the user wishes to wake up can be accurately determined according to one or more of the above types, recognition accuracy and viewing angle deviation. In this way, false wakeups can be effectively reduced, and better user experience can be brought to the user when using the voice interaction function of the electronic device.

In a second aspect, the present application provides a device wake-up system. The device wake-up system may include an image acquisition device and a processing device. Wherein, the image acquisition device can be used to detect the first user input, and when the first user input is detected, acquire the first image. The image acquisition device may also be configured to send a first instruction to the processing device, the first instruction may include the first image, and the first instruction may be used to instruct the processing device to select a target electronic device included in the first image from multiple electronic devices. The processing device may be configured to respond to the first instruction, select a target electronic device included in the first image from multiple electronic devices, and send a wake-up instruction to the target electronic device. The wake-up command can be used to trigger the target electronic device to enter the wake-up state.

It can be known from the above device wake-up system that the image acquisition device can collect images when the user needs to wake up the device, and send the acquired images to the processing device. The processing device may determine the target electronic device through the image from the image acquisition device, and instruct the target electronic device to enter a wake-up state. The above-mentioned target electronic equipment is the electronic equipment determined by the image acquisition device that the user wishes to wake up. That is to say, the user can wake up the electronic device he wants to wake up by means of the image acquisition device and the processing device. In the scenario where the user speaks a wake-up word to wake up the device, the above-mentioned target electronic device may enter a wake-up state to respond to the user's voice command. In this way, false wakeups can be reduced, and a better user experience can be brought to the user when using the voice interaction function of the electronic device.

It can be understood that the image acquisition device does not need to perform the operation of determining the target electronic device, which can save the power consumption of the image acquisition device. The aforementioned processing device may be an electronic device with strong computing power, such as a mobile phone, a cloud server, and the like.

With reference to the second aspect, in some embodiments, the above-mentioned image acquisition device may be smart glasses.

With reference to the second aspect, in some embodiments, the first user input is a voice input including a wake-up word; or, the first user input is a user operation acting on the first position of the image capture device.

Wherein, when the wake-up word is detected, the image acquisition device may perform image acquisition to obtain the above-mentioned first image, and determine the target electronic device according to the above-mentioned first image. In addition to the image acquisition device and the processing device, the above-mentioned device wake-up system may also include the above-mentioned multiple electronic devices. When the user speaks the wake-up word, in addition to the wake-up word that can be monitored by the image acquisition device, the above-mentioned multiple electronic devices can also monitor the wake-up word.

When the wake-up word is detected, the above-mentioned multiple electronic devices may detect whether the above-mentioned image acquisition device exists in the device wake-up system. In a possible implementation manner, the electronic devices that exist in the above device wake-up system may exist in the local device list. The local device list may be stored in one or more electronic devices in the device wake-up system. Optionally, the local device list may also be stored in a cloud server. All electronic devices in the local device list can obtain the local device list. That is, all the electronic devices in the local device list can determine which electronic devices are contained in the wake-up system of the above-mentioned devices.

The plurality of electronic devices may determine whether the image capture device exists in the wake-up system of the device by determining whether the image capture device is included in the local device list. If the above-mentioned local device list includes the above-mentioned image collection device, the above-mentioned multiple electronic devices may determine that the above-mentioned image collection device exists in the above-mentioned device wake-up system. If it is determined that the image capture device exists in the wake-up system of the device, the multiple electronic devices may further determine whether the image capture device is in a wearing state. If it is determined that the image capture device is in the wearing state, the above-mentioned multiple electronic devices may wait for a wake-up instruction instead of entering the wake-up state immediately. When an electronic device among the plurality of electronic devices receives a wake-up instruction, this electronic device may enter a wake-up state. During the process of waiting for the wake-up instruction, the plurality of electronic devices may not respond to the monitored wake-up words, voice instructions, and the like.

It can be seen from the above embodiments that when multiple electronic devices with voice interaction functions enabled monitor the wake-up word, the multiple electronic devices can determine whether the user will wake up the device through the image acquisition device. When it is determined that the user will wake up the device through the image acquisition device, the plurality of electronic devices may wait for a wake-up instruction, and enter into a wake-up state after receiving the wake-up instruction. In this way, the plurality of electronic devices will not all enter the wake-up state after listening to the wake-up word, and false wake-up will occur. In addition, the electronic device that has received the wake-up instruction is most likely to be the electronic device that the user wishes to wake up. This can bring a better user experience for the user to use the voice interaction function of the electronic device.

With reference to the second aspect, in some embodiments, the specific method for the above-mentioned processing device to select the target electronic device included in the first image from the plurality of electronic devices may be: determine the type of the electronic device included in the first image, the recognition accuracy rate , at least one item of viewing angle deviation; the recognition accuracy is used to indicate the accuracy of the recognition result of the type of electronic device contained in the first image, and the viewing angle deviation is used to indicate the difference between the position of the electronic device in the first image and the position of the first image Center distance. Determining the electronic device with the highest priority among the multiple electronic devices included in the first image as the target electronic device; the priority is determined according to one or more of the type, recognition accuracy and viewing angle deviation; the electronic device's The priority of the type in the wake-up sort determined by type is positively correlated with the priority of the electronic device, the recognition accuracy of the electronic device is positively correlated with the priority of the electronic device, and the viewing angle deviation of the electronic device is negatively correlated with the priority of the electronic device.

With reference to the second aspect, in some embodiments, the above-mentioned processing device may be one of the above-mentioned multiple electronic devices. That is, the above-mentioned processing device may be an electronic device with a voice interaction function enabled. If the processing device determines that it is the target electronic device according to the first image from the image acquisition device, the processing device may enter a wake-up state. That is, the processing device does not need to send a wake-up instruction.

With reference to the second aspect, in some embodiments, after capturing the first image, the image acquisition device may identify the electronic device contained in the first image, and send information of the identified electronic device to the processing device. The above-mentioned information of the electronic device may include one or more of the following: type, recognition accuracy, and viewing angle deviation. The processing device may determine the priority of the electronic device included in the first image according to the information of the electronic device, and select the electronic device with the highest priority included in the first image from the local device list. The selected electronic device is the target electronic device.

With reference to the second aspect, in some embodiments, after the image acquisition device acquires the first image, it may determine the priority of the electronic devices contained in the first image, and send the priority to the processing device. The processing device may, according to the priorities of the electronic devices contained in the first image, select the electronic device with the highest priority contained in the first image from the local device list. The selected electronic device is the target electronic device.

In a third aspect, the present application provides a method for waking up a device. In this method, a first image is acquired, a target electronic device included in the first image is selected from a plurality of electronic devices, and a wake-up instruction is sent to the target electronic device. The wake-up instruction can be used to trigger the target electronic device to enter the wake-up state.

With reference to the third aspect, in some embodiments, the method in the above third aspect may be executed by an image acquisition device. Wherein, the above-mentioned process of acquiring the first image may be: when the first user input is detected, the image acquisition device acquires the first image. The aforementioned detection of the first user input may specifically be detection of a wake-up word, or detection of a user operation acting on the first position of the image capture device. The above-mentioned image acquisition device may be smart glasses.

It can be understood that the image acquisition apparatus may determine whether the user needs to wake up the device by detecting the above-mentioned first user input. When it is determined that the user needs to wake up the device, the image acquisition device may perform image acquisition. That is, the above-mentioned first image may be acquired by the image acquisition device when it is determined that the user needs to wake up the device.

It can be known from the above embodiments that the image acquisition device can determine the target electronic device through the images it has collected, and instruct the target electronic device to enter the wake-up state. The above-mentioned target electronic equipment is the electronic equipment determined by the image acquisition device that the user wishes to wake up. That is to say, the user can use the image acquisition device to wake up the electronic device he wants to wake up. In a scenario where the user speaks a wake-up word to wake up the device, the target electronic device may enter a wake-up state to respond to the user's voice command. In this way, false wakeups can be reduced, and a better user experience can be brought to the user when using the voice interaction function of the electronic device.

With reference to the third aspect, in some embodiments, the method in the third aspect above may be executed by a processing device. Wherein, the above-mentioned process of acquiring the first image may be: receiving a first instruction from an image acquisition device. The first instruction may include a first image captured by an image capture device. The first instruction may be used to instruct the processing device to select a target electronic device included in the first image from multiple electronic devices.

It can be seen from the above embodiments that the processing device can determine the target electronic device according to the image from the image acquisition device, and instruct the target electronic device to enter the wake-up state. The above-mentioned target electronic equipment is the electronic equipment determined by the image acquisition device that the user wishes to wake up. That is to say, in the scene where the user speaks the wake-up word to wake up the device, the above-mentioned target electronic device can enter the wake-up state, while other electronic devices with voice interaction functions enabled will not enter the wake-up state. In this way, false wakeups can be reduced, and a better user experience can be brought to the user when using the voice interaction function of the electronic device.

With reference to the third aspect, in some embodiments, the specific method for selecting the target electronic device contained in the first image from the above-mentioned multiple electronic devices may be: determining the type, recognition accuracy, and viewing angle of the electronic device contained in the first image At least one of the deviations; the recognition accuracy rate is used to indicate the accuracy rate of the recognition result of the type of electronic device contained in the first image, and the viewing angle deviation is used to indicate the distance between the position of the electronic device in the first image and the center of the first image distance. Determining the electronic device with the highest priority among the multiple electronic devices included in the first image as the target electronic device; the priority is determined according to one or more of the type, recognition accuracy and viewing angle deviation; the electronic device's The priority of the type in the wake-up sort determined by type is positively correlated with the priority of the electronic device, the recognition accuracy of the electronic device is positively correlated with the priority of the electronic device, and the viewing angle deviation of the electronic device is negatively correlated with the priority of the electronic device.

In a fourth aspect, the present application provides a method for waking up a device. In this method, when a first user input is detected, the image capture device can capture a first image. The image acquisition device may send a first instruction to the processing device. The first instruction may include a first image. The first instruction may be used to instruct the processing device to select a target electronic device included in the first image from multiple electronic devices. The target electronic device may be an object to which the processing device sends a wake-up instruction. The wake-up instruction can be used to trigger the target electronic device to enter the wake-up state.

The above-mentioned first user input may be a voice input including a wake-up word, or may be a user operation acting on the first position of the above-mentioned image acquisition device.

In some embodiments, the above-mentioned image acquisition device may be smart glasses.

It can be known from the above embodiments that the image acquisition device may perform image acquisition when the user needs to wake up the device, and send the acquired image to the processing device. The image capture device may instruct the processing device to determine the target electronic device. Then, in a scenario where the user speaks a wake-up word to wake up the device, the above-mentioned target electronic device may enter a wake-up state to respond to the user's voice command. However, electronic devices with other voice interaction functions enabled may not enter the wake-up state. In this way, false wakeups can be reduced, and a better user experience can be brought to the user when using the voice interaction function of the electronic device.

In a fifth aspect, the present application provides a method for waking up a device. In this method, the first electronic device can monitor the wake-up word. In response to the wake-up word, the first electronic device may detect whether there are smart glasses in the device wake-up system, and whether the smart glasses are in a wearing state. If there are smart glasses in the device wake-up system, and the smart glasses are in a wearing state, the first electronic device may wait to receive a wake-up instruction. The wake-up instruction can be used to trigger the first electronic device to enter the wake-up state. The first electronic device enters into a wake-up state upon receiving the wake-up instruction.

In a possible implementation manner, the electronic devices that exist in the above device wake-up system may exist in the local device list. The local device list may be stored in one or more electronic devices in the device wake-up system. Optionally, the local device list can also be stored in the cloud server. All electronic devices in the local device list can obtain the local device list. That is, all the electronic devices in the local device list can determine which electronic devices are contained in the wake-up system of the above-mentioned devices.

When the wake-up word is detected, the first electronic device may determine whether smart glasses exist in the device wake-up system by determining whether the image acquisition device is included in the local device list. If the above-mentioned local device list includes smart glasses, the first electronic device may determine that there are smart glasses in the device wake-up system. If it is determined that there are smart glasses in the device wake-up system, the first electronic device may further determine whether the smart glasses are in a wearing state. If it is determined that the smart glasses are in the wearing state, the first electronic device may wait for a wake-up instruction without immediately entering the wake-up state. When the first electronic device receives the wake-up instruction, the first electronic device may enter the wake-up state. During the above process of waiting for the wake-up instruction, the first electronic device may not respond to the monitored wake-up words, voice instructions, and the like.

In some embodiments, the above-mentioned first electronic device is determined as the target electronic device and receives a wake-up instruction. Before receiving the above-mentioned wake-up instruction, the target electronic device listens to the wake-up word, but does not listen to the voice command (such as in the scenario where the user only speaks the wake-up word). Then, when entering the wake-up state, the above-mentioned target electronic device may output a voice response to the above-mentioned wake-up word. The voice response to the wake word may be, for example, "I am". Or, before receiving the above-mentioned wake-up instruction, the target electronic device neither listens to the wake-up word nor the voice command (such as the user does not say the wake-up word, but the user operation acting on the first position above realizes in scenarios where the device wakes up). Then, when entering the wake-up state, the target electronic device may also output a voice response to the wake-up word. That is to say, when entering the wake-up state but no voice command is heard, the target electronic device can output a voice response to the above-mentioned wake-up word to remind the user that the target electronic device has entered the wake-up state. In this way, the user can know which electronic device is awakened, and then instructs the electronic device in the awakened state to perform corresponding operations through voice instructions. When entering the wake-up state, the target electronic device can recognize the voice command and execute the user operation corresponding to the voice command.

In some embodiments, the above-mentioned first electronic device is determined as the target electronic device and receives a wake-up instruction. If the target electronic device listens to the voice command before receiving the wake-up command, then the target electronic device can directly output a voice response to the voice command after entering the wake-up state, and execute the operation corresponding to the voice command. For example, in the scenario where the user speaks the wake-up word and the voice command at one time, or in the scenario where the user speaks the voice command while performing the user operation on the above-mentioned first position or before performing the user operation on the first position, The target electronic device may have listened to the voice command before receiving the wake-up command. Wherein, the target electronic device may detect whether the sound signal collected during the first time period before receiving the wake-up instruction and after receiving the wake-up instruction contains the voice instruction. In this way, when the user speaks the voice command before the target electronic device receives the wake-up command, the target electronic device does not respond to the voice command because it does not detect the user's voice command.

In some embodiments, if the first electronic device determines that smart glasses do not exist in the device wake-up system (that is, the smart glasses are not included in the local device list), or determines that there are smart glasses in the device wake-up system but the smart glasses are not being worn state, the first electronic device and other electronic devices whose voice interaction function is enabled may negotiate to select an electronic device. An electronic device selected through the above negotiation may enter a wake-up state. Other electronic devices may not enter the wake-up state. In a possible implementation manner, the first electronic device and other electronic devices with the voice interaction function enabled may negotiate and select the one that receives the sound signal containing the wake-up word with the highest strength according to the strength of the received sound signal containing the wake-up word. Electronic equipment. The electronic device that receives the sound signal containing the wake-up word with the highest intensity may enter the wake-up state.

It can be seen from the above-mentioned embodiments that when multiple electronic devices with voice interaction functions enabled monitor the wake-up word, the multiple electronic devices can determine whether the user will wake up the device through the smart glasses. When it is determined that the user will wake up the device through the smart glasses, the plurality of electronic devices may wait for a wake-up instruction, and enter into a wake-up state after receiving the wake-up instruction. In this way, the plurality of electronic devices will not all enter the wake-up state after listening to the wake-up word, and false wake-up will occur. In addition, the electronic device that has received the wake-up instruction is most likely to be the electronic device that the user wishes to wake up. This can bring a better user experience for the user to use the voice interaction function of the electronic device.

In a sixth aspect, the present application provides an electronic device. The electronic device can include memory and a processor. Among them, memory can be used to store computer programs. The processor may be used to invoke a computer program, so that the electronic device executes any possible implementation manner in the third aspect, the fourth aspect, or the fifth aspect.

In a seventh aspect, the present application provides a chip, the chip is applied to an electronic device, the chip includes one or more processors, and the processor is used to invoke computer instructions so that the electronic device executes the third aspect or the fourth aspect or Any possible implementation manner in the fifth aspect.

In an eighth aspect, the present application provides a computer program product containing instructions, which is characterized in that, when the above-mentioned computer program product is run on an electronic device, the electronic device is executed as in the third aspect or the fourth aspect or the fifth aspect. any possible implementation.

In a ninth aspect, the present application provides a computer-readable storage medium, including instructions, characterized in that, when the above-mentioned instructions are run on an electronic device, the electronic device is made to execute the method described in the third aspect or the fourth aspect or the fifth aspect. any possible implementation.

It can be understood that the electronic device provided in the sixth aspect, the chip provided in the seventh aspect, the computer program product provided in the eighth aspect, and the computer-readable storage medium provided in the ninth aspect are all used to execute the method. Therefore, the beneficial effects that it can achieve can refer to the beneficial effects in the corresponding method, and will not be repeated here.

Description of drawings

FIG. 1 is a schematic structural diagram of an electronic device provided in an embodiment of the present application;

FIG. 2 is a schematic diagram of a device wake-up scenario provided by an embodiment of the present application;

FIG. 3 is a schematic structural diagram of a communication system provided by an embodiment of the present application;

FIG. 4 is a schematic structural diagram of another communication system provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of a device wake-up scenario provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of images collected by smart glasses provided in an embodiment of the present application;

FIG. 7 is a schematic diagram of a device wake-up scenario provided by an embodiment of the present application;

FIG. 8 is a schematic diagram of images collected by smart glasses provided in an embodiment of the present application;

FIG. 9A and FIG. 9B are schematic diagrams of a device wake-up scenario provided by an embodiment of the present application;

FIG. 10 is a flowchart of a method for an electronic device to enter a wake-up state according to an embodiment of the present application;

Fig. 11 is a schematic structural diagram of smart glasses provided by an embodiment of the present application;

Fig. 12 is a flow chart of a method for waking up a device provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described clearly and in detail below in conjunction with the accompanying drawings. Among them, in the description of the embodiments of this application, unless otherwise specified, "/" means or means, for example, A/B can mean A or B; "and/or" in the text is only a description of associated objects The association relationship indicates that there may be three kinds of relationships, for example, A and/or B, which may indicate: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiment of the present application , "plurality" means two or more than two.

Hereinafter, the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as implying or implying relative importance or implicitly specifying the quantity of indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of these features. In the description of the embodiments of the present application, unless otherwise specified, the "multiple" The meaning is two or more.

In order to reduce false wake-ups when electronic devices are woken up by voice, embodiments of the present application provide a device wake-up method and a related device. The electronic device involved in the embodiment of the present application is firstly introduced below.

FIG. 1 exemplarily shows a schematic structural diagram of an electronic device 100 .

As shown in Figure 1, the electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (universal serial bus, USB) interface 130, a charging management module 140, a power management module 141, and a battery 142 , antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, earphone jack 170D, sensor module 180, button 190, motor 191, indicator 192, camera 193 , a display screen 194, and a subscriber identification module (subscriber identification module, SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, bone conduction sensor 180M, etc.

It can be understood that, the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 100 . In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine certain components, or separate certain components, or arrange different components. The illustrated components can be realized in hardware, software or a combination of software and hardware.

The processor 110 may include one or more processing units, for example: the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processing unit (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), controller, memory, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural network processor (neural-network processing unit, NPU) wait. Wherein, different processing units may be independent devices, or may be integrated in one or more processors.

Wherein, the controller may be the nerve center and command center of the electronic device 100 . The controller can generate an operation control signal according to the instruction opcode and timing signal, and complete the control of fetching and executing the instruction.

In some embodiments, the processor 110 may include a voice wake-up module and a voice command recognition module. Wherein, the voice wake-up module and the voice command recognition module can be integrated in different processor chips and executed by different chips. For example, the voice wake-up module can be integrated in a coprocessor or DSP chip with low power consumption, and the voice command recognition module can be integrated in an AP or NPU or other chips. In this way, after the voice wake-up module recognizes the preset wake-up word, the chip where the voice command recognition module is located can be activated to trigger the voice command recognition function, thereby saving the power consumption of the electronic device. Alternatively, the voice wake-up module and the voice command recognition module can be integrated in the same processor chip, and the same chip performs related functions. For example, both the voice wake-up module and the voice command recognition module can be integrated in an AP chip or an NPU or other chips.

The processor 110 may also include a voice command execution module. After the speech instruction recognition module recognizes the speech instruction, the speech instruction execution module can execute the operation corresponding to the speech instruction. For example, play music, make calls, send text messages, and more.

It can be understood that the electronic device including the above-mentioned voice wake-up module, voice command recognition module and voice command execution module is an electronic device with voice interaction capability. The aforementioned voice interaction capability may mean that the electronic device can respond to a user's voice command and perform an operation corresponding to the voice command.

A memory may also be provided in the processor 110 for storing instructions and data. In some embodiments, the memory in processor 110 is a cache memory. The memory may hold instructions or data that the processor 110 has just used or recycled. If the processor 110 needs to use the instruction or data again, it can be called directly from the memory. Repeated access is avoided, and the waiting time of the processor 110 is reduced, thus improving the efficiency of the system.

The USB interface 130 is an interface conforming to the USB standard specification, specifically, it can be a Mini USB interface, a Micro USB interface, a USB Type C interface, and the like. The USB interface 130 can be used to connect a charger to charge the electronic device 100 , and can also be used to transmit data between the electronic device 100 and peripheral devices. It can also be used to connect headphones and play audio through them. This interface can also be used to connect other electronic devices, such as AR devices.

The charging management module 140 is configured to receive a charging input from a charger. Wherein, the charger may be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 can receive charging input from the wired charger through the USB interface 130 . In some wireless charging embodiments, the charging management module 140 may receive a wireless charging input through a wireless charging coil of the electronic device 100 . While the charging management module 140 is charging the battery 142 , it can also provide power for electronic devices through the power management module 141 .

The power management module 141 is used for connecting the battery 142 , the charging management module 140 and the processor 110 . The power management module 141 receives the input from the battery 142 and/or the charging management module 140 to provide power for the processor 110 , the internal memory 121 , the external memory, the display screen 194 , the camera 193 , and the wireless communication module 160 . In some other embodiments, the power management module 141 may also be disposed in the processor 110 . In some other embodiments, the power management module 141 and the charging management module 140 may also be set in the same device.

The wireless communication function of the electronic device 100 can be realized by the antenna 1 , the antenna 2 , the mobile communication module 150 , the wireless communication module 160 , a modem processor, a baseband processor, and the like.

Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 may be used to cover single or multiple communication frequency bands. Different antennas can also be multiplexed to improve the utilization of the antennas. For example: Antenna 1 can be multiplexed as a diversity antenna of a wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.

The mobile communication module 150 can provide wireless communication solutions including 2G/3G/4G/5G applied on the electronic device 100 . The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA) and the like. The mobile communication module 150 can receive electromagnetic waves through the antenna 1, filter and amplify the received electromagnetic waves, and send them to the modem processor for demodulation. The mobile communication module 150 can also amplify the signals modulated by the modem processor, and convert them into electromagnetic waves through the antenna 1 for radiation. In some embodiments, at least part of the functional modules of the mobile communication module 150 may be set in the processor 110 . In some embodiments, at least part of the functional modules of the mobile communication module 150 and at least part of the modules of the processor 110 may be set in the same device.

The wireless communication module 160 can provide wireless local area networks (wireless local area networks, WLAN) (such as wireless fidelity (Wireless Fidelity, Wi-Fi) network), bluetooth (bluetooth, BT), global navigation satellite, etc. applied on the electronic device 100. System (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field communication technology (near field communication, NFC), infrared technology (infrared, IR) and other wireless communication solutions. The wireless communication module 160 may be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2 , frequency-modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110 . The wireless communication module 160 can also receive the signal to be sent from the processor 110 , frequency-modulate it, amplify it, and convert it into electromagnetic waves through the antenna 2 for radiation.

The electronic device 100 realizes the display function through the GPU, the display screen 194 , and the application processor. The GPU is a microprocessor for image processing, and is connected to the display screen 194 and the application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. Processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

The display screen 194 is used to display images, videos and the like. In some embodiments, the electronic device 100 may include 1 or N display screens 194 , where N is a positive integer greater than 1.

The electronic device 100 can realize the shooting function through the ISP, the camera 193 , the video codec, the GPU, the display screen 194 and the application processor.

The ISP is used for processing the data fed back by the camera 193 . For example, when taking a picture, open the shutter, the light is transmitted to the photosensitive element of the camera through the lens, and the light signal is converted into an electrical signal, and the photosensitive element of the camera transmits the electrical signal to the ISP for processing, and converts it into an image visible to the naked eye. ISP can also perform algorithm optimization on image noise, brightness, and skin color. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene. In some embodiments, the ISP may be located in the camera 193 .

Camera 193 is used to capture still images or video. The object generates an optical image through the lens and projects it to the photosensitive element. The photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. DSP converts digital image signals into standard RGB, YUV and other image signals. In some embodiments, the electronic device 100 may include 1 or N cameras 193 , where N is a positive integer greater than 1.

Digital signal processors are used to process digital signals. In addition to digital image signals, they can also process other digital signals. For example, when the electronic device 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the energy of the frequency point.

Video codecs are used to compress or decompress digital video. The electronic device 100 may support one or more video codecs. In this way, the electronic device 100 can play or record videos in various encoding formats, for example: moving picture experts group (moving picture experts group, MPEG) 1, MPEG2, MPEG3, MPEG4 and so on.

The NPU is a neural-network (NN) computing processor. By referring to the structure of biological neural networks, such as the transfer mode between neurons in the human brain, it can quickly process input information and continuously learn by itself. Applications such as intelligent cognition of the electronic device 100 can be realized through the NPU, such as image recognition, face recognition, speech recognition, text understanding, and the like.

The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, so as to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function. Such as saving music, video and other files in the external memory card.

The internal memory 121 may be used to store computer-executable program codes including instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by executing instructions stored in the internal memory 121 . The internal memory 121 may include an area for storing programs and an area for storing data. Wherein, the stored program area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.) and the like. The storage data area can store data created during the use of the electronic device 100 (such as audio data, phonebook, etc.) and the like. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, universal flash storage (universal flash storage, UFS) and the like.

The electronic device 100 can implement audio functions through the audio module 170 , the speaker 170A, the receiver 170B, the microphone 170C, the earphone interface 170D, and the application processor. Such as music playback, recording, etc.

The audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signal. The audio module 170 may also be used to encode and decode audio signals. In some embodiments, the audio module 170 may be set in the processor 110 , or some functional modules of the audio module 170 may be set in the processor 110 .

Speaker 170A, also referred to as a "horn", is used to convert audio electrical signals into sound signals. Electronic device 100 can listen to music through speaker 170A, or listen to hands-free calls.

Receiver 170B, also called "earpiece", is used to convert audio electrical signals into sound signals.

The microphone 170C, also called "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a phone call or sending a voice message, the user can put his mouth close to the microphone 170C to make a sound, and input the sound signal to the microphone 170C. The electronic device 100 may be provided with at least one microphone 170C. In some other embodiments, the electronic device 100 may be provided with two microphones 170C, which may also implement a noise reduction function in addition to collecting sound signals. In some other embodiments, the electronic device 100 can also be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify sound sources, and realize directional recording functions, etc.

In some embodiments, microphone 170C may interface with a low power processor. A voice wake-up module may be integrated in the low-power processor. The microphone 170C can send the collected sound signal to the low power consumption processor. The voice wake-up module in the low-power processor can detect whether the voice signal contains a preset wake-up word. If included, the low-power processor can wake up the application processor. A voice command recognition module and a voice command execution module may be integrated in the application processor. When the application processor is woken up, the sound signal collected by the microphone 170C can be sent to the application processor through the above-mentioned low power consumption processor. The speech command recognition module in the application processor can recognize the speech command in the sound signal. Further, the voice instruction executing module can execute the operation corresponding to the voice instruction.

When the voice interaction function of the electronic device 100 is turned on, the microphone 170C and the above-mentioned low-power processor can be in working state in real time. The sound signal collected by the microphone 170C needs to be judged by the low-power processor first whether it contains a preset wake-up word. The application processor is only woken up when the sound signal contains a preset wakeup word. This can save power consumption of the electronic device 100 .

The earphone interface 170D is used for connecting wired earphones. The earphone interface 170D can be a USB interface 130, or a 3.5mm open mobile terminal platform (OMTP) standard interface, or a cellular telecommunications industry association of the USA (CTIA) standard interface.

The pressure sensor 180A is used to sense the pressure signal and convert the pressure signal into an electrical signal. In some embodiments, pressure sensor 180A may be disposed on display screen 194 . There are many types of pressure sensors 180A, such as resistive pressure sensors, inductive pressure sensors, and capacitive pressure sensors. A capacitive pressure sensor may be comprised of at least two parallel plates with conductive material. When a force is applied to the pressure sensor 180A, the capacitance between the electrodes changes. The electronic device 100 determines the intensity of pressure according to the change in capacitance. When a touch operation acts on the display screen 194, the electronic device 100 detects the intensity of the touch operation according to the pressure sensor 180A. The electronic device 100 may also calculate the touched position according to the detection signal of the pressure sensor 180A. In some embodiments, touch operations acting on the same touch position but with different touch operation intensities may correspond to different operation instructions. For example: when a touch operation with a touch operation intensity less than the first pressure threshold acts on the short message application icon, an instruction to view short messages is executed. When a touch operation whose intensity is greater than or equal to the first pressure threshold acts on the icon of the short message application, the instruction of creating a new short message is executed.

The gyro sensor 180B can be used to determine the motion posture of the electronic device 100 . In some embodiments, the angular velocity of the electronic device 100 around three axes (ie, x, y and z axes) may be determined by the gyro sensor 180B.

The air pressure sensor 180C is used to measure air pressure.

The magnetic sensor 180D includes a Hall sensor. The electronic device 100 may use the magnetic sensor 180D to detect the opening and closing of the flip leather case.

The acceleration sensor 180E can detect the acceleration of the electronic device 100 in various directions (generally three axes). When the electronic device 100 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of electronic devices, and can be used in applications such as horizontal and vertical screen switching, pedometers, etc.

The distance sensor 180F is used to measure the distance. The electronic device 100 may measure the distance by infrared or laser. In some embodiments, when shooting a scene, the electronic device 100 may use the distance sensor 180F for distance measurement to achieve fast focusing.

Proximity light sensor 180G may include, for example, light emitting diodes (LEDs) and light detectors, such as photodiodes. The light emitting diodes may be infrared light emitting diodes. The electronic device 100 emits infrared light through the light emitting diode. Electronic device 100 uses photodiodes to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it may be determined that there is an object near the electronic device 100 . When insufficient reflected light is detected, the electronic device 100 may determine that there is no object near the electronic device 100 .

The ambient light sensor 180L is used for sensing ambient light brightness. The electronic device 100 can adaptively adjust the brightness of the display screen 194 according to the perceived ambient light brightness. The ambient light sensor 180L can also be used to automatically adjust the white balance when taking pictures. The ambient light sensor 180L can also cooperate with the proximity light sensor 180G to detect whether the electronic device 100 is in the pocket, so as to prevent accidental touch.

The fingerprint sensor 180H is used to collect fingerprints. The electronic device 100 can use the collected fingerprint characteristics to implement fingerprint unlocking, access to application locks, take pictures with fingerprints, answer incoming calls with fingerprints, and the like.

The temperature sensor 180J is used to detect temperature. In some embodiments, the electronic device 100 uses the temperature detected by the temperature sensor 180J to implement a temperature treatment strategy. For example, when the temperature reported by the temperature sensor 180J exceeds the threshold, the electronic device 100 may reduce the performance of the processor located near the temperature sensor 180J, so as to reduce power consumption and implement thermal protection. In other embodiments, when the temperature is lower than another threshold, the electronic device 100 heats the battery 142 to prevent the electronic device 100 from being shut down abnormally due to the low temperature.

Touch sensor 180K, also known as "touch panel". The touch sensor 180K can be disposed on the display screen 194, and the touch sensor 180K and the display screen 194 form a touch screen, also called a “touch screen”. The touch sensor 180K is used to detect a touch operation on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. Visual output related to the touch operation can be provided through the display screen 194 . In other embodiments, the touch sensor 180K may also be disposed on the surface of the electronic device 100 , which is different from the position of the display screen 194 .

The bone conduction sensor 180M can acquire vibration signals. In some embodiments, the bone conduction sensor 180M can acquire the vibration signal of the vibrating bone mass of the human voice. The bone conduction sensor 180M can also contact the human pulse and receive the blood pressure beating signal. In some embodiments, the bone conduction sensor 180M can also be disposed in the earphone, combined into a bone conduction earphone. The audio module 170 can analyze the voice signal based on the vibration signal of the vibrating bone mass of the vocal part acquired by the bone conduction sensor 180M, so as to realize the voice function.

The keys 190 include a power key, a volume key and the like. The key 190 may be a mechanical key. It can also be a touch button. The electronic device 100 can receive key input and generate key signal input related to user settings and function control of the electronic device 100 .

The motor 191 can generate a vibrating reminder.

The indicator 192 can be an indicator light, and can be used to indicate charging status, power change, and can also be used to indicate messages, missed calls, notifications, and the like.

The SIM card interface 195 is used for connecting a SIM card. The SIM card can be connected and separated from the electronic device 100 by inserting it into the SIM card interface 195 or pulling it out from the SIM card interface 195 . The electronic device 100 may support 1 or N SIM card interfaces, where N is a positive integer greater than 1. SIM card interface 195 can support Nano SIM card, Micro SIM card, SIM card etc. Multiple cards can be inserted into the same SIM card interface 195 at the same time. The types of the multiple cards may be the same or different. The SIM card interface 195 is also compatible with different types of SIM cards. The SIM card interface 195 is also compatible with external memory cards. The electronic device 100 interacts with the network through the SIM card to implement functions such as calling and data communication. In some embodiments, the electronic device 100 adopts an eSIM, that is, an embedded SIM card. The eSIM card can be embedded in the electronic device 100 and cannot be separated from the electronic device 100 .

The electronic device 100 may be a mobile phone, a tablet computer, a notebook computer, a speaker, a TV, a router, a wearable device (such as smart glasses, a smart watch, a smart bracelet, etc.), a smart home device (such as a refrigerator, a washing machine, an air conditioner, a lamp, etc.) etc. The embodiment of the present application does not limit the specific type of the electronic device 100 .

Speech recognition applications, such as voice assistant applications, are installed in many electronic devices. An electronic device installed with a voice assistant application has a voice interaction function. Wherein, when the voice interaction function is turned on, the electronic device can collect the sound in the environment in real time, and detect whether the sound contains a wake-up word. A wake word can be used to wake up an electronic device. The aforementioned waking up the electronic device may mean that the triggering electronic device invokes a processor (such as an application processor) integrated with a voice command recognition module and a voice command execution module to recognize the voice command in the collected sound and execute the operation corresponding to the voice command.

In some embodiments, the electronic device is in a sleep state. The sleep state may indicate that the application processor of the electronic device is in a sleep state. When in a sleep state, the microphone and the low-power processor of the electronic device can be in a working state in real time. When it is detected that the sound in the environment contains a wake-up word, the application processor of the electronic device can be woken up to perform the operation corresponding to the voice command (for example, the speaker is woken up when it is in a sleep state and plays music according to the user's voice command). In some embodiments, the application processor of the electronic device is in a working state. Wherein, the microphone and the low-power processor of the electronic device can be in working state in real time. When it is detected that the sound in the environment contains a wake-up word, the application processor of the electronic device can receive the sound collected by the microphone, recognize the voice command contained in the sound and perform the operation corresponding to the voice command (for example, the speaker monitors the wake-up call while playing music. words and turn on the air conditioner according to the user's voice command).

In some embodiments, a room includes multiple electronic devices with voice interaction functions. As shown in Figure 2, a room includes a mobile phone, a speaker and a TV. The mobile phone, speakers, and TV all have voice interaction functions, and the voice interaction functions are all turned on. Users want to instruct the speakers to play music through voice commands. The user can say "Xiaoyi Xiaoyi, I want to listen to the song". Among them, "Xiaoyi Xiaoyi" is the default wake-up word. "I want to listen to the song" is the voice command. Since the mobile phone, the sound box and the TV can all collect sounds in the environment, all these multiple electronic devices can monitor the wake-up word. Furthermore, the plurality of electronic devices can all be woken up. When awakened, the plurality of electronic devices can recognize the above-mentioned voice command "I want to listen to a song", and perform the operation corresponding to the voice command, that is, play music.

As shown in Figure 2, when the user says "Xiaoyi Xiaoyi, I want to listen to the song", the mobile phone can answer "no problem" and call the music playing application to play the music. The speaker can answer "no problem" by voice, and call the application that plays music to play music. The TV can also answer "no problem" and invoke the music-playing app to play the music. It can be seen that the electronic device that the user wishes to wake up is a speaker. Mobile phones and TVs were woken up by mistake. The above-mentioned false wake-up will interfere with the user and reduce the user experience of using the voice interaction function of the electronic device.

In a possible implementation manner, device priority rankings are stored in multiple electronic devices with a voice interaction function. The priority ranking of the devices may be: sound box>television>tablet computer>mobile phone. These multiple electronic devices can communicate with each other after listening to the wake-up word (such as "Xiaoyi Xiaoyi"), and determine the top electronic device among the multiple electronic devices, such as a TV, according to the device priority ranking. Further, the TV may respond to the above-mentioned wake-up word, and wake up the application processor to execute the user's voice command. The method for the television to respond to the wake-up word may be, for example, to answer "I am" by voice. The last electronic device among the above multiple electronic devices will not respond to the above wake-up word.

This embodiment of the present application does not specifically limit the prioritization of the foregoing devices.

The above-mentioned method for the plurality of electronic devices to communicate with each other after listening to the wake-up word may be a Bluetooth-based communication method. Then the distance between the above-mentioned multiple electronic devices is within the distance range of Bluetooth communication. Wherein, when the user speaks the wake-up word, multiple electronic devices can monitor the wake-up word. The embodiment of the present application does not limit the communication method when the above-mentioned multiple electronic devices negotiate which electronic device should respond to the above-mentioned wake-up word.

The above method can reduce the situation that multiple electronic devices respond to the wake-up word. However, according to the above device priority ranking, the electronic device that responds to the wake-up word determined through negotiation among the plurality of electronic devices is not necessarily the electronic device that the user wishes to wake up. That is to say, the above method is difficult to meet the actual needs of users. There may still be a problem of false wake-up when electronic equipment is woken up by the above-mentioned method.

An embodiment of the present application provides a method for waking up a device. In this method, the user can use the smart glasses to wake up the electronic device that he wants to wake up. Specifically, when the smart glasses are in the wearing state, it may be detected whether the user needs to wake up other electronic devices. If it is detected that the user needs to wake up other electronic devices, the smart glasses can collect images. The collected images are images within the user's field of view. The smart glasses can perform image recognition processing on the image to determine the type of electronic equipment contained in the image. The smart glasses can use a ranking algorithm to prioritize the electronic devices contained in this image. The smart glasses can acquire a local device list, and send a wake-up instruction to the above-mentioned electronic device with the highest priority and existing in the local device list. An electronic device with a voice interaction function can be woken up after receiving the wake-up command, while other electronic devices that have not received the wake-up command do not respond to the user's voice command.

Understandably, when a user wishes to wake up an electronic device, he usually looks at the electronic device and speaks a voice command. Then, if the user wears smart glasses, the smart glasses can collect images within the user's field of vision, and judge which electronic device the user wants to wake up based on the images. When the electronic device that the user wishes to wake up is determined, the smart glasses may send a wake-up instruction to the electronic device. When the wake-up command is received, the electronic device can be woken up, recognize the user's voice command and execute the operation corresponding to the voice command.

It can be seen from the above method that in a scene where there are multiple electronic devices with voice interaction functions, the user can use smart glasses to wake up the electronic device he wants to wake up. This can effectively reduce the situation of false wake-up, and bring a better user experience for the user to use the voice interaction function of the electronic device.

The above method involves communication between smart glasses and other electronic devices. In order to facilitate the understanding of the device wake-up method provided in the present application, a communication system provided in the present application is introduced below.

FIG. 3 exemplarily shows a schematic diagram of the communication system 10 .

The communication system 10 may include a plurality of electronic devices, and a communication connection 108 may be established between the plurality of electronic devices. For example, as shown in FIG. 3 , the communication system 10 may include smart glasses 101 , a mobile phone 102 , a headset 103 , a tablet computer 104 , a router 105 , a speaker 106 and a TV 107 . Not limited to the electronic devices shown in FIG. 3 , the communication system 10 may also include other types of electronic devices. For example, desktop computers, laptop computers, handheld computers, augmented reality (augmented reality, AR) equipment, virtual reality (virtual reality, VR) equipment, artificial intelligence (artificial intelligence, AI) equipment, car machines, game consoles, Other smart wearable devices may also include Internet of Things (IOT) devices or smart home devices such as smart water heaters, smart lamps, smart air conditioners, and the like. This embodiment of the present application does not limit it. For the structure of these electronic devices, reference may be made to the schematic structural diagram of the electronic device 100 shown in FIG. 1 .

In the communication system 10, a communication connection 108 may be established between electronic devices, and the communication connection 108 may be a near field communication connection. The near-field communication connection may be a wired connection, such as a universal serial bus (uniersalserialbus, USB) connection, or a wireless connection, such as a Bluetooth communication connection, a Wi-Fi communication connection, a wireless fidelity peer-to-peer , Wi-Fi P2P) communication connection and so on. The embodiment of the present application does not limit the specific manner of the foregoing near field communication connection.

Based on the communication system 10 shown in FIG. 3 , the local device list involved in this embodiment of the present application is introduced here.

In some embodiments, the local device list may include electronic devices connected to the same communication network. For example, electronic devices connected to the same home Wi-Fi in a family. Communication connections are established between multiple electronic devices in the local device list. Exemplarily, the above communication system 10 has a local device list. The electronic devices included in the communication system 10 are the electronic devices in the local device list. That is, the electronic device that joins the aforementioned communication connection 108 can be added to the aforementioned local device list. An electronic device that exits the communication connection 108 may be removed from the local device list. The local device list may be stored in one or more electronic devices included in the communication system 10, or may be stored in a cloud server.

All electronic devices in the communication system 10 can acquire and update the local device list. For example, any electronic device in the communication system 10 may update the local device list according to the detection of electronic devices joining or leaving the communication connection 108 . If the aforementioned local device list is stored in multiple electronic devices in the communication system 10, the local device list can be updated synchronously among the multiple electronic devices. In this way, the local device lists acquired by the electronic devices in the communication system 10 are consistent.

In some embodiments, the local device list may be created by an electronic device in the communication system 10 described above. The one electronic device may be, for example, the mobile phone 102 . The electronic devices added to the aforementioned local device list may be electronic devices that have undergone trusted identity authentication. The above-mentioned trusted identity authentication may be realized by an electronic device (such as the mobile phone 102) existing in the local device list. For example, handset 102 may add speaker 106 to the local device list in response to a user action agreeing to add speaker 106 to the local device list. The embodiment of the present application does not limit the specific implementation manner of the above-mentioned trusted identity authentication. The above process of trusted identity authentication may be, for example, a process of implementing network distribution for electronic devices.

The embodiment of the present application does not limit the communication connection manners of the electronic devices in the above-mentioned communication system 10 .

In a possible implementation manner, an electronic device in the communication system 10 may establish a communication connection 108 as shown in FIG. 4 . Wherein, the mobile phone 102 , the tablet computer 104 , the sound box 106 and the TV 107 can establish a Wi-Fi communication connection with the router 105 . The aforementioned electronic devices that establish a Wi-Fi communication connection with the router 105 can access the network through the router 105 to realize the function of surfing the Internet. That is to say, the mobile phone 102, the tablet computer 104, the router 105, the sound box 106 and the TV 107 are in the same local area network (like a home Wi-Fi). The electronic devices in the local device list may include the electronic devices in this one local area network. The smart glasses 101 and the earphone 103 can establish a Bluetooth communication connection with the mobile phone 102 . When the smart glasses 101 and the earphone 103 are connected to the mobile phone 102 via Bluetooth, and the mobile phone 102 is in the local area network, the mobile phone 102 can update the local device list. Specifically, the mobile phone 102 may add the smart glasses 101 and the earphone 103 to the local device list. Then, the electronic devices in the local device list may include smart glasses 101 , mobile phone 102 , earphone 103 , tablet computer 104 , router 105 , speaker 106 and TV 107 shown in FIG. 4 .

If the smart glasses 101 end the Bluetooth communication connection with the mobile phone 102, and the mobile phone 102 is in the local area network, the mobile phone 102 can update the local device list. Specifically, the mobile phone 102 may remove the smart glasses 101 from the local device list. If the mobile phone 102 ends the Wi-Fi communication connection with the router 105 (such as after the user goes out with the mobile phone), and the router 105 is in the above-mentioned local area network, the router 105 can update the above-mentioned local device list. Specifically, the router 105 may remove the mobile phone 105 from the local device list. Among them, after the mobile phone 102 is removed from the local device list, there are still electronic devices in the local device list that can detect whether the electronic devices (such as smart glasses 101 and earphones 103) that join the communication connection 108 through the mobile phone 102 are connected to the communication system 10. Electronic devices other than the mobile phone 102 are connected. If it is detected that the smart glasses 101 and the earphone 103 are only connected to the mobile phone 102, the smart glasses 101 and the earphone 103 may be removed from the local device list. If it is detected that the smart glasses 101 and the earphone 103 are also connected to other electronic devices (such as the tablet computer 104), the smart glasses 101 and the earphone 103 may still exist in the local device list.

As can be seen from the above implementation, the electronic devices in the local device list can be based on the electronic devices in the local area network established by the router 105 (such as mobile phones 102, tablet computers 104, sound boxes 106, and televisions 107), and the electronic devices in the local area network. An electronic device connected to the electronic device through other wireless connection methods (such as smart glasses 101, earphone 103).

In some embodiments, an application (application, APP) for controlling other electronic devices is installed in the mobile phone 102 . The APP can be, for example, a smart home APP. The electronic devices in the local device list can be the electronic devices (such as router 105, speaker 106, TV 107) that the mobile phone 102 can control through the smart home APP, and other electronic devices that are connected to the mobile phone 102 but cannot be controlled through the smart home APP (such as smart glasses 101, earphones 103). In a possible implementation, the mobile phone 102 and the electronic devices that can be controlled by the smart home APP are connected to the router 105. In response to user operations acting on the smart home APP, the mobile phone 102 can send control instructions to the aforementioned electronic devices that can be controlled by the smart home APP through the router 105 . Optionally, the mobile phone 102 can also directly communicate with the above-mentioned electronic devices that can be controlled by the smart home APP without forwarding by the router 105 . The embodiment of the present application does not limit the implementation manner in which the mobile phone 102 controls other electronic devices through the smart home APP.

It can be understood that the schematic structural diagrams of the communication system shown in FIG. 3 and FIG. 4 are only exemplary descriptions of the embodiments of the present application, and should not limit the present application.

The following specifically introduces a schematic diagram of a scenario where a user wakes up an electronic device by means of smart glasses involved in the embodiment of the present application.

As shown in FIG. 5 , electronic devices in a family may include smart glasses 101 , mobile phones 102 , routers 105 , speakers 106 , and televisions 107 . Wherein, the mobile phone 102 , the sound box 106 and the TV 107 all establish Wi-Fi communication connections with the router 105 . A user wears smart glasses 101 . The smart glasses 101 establish a Bluetooth communication connection with the mobile phone 102 . It can be seen from the foregoing embodiments that the smart glasses 101, the mobile phone 102, the router 105, the sound box 106, and the television 107 can form a communication system. The electronic devices in the local device list of the communication system include smart glasses 101 , mobile phones 102 , routers 105 , speakers 106 , and televisions 107 .

In the scenario shown in FIG. 5 , the user wishes to wake up the speaker 106 and instruct the speaker 106 to play music through a voice command. Among them, the user wears the smart glasses 101 and looks at the speaker 106 and says "Xiaoyi Xiaoyi, I want to listen to a song". The mobile phone 102, the sound box 106 and the TV 107 are all electronic devices with voice interaction function and semantic interaction function turned on. The wake-up words used to wake up the mobile phone 102, the speaker 106 and the TV 107 are the same, for example, "Xiaoyi Xiaoyi". The mobile phone 102, the sound box 106 and the TV 107 can all collect the voice input of the user through the microphone. The voice input above includes the wake-up word "Xiaoyi Xiaoyi" and the voice command "I want to listen to a song".

In a possible implementation manner, when the wake-up word is detected, the mobile phone 102, the speaker 106 and the TV 107 may all enter the pre-wake-up state from the wake-up word monitoring state.

The above-mentioned wake-up word monitoring state can collect ambient sound for the electronic device and identify whether the wake-up word is included in the ambient sound. In the aforementioned wake-up word monitoring state, the microphone and the low-power processor of the electronic device can work in real time. The microphone can be used to collect ambient sound. A low-power processor can be used to identify whether the wake word is contained in ambient sounds.

The aforementioned pre-awakening state may be a state in which the electronic device detects whether there are smart glasses in the local device list and whether the smart glasses are worn after listening to the wake-up word. That is to say, when listening to the wake-up word, the mobile phone 102, the sound box 106 and the TV 107 can detect whether the smart glasses 101 exist in the local device list and whether the smart glasses 101 are worn, instead of being woken up immediately in response to the wake-up word. In the above-mentioned pre-wake-up state, the electronic device may wait for receiving a wake-up instruction, and does not respond to the monitored wake-up words, voice instructions, and the like.

It should be noted that when not in the wake-up state (for example, in the wake-up word monitoring state), if a wake-up instruction is received, the electronic device may enter the wake-up state.

If it is detected that the smart glasses 101 do not exist in the local device list, for example, the smart glasses 101 do not exist in the home or the smart glasses 101 are not connected to the mobile phone 102, the mobile phone 102, the sound box 106 and the TV 107 can all enter the wake-up state from the above-mentioned pre-wake-up state. Alternatively, the mobile phone 102, the sound box 106 and the TV 107 can communicate with each other, negotiate and determine an electronic device to respond to the wake-up word. Wherein, the selected electronic device can enter the wake-up state from the above-mentioned pre-wake-up state. Other electronic devices can enter the above-mentioned wake-up word monitoring state again from the above-mentioned pre-wake-up state. That is, other electronic devices do not respond to the above-mentioned wake-up word.

The aforementioned wake-up state may indicate that the voice recognition application of the electronic device is in a state of being woken up. In the above wake-up state, the electronic device can start a speech recognition application. Specifically, the electronic device can start the application processor to recognize the voice command, and execute the operation corresponding to the voice command. It should be noted that, in the aforementioned wake-up state, the electronic device may also monitor in real time whether the ambient sound contains a wake-up word. In a possible implementation, after the electronic device enters the wake-up state, if no voice command is recognized in the ambient sound within a preset time period, the electronic device may enter the wake-up word monitoring state from the wake-up state.

If it is detected that the smart glasses 101 exist in the local device list, but the smart glasses 101 are not worn, the mobile phone 102, the sound box 106 and the TV 107 can all enter the wake-up state from the above-mentioned pre-wake-up state. Alternatively, the mobile phone 102, the sound box 106 and the TV 107 can communicate with each other, negotiate and determine an electronic device to respond to the wake-up word.

It can be understood that if the smart glasses 101 do not exist in the above local device list, or if the smart glasses 101 exist in the local device list but the smart glasses 101 are not worn, the user cannot wake himself up with the help of the smart glasses 101 Electronic devices that wish to wake up. Then, the electronic devices with voice interaction function may all be woken up after listening to the wake-up word, or negotiate and determine an electronic device that is most likely to be woken up by the user to respond to the wake-up word.

If it is detected that the smart glasses 101 exist in the local device list, and the smart glasses 101 are in the wearing state, the mobile phone 102, the sound box 106 and the TV 107 can wait for a wake-up instruction. Wherein, the mobile phone 102, the sound box 106 and the TV 107 may wait for a wake-up instruction within a preset time period. If a wake-up instruction is received within a preset time period, the electronic device that receives the wake-up instruction may enter a wake-up state from a pre-wake-up state. If no wake-up instruction is received within the preset time period, the electronic device may enter the wake-up word monitoring state again from the pre-wake-up state.

When the smart glasses 101 are in the wearing state, it may be detected whether the user needs to wake up other electronic devices.

In a possible implementation manner, the smart glasses 101 have a microphone and a processor with low power consumption. When in the wearing state, the microphone and the low power consumption processor of the smart glasses 101 may be in the working state. The smart glasses 101 can collect ambient sound through a microphone, and use a low-power processor to identify whether the ambient sound contains a wake-up word. When the wake-up word is detected, the smart glasses 101 may determine that the user needs to wake up other electronic devices. Further, the smart glasses 101 can collect images through a camera. The collected images are images within the user's field of view. The smart glasses can perform image recognition processing on the image to determine the type of electronic equipment contained in the image.

In the scene where the user wears the smart glasses 101 and looks at the speaker 106 and says "Xiaoyi Xiaoyi, I want to listen to a song", the image collected by the smart glasses 101 can be as shown in FIG. 6 . Electronic devices in the image include speakers 106 and television 107 . Wherein, the speaker 106 is located in the center of the image. Television 107 is located on the right edge of the image. The smart glasses can use a sorting algorithm to prioritize the electronic devices in this image. For example, the result of the above priority sorting is that the priority of the sound box 106 is higher than that of the TV 107 .

Further, the smart glasses 101 may obtain a local device list, and send a wake-up instruction to the above-mentioned electronic device with the highest priority and existing in the local device list. Since the speaker 106 and the TV 107 both exist in the local device list, and in the above priority sorting, the priority of the speaker 106 is higher than that of the TV 107, the smart glasses 101 can determine that the speaker 106 is the electronic device that the user wants to wake up. Then, the smart glasses 101 may send a wake-up instruction to the speaker 106 .

As shown in FIG. 5 , when a wake-up instruction is received, the speaker 106 may enter the wake-up state from the above-mentioned pre-wake-up state. Wherein, the speaker 106 can use the voice command recognition module to recognize the information contained in the sound after the wake-up word. The voice after the above-mentioned wake-up word contains the voice instruction "I want to listen to a song". The voice command recognition module of the speaker 106 can recognize the voice command. Then, the speaker 106 can execute the operation corresponding to the voice command through the voice command execution module, that is, play music. Exemplarily, the speaker 106 can answer "no problem" by voice, and start playing music. The embodiment of the present application does not limit the content of the voice answer of the above-mentioned speaker 106 .

The above-mentioned method of performing image recognition processing on an image by smart glasses and the method of prioritizing electronic devices in an image by using a sorting algorithm will be described in detail in subsequent embodiments, and will not be introduced here.

In a possible implementation manner, since the smart glasses 101 are connected with the mobile phone 102 , the smart glasses 101 may send the result of prioritization of the electronic devices included in the image to the mobile phone 102 . The mobile phone 102 may acquire the local device list, and determine the electronic device that the user wishes to wake up according to the local device list and the result of the prioritization. The above-mentioned electronic device that the user wishes to wake up is the above-mentioned electronic device with the highest priority and existing in the local device list. The mobile phone can send a wake-up instruction to the electronic device that the user wishes to wake up. Wherein, the mobile phone 102 may send a wake-up command to the electronic device that the user wishes to wake up through the router 102, or directly send a wake-up command to the electronic device that the user wishes to wake up.

The embodiment of the present application does not limit the method for the smart glasses 101 or the mobile phone 102 to send a wake-up instruction to the electronic device that the user wishes to wake up.

Optionally, the above-mentioned process of performing image recognition processing on the image and/or the process of prioritizing the electronic devices in the image by using a sorting algorithm may also be implemented by the mobile phone 102 . The above method can effectively save computing resources and power consumption of the smart glasses 101 .

In another possible implementation manner, the smart glasses 101 may be connected to the router 105 . When the smart glasses 101 detect that the user needs to wake up other electronic devices, they can collect images. When the image is obtained, the above-mentioned process of image recognition processing for the image and/or the process of prioritizing the electronic devices in the image by using a sorting algorithm and/or determining the electronic device that the user wants to wake up and sending a message to the electronic device that the user wants to wake up The process of waking up the instruction can also be realized by the router 105 . This can effectively save computing resources and power consumption of the smart glasses 101 .

It can be seen from the scenarios shown in FIG. 5 and FIG. 6 that when the smart glasses are in the wearing state, the electronic device with voice interaction function will not enter the wake-up state immediately after listening to the wake-up word. Smart glasses can be used to determine which electronic device the user wishes to wake up. When it is determined that the electronic device that the user wishes to wake up, the smart glasses or an electronic device (such as a mobile phone or a router) connected to the smart glasses may send a wake-up instruction to the electronic device that the user wishes to wake up. The electronic device that receives the wake-up instruction can enter the wake-up state. However, the electronic device that monitors the wake-up word but does not receive the wake-up instruction does not enter the wake-up state. By using the device wake-up method in the above scenario, the user can use the smart glasses to wake up the electronic device he wants to wake up. This can effectively reduce the situation of false wake-up, and bring a better user experience for the user to use the voice interaction function of the electronic device.

FIG. 7 and FIG. 8 exemplarily show another scenario where a user wakes up an electronic device by means of smart glasses according to an embodiment of the present application.

As shown in FIG. 7 , electronic devices in a family may include smart glasses 101 , mobile phones 102 , routers 105 , speakers 106 , and televisions 107 . For the connection relationship among the multiple electronic devices, reference may be made to the introduction of the embodiment shown in FIG. 5 above. I won't go into details here.

In the scenario shown in FIG. 7 , the user has awakened the speaker 106 by means of the smart glasses 101 , and instructed the speaker 106 to play music through a voice command. Further, the user wishes to wake up the mobile phone 102 and instruct the mobile phone 102 to send a short message through a voice command. As shown in FIG. 7 , the speaker 106 has played music in response to the user's voice instruction for playing music (such as "I want to listen to a song"). The user wears the smart glasses 101 and looks at the mobile phone 102 and says "Xiaoyi Xiaoyi, send a text message to Lao Zhang". The mobile phone 102, the sound box 106 and the TV 107 can all collect the voice input of the user through the microphone. The above-mentioned voice input includes the wake-up word "Xiaoyi Xiaoyi" and the voice command "send a text message to Lao Zhang".

In a possible implementation manner, before the wake-up word is monitored, the mobile phone 102, the speaker 106, and the TV 107 are all in a wake-up word monitoring state. When the wake-up word is monitored, the mobile phone 102, the speaker 106 and the TV 107 can all enter the pre-wake-up state from the wake-up word monitoring state.

In another possible implementation, the speaker 106 has not exited the wake-up state after receiving the wake-up instruction in the scene shown in FIG. 5 and entering the wake-up state. That is, before the wake-up word shown in FIG. 7 is monitored, the mobile phone 102 and the TV 107 are in the wake-up word monitoring state. The speaker 106 is in an awake state. When the wake-up word is detected, the mobile phone and the TV 107 can enter the pre-wake-up state from the wake-up word monitoring state. Speaker 106 can enter a pre-awake state from an awake state.

In the pre-awakening state, the mobile phone 102, the sound box 106 and the TV 107 can all obtain the local device list, and detect that the smart glasses 101 exist in the local device list and the smart glasses 101 are in the wearing state. Then, the mobile phone 102, the sound box 106 and the TV 107 can wait for the wake-up instruction, instead of entering the wake-up state immediately.

After the smart glasses 101 detect that the user needs to wake up other electronic devices, the method for determining which electronic device in the local device list is the electronic device that the user wants to wake up can refer to the embodiment shown in FIG. 5 above.

Wherein, the smart glasses 101 can collect images. The image is the image within the user's field of view. As shown in FIG. 8 , the electronic devices in this image include a mobile phone 102 . Referring to the methods of the foregoing embodiments, the mobile phone 102 is the electronic device that the user wishes to wake up.

Cell phone 102 may receive a wake-up instruction. When receiving the wake-up command, the mobile phone 102 can enter into the wake-up state, and recognize the information contained in the sound after the wake-up word. The voice after the above-mentioned wake-up word contains the voice instruction "send a text message to Lao Zhang". The voice command recognition module of the mobile phone 102 can recognize the voice command. Then, the mobile phone 102 can execute the operation corresponding to the voice command through the voice command execution module, that is, send a short message. Exemplarily, the mobile phone 102 may search whether there is a contact information named "Lao Zhang" in the contacts application. If it exists, the mobile phone 102 can answer "OK, please say the content of the short message" by voice. The embodiment of the present application does not limit the content of the above-mentioned voice answer of the mobile phone 102 .

The speaker 106 and the TV 107 may enter the wake-up word monitoring state from the pre-wake-up state if they do not receive a wake-up instruction within a preset period of time after entering the pre-wake-up state.

In some embodiments, the smart glasses 101 can send the collected images to the mobile phone 102, and instruct the mobile phone 102 to determine which electronic device is the electronic device that the user wishes to wake up. The mobile phone 102 may perform image recognition processing on the image, and use a sorting algorithm to prioritize the identified electronic devices contained in the image, so as to determine the electronic device that the user wishes to wake up. If the mobile phone 102 determines that the electronic device that the user wants to wake up is itself (ie, the mobile phone 102), the mobile phone 102 can enter the wake-up state without sending a wake-up command. If the mobile phone 102 determines that the electronic device that the user wishes to wake up is not itself, the mobile phone 102 may send a wake-up instruction to the determined electronic device that the user wishes to wake up.

It can be seen from the scenarios shown in FIG. 7 and FIG. 8 that the user can wake up the electronic device he wants to wake up with the help of smart glasses. This can effectively reduce the situation of false wake-up, and bring a better user experience for the user to use the voice interaction function of the electronic device.

In some embodiments, when the user wears the smart glasses 101, he can trigger the smart glasses 101 to recognize the electronic device he wants to wake up by touching a preset position of the smart glasses 101 (such as a position on the temple), and to wake up the electronic device he wants to wake up. The wake-up electronic device sends a wake-up command. Wherein, the user can speak the voice command directly after touching the preset position of the smart glasses 101 instead of saying the wake-up word. The electronic device that receives the wake-up instruction can recognize the user's voice instruction and execute the operation corresponding to the voice instruction. The above method can not only reduce false wake-ups, but also simplify user operations for users to control electronic devices through voice, and improve user experience.

FIG. 9A and FIG. 9B exemplarily show another scenario where a user wakes up an electronic device by means of smart glasses according to an embodiment of the present application.

As shown in FIG. 9A , electronic devices in a family may include smart glasses 101 , mobile phones 102 , routers 105 , speakers 106 , and televisions 107 . For the connection relationship among the multiple electronic devices, reference may be made to the introduction of the embodiment shown in FIG. 5 above. I won't repeat them here.

In the scenarios shown in FIG. 9A and FIG. 9B , the user wishes to wake up the speaker 106 and instruct the speaker 106 to play music through a voice command. Wherein, the user may wear the smart glasses 101, look at the sound box 106 and touch a preset position of the smart glasses 101 (such as a position on the temple).

In a possible implementation manner, when a touch operation acting on a preset position of the smart glasses 101 is detected, the smart glasses 101 may determine that the user needs to wake up other electronic devices. Further, the smart glasses 101 can collect images through a camera. The image is the image within the user's field of vision. The smart glasses can perform image recognition processing on the image to determine the type of electronic equipment contained in the image. Further, the smart glasses can use a sorting algorithm to prioritize the electronic devices in the image. The images collected by the smart glasses 101 in the scene shown in FIG. 9A may refer to the aforementioned images shown in FIG. 6 (including the sound box 106 and the TV 107 ). For example, the result of the above priority sorting is that the priority of the sound box 106 is higher than that of the TV 107 .

The embodiment of the present application does not limit the preset position of the above-mentioned smart glasses 101 .

The smart glasses 101 may obtain a local device list, and send a wake-up instruction to the above-mentioned electronic device with the highest priority and existing in the local device list. Since the speaker 106 and the TV 107 both exist in the local device list, and in the above priority sorting, the priority of the speaker 106 is higher than that of the TV 107, the smart glasses 101 can determine that the speaker 106 is the electronic device that the user wants to wake up. Then, the smart glasses 101 may send a wake-up instruction to the speaker 106 .

In a possible implementation manner, when the wake-up word is not monitored but the wake-up instruction is received, the electronic device may directly enter the wake-up state. As shown in FIG. 9A , the mobile phone 102 , the speaker 106 and the TV 107 are all in the wake-up word monitoring state. When receiving the wake-up instruction from the smart glasses 101, the speaker 106 can enter the wake-up state.

When entering the wake-up state, the speaker 106 can recognize the information in the ambient sound after receiving the wake-up command through the voice command recognition module. If the voice command is not recognized from the ambient sound, the speaker 106 can voice answer "I am here" to remind the user that he has been awakened and can execute the user's voice command. The embodiment of the present application does not limit the content of the voice answer after the speaker 106 receives the wake-up instruction. If a voice instruction is recognized from the ambient sound, such as "I want to listen to a song", the speaker 106 can answer "no problem" and start playing music.

As shown in FIG. 9B , after hearing the voice answer "I'm here" from the speaker 106, the user can issue a voice command "I want to listen to a song" to the speaker 106. The speaker 106 can recognize the voice command through the voice command recognition module, and execute the operation corresponding to the voice command through the voice command execution module, that is, play music. For example, after the speaker 106 recognizes the voice instruction "I want to listen to a song", it can voice answer "no problem" and start playing music.

Optionally, when entering the wake-up state, the speaker 106 can use the voice command recognition module to recognize the information in the ambient sound collected from time A before receiving the wake-up command. Exemplarily, the user may say the voice command "I want to listen to a song" while looking at the speaker 106 and touching the preset position of the smart glasses 101 . That is to say, the user may speak the voice command before the speaker 106 receives the wake-up command. Then, the speaker 106 recognizes the voice command from the ambient sound collected within a period of time before receiving the wake-up command, which can reduce the occurrence of missed voice command recognition and improve user experience.

It should be noted that the smart glasses 101 can be connected to the mobile phone 102 or to the router 105 . The above-mentioned process of performing image recognition processing on an image and/or the process of prioritizing electronic devices in an image by using a sorting algorithm may also be implemented by the mobile phone 102 or by the router 105 . This can effectively save computing resources and power consumption of the smart glasses 101 .

As can be seen from the scenarios shown in FIGS. 9A and 9B above, when a user wants to control an electronic device through voice, he can wear smart glasses to look at the electronic device, touch a preset position of the smart glasses, and speak a voice command. When determining that the user wishes to wake up other electronic devices, the smart glasses can determine which electronic device in the local device list is the electronic device that the user wishes to wake up, and wake up the electronic device that the user wishes to wake up. In this scenario, the user can directly issue voice commands without uttering the wake-up word. This can not only reduce false wake-ups, but also simplify user operations for users to control electronic devices through voice, and improve user experience.

In some embodiments, when wearing the smart glasses 101 , the user can trigger the smart glasses 101 to identify the electronic device that the user wants to wake up by touching a preset position of the smart glasses 101 (such as a position on the temple). Moreover, the user can speak the wake-up word before speaking the voice command. Then, the electronic device that receives the wake-up instruction can enter the wake-up state. If the wake-up word is monitored, the electronic device in the wake-up state can recognize whether the sound after the wake-up word contains a voice command through the voice command recognition module. Further, when the voice command is recognized, the electronic device can execute the operation corresponding to the voice command through the voice command executing module.

In some embodiments, when a wake-up word is detected, the smart glasses 101 may collect an image, and determine the electronic device that the user wishes to wake up according to the image. In a scenario where both user A and user B are at home, and user A wears smart glasses, and user B speaks a wake-up word to wake up the device, there may be no electronic device in the image collected by the smart glasses 101 . When monitoring the wake-up word (that is, user B's voice input), the smart glasses 101 can collect an image, and perform image recognition processing on the image. When it is recognized that there is no electronic device in the image, the smart glasses 101 may send an indication message to the electronic devices in the local device list (such as the mobile phone 102, the sound box 106, the TV 107, etc.). The indication message may be used to indicate that the smart glasses 101 will not send a wake-up instruction. When the above-mentioned wake-up word (that is, the voice input of user B) is monitored, the electronic device (such as mobile phone 102, speaker 106, TV 107, etc.) is worn. If the smart glasses exist in the local device list and the smart glasses are worn, the electronic device with the voice interaction function enabled can wait for a wake-up instruction. When receiving the above indication message from the smart glasses, the electronic devices with the voice interaction function enabled may all enter the wake-up state, or one of the electronic devices with the voice interaction function enabled enters the wake-up state. Exemplarily, the electronic device with the voice interaction function enabled may negotiate and select the electronic device that receives the sound signal containing the wake-up word with the highest intensity according to the strength of the received sound signal containing the wake-up word. The electronic device that receives the sound signal containing the wake-up word with the highest intensity may enter the wake-up state. Other devices can enter the wake-up word monitoring state from the pre-wake-up state.

That is to say, if the user who is not wearing smart glasses wakes up the device through the wake-up word, and there is no electronic device with the voice interaction function enabled in the field of view of the user wearing the smart glasses, at least one of the electronic devices with the voice interaction function is enabled. The device may enter the wake state in response to the above wake word. In this way, when the user who does not wear the smart glasses is in the same environment as the user who wears the smart glasses, the situation that the user who does not wear the smart glasses cannot wake up the device through the wake-up word.

It can be seen from the foregoing embodiments that an electronic device having a voice interaction function and the voice interaction function is turned on can always monitor whether the ambient sound contains a wake-up word. When the wake-up word is detected, the electronic device may enter a pre-wake-up state.

The implementation method of whether the electronic device monitors whether the ambient sound contains the wake-up word is specifically introduced below.

In some embodiments, the electronic device can collect ambient sound through a microphone. Wherein, when the user speaks the wake-up voice (such as "Xiao Yi Xiao Yi") near the electronic device, the wake-up voice may be included in the ambient sound. After collecting the ambient sound, the electronic device can separate the user's wake-up voice from the ambient sound. Next, the electronic device may decode a phoneme sequence from the user's speech signal by using an acoustic model from the wake-up speech. After decoding the phoneme sequence from the wake-up speech, the electronic device can determine whether the decoded phoneme sequence matches the stored wake-up word phoneme sequence. If yes, it indicates that the wake-up voice includes a wake-up word. When it is determined that the ambient sound contains a wake-up word, the electronic device may enter a pre-wake-up state. The embodiment of the present application does not specifically limit the above wake-up voice.

In other embodiments, the electronic device may collect ambient sound through a microphone. Wherein, when the user speaks the wake-up voice (such as "Xiao Yi Xiao Yi") near the electronic device, the wake-up voice may be included in the ambient sound. After collecting the ambient sound, the electronic device can separate the user's wake-up voice from the ambient sound. Next, the electronic device may decode a phoneme sequence from the user's speech signal by using an acoustic model from the wake-up speech. Then, through the speech model and the pronunciation dictionary of the speech model, the electronic device can further decode text information from the decoded phoneme sequence. After decoding the text information, the electronic device can determine whether the text information decoded from the wake-up voice contains the stored wake-up word text. If yes, it indicates that the wake-up voice includes a wake-up word. When it is determined that the ambient sound contains a wake-up word, the electronic device may enter a pre-wake-up state.

In a possible implementation manner, the electronic device may extract a wake-up word and a voiceprint feature of the user from the user's wake-up voice. When the wake-up word matches the stored wake-up word template, and the user's voiceprint feature matches the stored voiceprint feature template, the electronic device may enter a pre-wake-up state. This can realize that only a specific user can wake up the electronic device and control the electronic device through voice commands, which improves the information security of the electronic device.

The embodiment of the present application does not limit the specific method for the electronic device to monitor whether the ambient sound contains the wake-up word.

In some embodiments, the electronic device in the wake-up word monitoring state or in the pre-wake-up state may enter the wake-up state after receiving the wake-up instruction. The above wake-up instruction may be sent by smart glasses or other electronic devices that establish a communication connection with the smart glasses. The above wake-up instruction can be used to instruct the electronic device to enter the wake-up state.

In the wake-up state, the electronic device can start a speech recognition application. Specifically, starting the voice recognition application may start the voice command recognition module and the voice command execution module in the application processor of the electronic device. The electronic device can recognize the user's voice command in the ambient sound through the voice command recognition module, and execute the operation corresponding to the voice command through the voice command execution module. In the wake-up state, the electronic device can also monitor in real time whether the ambient sound contains the wake-up word. If the electronic device in the wake-up state monitors the wake-up word, the electronic device may enter the pre-wake-up state from the wake-up state.

It can be understood that the electronic device in the wake-up word monitoring state and in the wake-up state can monitor whether the wake-up word is included in the ambient sound in real time. However, the electronic device in the wake-up word monitoring state cannot recognize the user's voice command and perform the user operation corresponding to the voice command. For example, when in the wake word monitoring state, the application processor of the electronic device is in a dormant state.

In some embodiments, after the electronic device with the voice interaction function and the voice interaction function is turned on, after listening to the wake-up word, it can determine whether the smart glasses exist in the local device list and whether the smart glasses are in the wearing state. Immediately to wake up. It can be understood that when the smart glasses exist in the local device list and the smart glasses are in the wearing state, the possibility of the user waking up the electronic device by means of the smart glasses is high. If the smart glasses do not exist in the local device list (for example, the user does not have smart glasses) or the smart glasses exist in the local device list but the smart glasses are not in the wearing state, the possibility of the user waking up the electronic device by means of the smart glasses is low. Then, the electronic device that hears the wake-up word and enters the pre-wake-up state can determine whether to enter the wake-up state according to the method of directly waking up the electronic device through the wake-up word provided in the embodiment of the present application.

The following specifically introduces the flow chart of the method for the electronic device to determine whether it enters the wake-up state according to whether there are smart glasses provided by the embodiment of the present application.

As shown in FIG. 10, the method may include steps S101-S106. in:

S101. The electronic device monitors a wake-up word.

The electronic device can be any of the electronic devices that exist in the local device list and whose voice interaction function is turned on. The implementation method for the electronic device to collect ambient sound and identify whether there is a wake-up word in the ambient sound may refer to the foregoing embodiments, and details are not repeated here.

When the wake-up word is detected, the electronic device may enter a pre-wake-up state.

S102. The electronic device queries whether the smart glasses exist in the local device list.

In the pre-awakening state, the electronic device can acquire a local device list. For the method for updating and storing the local device list, reference may be made to the foregoing embodiments. Exemplarily, electronic devices such as mobile phones, speakers, and TVs are all connected to the router and connected to the same home Wi-Fi. Phones, speakers, TVs, and routers all exist in one local device list. If the smart glasses establish a Bluetooth communication connection with the mobile phone, the electronic devices included in the local device list can add the smart glasses. In this way, an electronic device (such as a mobile phone, a sound box, and a TV) can inquire that there are smart glasses in the local device list.

Understandably, if the user does not have smart glasses, or the smart glasses have not established a communication connection with any electronic device in the local device list (for example, the smart glasses are turned off), then there are no smart glasses in the local device list.

S103. If it is found that smart glasses exist in the local device list, the electronic device may determine whether the smart glasses are in a wearing state.

It can be understood that the images collected when the smart glasses are in the wearing state may be equivalent to images within the user's field of view. If the smart glasses are not being worn, the images collected by the smart glasses cannot be considered as images within the user's field of vision. That is to say, the smart glasses in the wearing state can more accurately determine the electronic device that the user wishes to wake up.

After inquiring that the smart glasses exist in the local device list, the electronic device can further determine whether the smart glasses are in a wearing state. In a possible implementation manner, the smart glasses establish a Bluetooth communication connection with the mobile phone. Electronic devices such as speakers and TVs can obtain the wearing status of the smart glasses through the mobile phone. Wherein, the mobile phone can send a message to the smart glasses to ask whether the smart glasses are in the wearing state.

Smart glasses can perform wearing detection. Exemplarily, the smart glasses can determine whether they are in a wearing state by detecting their posture through a gyroscope sensor and an acceleration sensor. Alternatively, smart glasses can use eye-tracking technology to determine whether they are wearing them. The embodiment of the present application does not limit the method for detecting wearing of smart glasses. Wherein, for a specific implementation method of wearing detection, reference may be made to the prior art. This embodiment of the present application does not describe it in detail.

In response to the message from the mobile phone asking whether the smart glasses are in the wearing state, the smart glasses may send the wearing detection result to the mobile phone. In this way, electronic devices such as mobile phones, speakers, and televisions can obtain the wearing status of the smart glasses.

In some embodiments, step S103 is optional. Exemplarily, after the electronic device determines that smart glasses exist in the local device list, it may directly execute the following step S104.

S104. If the smart glasses are in the wearing state, the electronic device may determine whether a wake-up instruction is received within a preset time period.

When it is determined that the smart glasses are in a wearing state, the electronic device may wait for a wake-up instruction. Wherein, after the smart glasses determine the electronic device that the user wishes to wake up, they may send a wake-up instruction to the electronic device that the user wishes to wake up.

In some embodiments, the electronic device may wait for a preset period of time after determining that the smart glasses are in the wearing state. If the wake-up instruction is received within the preset time period, the electronic device may execute the following step S105. If no wake-up instruction is received within the preset time period, the electronic device may execute the following step S106. The embodiment of the present application does not limit the length of the foregoing preset time period.

S105. If a wake-up instruction is received within a preset time period, or if there is no smart glasses in the local device list, or if there are smart glasses in the local device list but the smart glasses are not being worn, the electronic device may enter the wake-up state.

If the electronic device receives the wake-up instruction within the preset time period, the electronic device is the target wake-up device (ie, the electronic device that the user wishes to wake up). In response to a wake-up instruction, the electronic device may enter a wake-up state.

If there are no smart glasses in the local device list, or if there are smart glasses in the local device list but the smart glasses are not being worn, the user will not use the smart glasses to wake up other electronic devices. Then, in response to the detected wake-up word, the electronic device may enter a wake-up state.

Optionally, if the smart glasses do not exist in the local device list, or if the smart glasses exist in the local device list but the smart glasses are not in the wearing state, multiple electronic devices that monitor the wake-up word can communicate with each other, and negotiate to determine the smart glasses. One of the electronic devices enters the wake-up state, and other electronic devices may not enter the wake-up state.

In a possible implementation manner, the multiple electronic devices may determine the intensity of the sound signal corresponding to the wake-up word that they have monitored. Understandably, the greater the intensity of the sound signal received by an electronic device, the closer the distance between the electronic device and the user. These multiple electronic devices can all send information including the intensity of the sound signal they receive to each other. Further, the multiple electronic devices may negotiate to determine the electronic device with the highest strength of the received sound signal. The electronic device that receives the sound signal with the highest intensity may enter the wake-up state, and other electronic devices may not enter the wake-up state.

In the embodiment of the present application, when the electronic device determines that the user will not wake up the electronic device through the smart glasses (for example, the smart glasses do not exist in the local device list, or the smart glasses exist in the local device list but the smart glasses are not wearing state), the method of responding to the monitored wake-up word is not limited. Wherein, the specific implementation method can refer to the implementation method provided by the embodiment of the present application, when there are multiple electronic devices with the voice interaction function enabled in an environment, the multiple electronic devices respond to the monitored wake-up words. This embodiment of the present application does not describe it in detail.

S106. If no wake-up command is received within a preset time period, the electronic device may enter a wake-up word monitoring state.

If the electronic device determines that the smart glasses are in the wearing state, but does not receive a wake-up instruction within a preset time period, then the electronic device is not a target wake-up device. The electronic device can enter a wake-up word monitoring state from a pre-wake-up state.

From the method shown in FIG. 10 above, it can be seen that after the electronic device with the voice interaction function enabled listens to the wake-up word, it can first determine whether the user will wake up the device with the help of smart glasses. If it is determined that the user will use the smart glasses to wake up the device, the electronic device may wait for a wake-up instruction. If it is determined that the user will not use the smart glasses to wake up the device, the electronic device may respond to the monitored wake-up word. In this way, when the user wears the smart glasses, the electronic device that he wishes to wake up can be woken up by means of the smart glasses. When the user is not wearing the smart glasses, the electronic device can be directly woken up through the wake-up word.

In some embodiments, an electronic device with a voice interaction function may have a smart wake-up switch. Alternatively, the smart home APP for controlling the above-mentioned electronic device with voice interaction function has a smart wake-up control. The smart wake-up control can be used to turn off or turn on the above-mentioned smart wake-up switch. Wherein, when the above-mentioned smart wake-up switch is turned on, the electronic device may execute the method shown in FIG. 10 after listening to the wake-up word. In this way, whether the user wears the smart glasses or not, the electronic device can be conveniently woken up. Among them, with the help of smart glasses, users can more accurately wake up the electronic devices they want to wake up.

The following introduces a schematic structural diagram of smart glasses provided by an embodiment of the present application in combination with the aforementioned scenario of device wake-up by means of smart glasses.

As shown in FIG. 11 , the smart glasses may include a user behavior recognition module 1101 , an image collection module 1102 , an image recognition module 1103 , a device priority determination module 1104 and a device wakeup module 1105 . The multiple modules can be coupled to each other via a bus. in:

The user behavior recognition module 1101 can be used to detect whether the user needs to wake up other electronic devices.

The user behavior recognition module 1101 may include, but is not limited to: a pressure sensor, a voice recognition sensor, and an inclination sensor.

In a possible implementation manner, the user behavior recognition module 1101 may use a voice recognition sensor to recognize whether the collected ambient sound contains a preset wake-up word. When listening to the preset wake-up word in the ambient sound, the user behavior recognition module 1101 can determine that the user needs to wake up other electronic devices. Then, the smart glasses can collect images through the image collection module 1102 .

Wherein, the aforementioned preset wake-up words may be stored in the smart glasses. If the wake-up word used to wake up the electronic device whose voice interaction function is enabled in the same local device list as the smart glasses is updated (for example, the user resets the wake-up word), the wake-up word stored in the smart glasses can also be updated synchronously. Exemplarily, the smart glasses establish a communication connection with the mobile phone. A smart home APP that controls electronic devices such as speakers and TVs is installed in the mobile phone. The wake-up word for waking up the speaker may be modified in response to a user operation acting on the smart home APP for resetting the wake-up word for the speaker. A modified wake-up word for waking up the speaker can be stored in the mobile phone. The smart glasses can obtain the above-mentioned modified wake-up word for waking up the speaker from the mobile phone. The embodiment of the present application does not limit the method for the smart glasses to acquire the wake-up word for waking up the electronic device.

In a possible implementation manner, the user behavior recognition module 1101 may use a pressure sensor to detect whether there is a user's touch operation on a preset position of the smart glasses. For example, when detecting a user operation in which a position on the temple is touched twice, the user behavior recognition module 1101 may determine that the user needs to wake up other electronic devices. Then, the smart glasses can collect images through the image collection module 1102 .

The embodiment of the present application does not limit the specific implementation method for the user behavior identification module 1101 to detect whether the user needs to wake up other electronic devices. For example, the user behavior recognition module 1101 may also detect whether the user needs to wake up the electronic device by judging whether the user blinks in a preset manner.

It should be noted that the smart glasses may also include a wearing detection module (not shown in FIG. 11 ). Before the detection by the user behavior recognition module 1101, the wearing detection module can detect whether the smart glasses are in the wearing state. If it is detected that the smart glasses are in the wearing state, the user behavior recognition module 1101 may perform the detection. If it is detected that the smart glasses are not being worn, the smart glasses may be in a dormant state. The fact that the smart glasses are in a dormant state may indicate that all components in the smart glasses except the wearing detection module are in a dormant state. This saves power consumption of the smart glasses. Wherein, the implementation method of detecting whether the smart glasses are in the wearing state by the wearing detection module can refer to the foregoing embodiments. I won't go into details here.

The image capture module 1102 can be used to capture images.

The image acquisition module 1102 may include but is not limited to a camera.

When the smart glasses are in the wearing state, the images collected by the smart glasses through the image acquisition module 1102 may be equivalent to the images within the user's field of vision (such as the images shown in FIGS. 6 and 8 in the foregoing embodiments). The embodiment of the present application does not limit the installation position of the camera in the image acquisition module 1102 on the smart glasses.

The image recognition module 1103 can be used to perform image recognition processing on the image to determine the electronic equipment included in the image.

The image recognition module 1103 may include a device recognition model. The device recognition model may be a neural network model. The device recognition model can be obtained through off-line training. Wherein, the input of the device recognition model may include an image. One or more electronic devices may be included in the image. The output of the device recognition model may include but not limited to the following features: type of electronic device, recognition accuracy, and viewing angle deviation.

Smart glasses can store trained device recognition models before leaving the factory. Optionally, the above device identification model can be updated. The smart glasses can obtain an updated device recognition model from the server used to train the above device recognition model.

The image recognition module 1103 can use the device recognition model to determine the type of electronic device in the image, recognition accuracy, viewing angle deviation and other characteristics. Wherein, the type of the electronic device may include the category of the electronic device and the specific model of the electronic device. For example, the image recognition module 1103 determines that the type of the speaker 106 shown in FIG. 6 is a speaker Sound X, and the type of the TV 107 is an electronic device of a smart screen S Pro 65. The sound box is a category of the sound box 106, and Sound X is a specific model of the sound box 106. The recognition accuracy may represent the accuracy of recognizing the type of an electronic device in the image. The higher the recognition accuracy rate of an electronic device, the greater the possibility that the type of this electronic device is actually the type determined by the image recognition module 1103. For example, the higher the recognition accuracy rate of the image recognition module 1103 determining that the speaker 106 shown in FIG. 6 is the speaker Sound X, the greater the possibility that the speaker 106 is the speaker Sound X. The viewing angle deviation can be used to represent the distance between the electronic device and the center of the user's field of view within the user's field of view. The smaller the viewing angle deviation of the electronic device is, the closer the position of the electronic device is to the center of the user's field of view. The larger the viewing angle deviation of the electronic device is, the closer the position of the electronic device is to the edge of the user's field of view. It can be understood that the viewing angle deviation of the electronic device can be determined through the position of the electronic device in the image collected by the above-mentioned image collection module 1102 . The closer the position of the electronic device in the image is to the center of the image, the smaller the viewing angle deviation of the electronic device is. The farther the position of the electronic device in the image is from the center of the image, the greater the deviation of the viewing angle of the electronic device.

The embodiment of the present application does not limit the specific training method of the above-mentioned device recognition model.

In some embodiments, the output of the above-mentioned device recognition model may also include but not limited to the following features: electronic device category, recognition accuracy, and viewing angle deviation. That is, when the image recognition module 1103 recognizes the electronic device included in the image, it may only recognize the category of the electronic device (such as the electronic device whose category is a sound box), without being accurate to the model of the electronic device. Then in the subsequent process, the device priority determining module 1104 may also determine the priority of the electronic device according to the category of the electronic device, recognition accuracy and viewing angle deviation.

After obtaining features such as the type of the electronic device in the determined image, recognition accuracy, and viewing angle deviation, the image recognition module 1103 may transfer these features to the device priority determination module 1104 .

The device priority determination module 1104 may be used to prioritize the electronic devices included in the image determined by the image recognition module 1103 .

The device priority determination module 1104 may use a ranking algorithm to prioritize electronic devices included in the image.

In a possible implementation manner, the above sorting algorithm may be: Y=β ₁ *type+β ₂ *α+β ₃ *θ. Wherein, Y may represent the priority of the electronic device. The larger the value of Y, the higher the priority of the electronic device. type may represent a type priority value determined according to the type of the electronic device. α can represent the recognition accuracy of the electronic device. θ may represent the viewing angle deviation of the electronic device. β ₁ , β ₂ , and β ₃ may respectively represent the type priority value of the electronic device, the recognition accuracy rate, and the weight of the viewing angle deviation. β ₁ , β ₂ , and β ₃ are all positive numbers less than 1. The sum of β ₁ , β ₂ , and β ₃ may be 1. The values of β ₁ , β ₂ , and β ₃ can be set according to empirical values. Optionally, the values of β ₁ , β ₂ , and β ₃ can be updated according to an optimization algorithm, so that the electronic device with the highest priority is the electronic device that the user wishes to wake up. The embodiment of the present application does not specifically limit the above values of β ₁ , β ₂ , and β ₃ .

It can be understood that, in response to the monitored wake-up words, multiple electronic devices with voice interaction functions may be prioritized to be woken up according to categories. For example, Speaker > TV > Tablet > Phone. That is to say, the value of the feature type in the above sorting algorithm may have the following size distribution: type of sound box>type of TV>type of tablet computer>type of mobile phone. The embodiment of the present application does not limit the above-mentioned wake-up priority sorting determined according to the type of the electronic device.

The higher the recognition accuracy of the electronic device, the greater the probability that the electronic device can match the electronic device in the local device list, and the greater the probability that the electronic device is successfully awakened.

The smaller the viewing angle deviation of the electronic device and the closer the position of the electronic device is to the center of the user's field of vision, the greater the probability that the electronic device is the electronic device that the user wishes to wake up.

Not limited to the above-mentioned type of electronic device, recognition accuracy, and viewing angle deviation, the above-mentioned image recognition module 1103 may also extract more features of the electronic device contained in the image from the image. The device priority determining module 1104 may determine the priority of each electronic device according to more or less features. For example, the device priority determining module 1104 may also determine the priority of the electronic device according to one or more of the three characteristics of the electronic device category, recognition accuracy, and viewing angle deviation.

In some embodiments, the wake-up words used by the user to wake up different electronic devices may be different. When the smart glasses detect that the user needs to wake up other electronic devices and the wake-up word is heard, the device priority determination module 1104 can first screen the electronic devices contained in the image. Wherein, if the wake-up word used to wake up an electronic device does not match the wake-up word detected by the smart glasses, the device priority determination module 1104 may exclude this electronic device. Further, the device priority determination module 1104 may perform priority sorting on electronic devices that are not excluded in the image. Optionally, if the wake-up word used to wake up an electronic device does not match the wake-up word detected by the smart glasses, the device priority determination module 1104 may determine the priority of this electronic device as the lowest priority. In this way, it is possible to avoid the situation that the smart glasses cannot wake up the user who wishes to wake up due to an error in device identification based on the collected images.

Optionally, the aforementioned screening of electronic devices included in the image may also be implemented by the aforementioned image recognition module 1103 .

Exemplarily, the image recognition module 1103 performs image recognition on the image shown in FIG. 6 , and transmits the types, recognition accuracy, and viewing angle deviation of the sound box 106 and the TV 107 in the image to the device priority determination module 1104 . The device priority determination module 1104 performs priority sorting on the two electronic devices, and the priority list shown in the following table 1 can be obtained:

优先级列表 priority list

音箱106Speaker 106
电视107 TV 107

Table 1

It can be seen from Table 1 that the priority of the speaker 106 is higher than that of the TV 107 . In the above priority list, the electronic device may be represented by its type (such as a sound box Sound X). The embodiment of the present application does not limit the content of the electronic device in the priority list.

When the above priority list is obtained, the device priority determination module 1104 may transmit the above priority list to the device wakeup module 1105 .

The device wake-up module 1105 can be used to determine the target wake-up device (that is, the electronic device that the user wants to wake up) according to the local device list and the priority of the electronic devices included in the image, and send a wake-up instruction to the target wake-up device.

When receiving the above priority list, the device wakeup module 1105 may match the electronic devices in the priority list with the electronic devices in the local device list in descending order of priority. According to the priority list and the local device list, the device wake-up module 1105 may determine the electronic device with the highest priority in the priority list and existing in the local device list as the target wake-up device. The device wake-up module 1105 may send a wake-up instruction to the target wake-up device. Wherein, the wake-up instruction may be directly sent by the smart glasses to the target wake-up device. Alternatively, the wake-up instruction may also be forwarded to the target wake-up device via a mobile phone or a router, such as an electronic device connected to the smart glasses. This embodiment of the present application does not limit it.

Exemplarily, in the scenario shown in FIG. 5, the device wake-up module 1105 of the smart glasses can obtain the local device list shown in Table 2 below:

本地设备列表local device list
手机102 mobile phone 102
音箱106 Speaker 106
电视107 TV 107
智能眼镜101 Smart Glasses 101

...

Table 2

It can be known from Table 1 and Table 2 that the device wake-up module 1105 can determine the speaker 106 as the target wake-up device, and send a wake-up instruction to the speaker 106 .

In some embodiments, the local device list includes multiple electronic devices of the same type. Exemplarily, the local device list includes the speaker 106 . The speaker 106 is specifically a speaker Sound X. In addition to the speaker 106, the local device list also includes a speaker Sound X. That is, two speakers, Sound X, are included in the local device list. If the target wake-up device determined by the device wake-up module 1105 is the sound box Sound X, the device wake-up module 1105 may send an indication message to the two sound box Sound X included in the local device list. The indication message may be used to instruct the two speakers, the Sound X, to determine through negotiation that one enters the wake-up state. In a possible implementation manner, when receiving the indication message, the two speakers Sound X can determine who enters the wake-up state according to the intensity of the sound signal containing the wake-up word received respectively. It can be understood that the higher the intensity of the received sound signal containing the wake-up word, the closer the distance between the electronic device and the user, and the greater the possibility that the electronic device is the electronic device that the user wishes to wake up. Then, the speaker Sound X that receives the sound signal containing the wake-up word with the highest intensity can enter the wake-up state.

From the schematic structural diagram of the smart glasses shown in FIG. 11 , it can be seen that the smart glasses can determine which electronic device the user wants to wake up by collecting images within the user's field of vision. In this way, the user can use the smart glasses to wake up the electronic device he wants to wake up, reducing the situation of false wakeup.

In some embodiments, the smart glasses may only include the above-mentioned user behavior recognition module 1101 , image collection module 1102 , image recognition module 1103 and device priority determination module 1104 . The above-mentioned device wake-up module 1105 may be included in an electronic device connected to smart glasses such as a mobile phone or a router. Here, the device wake-up module 1105 is included in the mobile phone as an example for illustration. Smart glasses can establish a Bluetooth communication connection with a mobile phone. When the smart glasses obtain the priority list through the device priority determining module 1104 . The smart glasses can send that priority list to the phone. The device wake-up module 1105 in the mobile phone can determine the target wake-up device, and send a wake-up instruction to the target wake-up device. For the method for the device wake-up module 1105 to determine the target wake-up device, reference may be made to the foregoing embodiments.

In the above embodiment, the smart glasses may not determine the target wake-up device, and send a wake-up instruction to the target wake-up device. This can reduce the requirements on the computing power and storage capacity of the smart glasses, and save the power consumption of the smart glasses.

In some embodiments, the smart glasses may only include the above-mentioned user behavior recognition module 1101 , image collection module 1102 and image recognition module 1103 . The above device priority determination module 1104 and device wakeup module 1105 may be included in electronic devices connected to smart glasses such as mobile phones or routers. Here, the device priority determination module 1104 and the device wake-up module 1105 are included in the mobile phone as an example for illustration. Smart glasses can establish a Bluetooth communication connection with a mobile phone. When the smart glasses determine the type of electronic device in the image, recognition accuracy, viewing angle deviation and other characteristics through the image recognition module 1103, the smart glasses can send these characteristics to the mobile phone. The mobile phone can determine the priority of electronic devices in the image through the device priority determination module 1104 to obtain a priority list. Further, according to the priority list and the local device list, the device wake-up module 1105 in the mobile phone can determine the target wake-up device, and send a wake-up instruction to the target wake-up device.

In the above embodiment, the smart glasses may not determine the priority of the electronic device and the target wake-up device, and send a wake-up instruction to the target wake-up device. This can reduce the requirements on the computing power and storage capacity of the smart glasses, and save the power consumption of the smart glasses.

In some embodiments, the smart glasses may only include the above-mentioned user behavior recognition module 1101 and image collection module 1102. The above image recognition module 1103, device priority determination module 1104 and device wakeup module 1105 may be included in electronic devices connected to smart glasses such as mobile phones or routers. Here, the image recognition module 1103, the device priority determination module 1104 and the device wakeup module 1105 are included in the mobile phone as an example for illustration. Smart glasses can establish a Bluetooth communication connection with a mobile phone. When the smart glasses acquire an image through the image acquisition module 1102, the image can be sent to the mobile phone. When receiving the image, the mobile phone can determine the target wake-up device through the image recognition module 1103 , device priority determination module 1104 and device wake-up module 1105 , and send a wake-up instruction to the target wake-up device. For the specific method for the mobile phone to determine the target to wake up the device, reference may be made to the foregoing embodiments. I won't go into details here.

In the above embodiment, the smart glasses can perform image recognition processing on the image without the storage device identification module, and send a wake-up instruction to the target wake-up device without determining the priority of the electronic device and the target wake-up device. This can reduce the requirements on the computing power and storage capacity of the smart glasses, and save the power consumption of the smart glasses.

In some embodiments, the above operation of judging whether the user needs to wake up other electronic devices may also be completed by other electronic devices (such as mobile phones) connected to the smart glasses. For example, when the mobile phone monitors the wake-up word, the mobile phone can send an instruction to the smart glasses to collect images. After the smart glasses capture the image, the image can be sent to the mobile phone. Based on this image, the phone can determine a target to wake the device. Optionally, after the smart glasses collect the image, the target wake-up device may also be determined according to the image.

FIG. 12 exemplarily shows a flow chart of a method for waking up a device provided by an embodiment of the present application.

As shown in FIG. 12, the method may include steps S201-S207. in:

S201. The smart glasses detect that the user needs to wake up other electronic devices.

When the smart glasses are in the wearing state, the smart glasses can detect whether the user needs to wake up other electronic devices (such as mobile phones, speakers, TVs, etc.). Wherein, the smart glasses may include the user behavior recognition module 1101 of the foregoing embodiments. The smart glasses can detect whether the user needs to wake up other electronic devices through the user behavior recognition module 1101 . For a specific implementation method, reference may be made to the foregoing embodiments. I won't go into details here.

S202. The smart glasses collect an image, and determine the type, recognition accuracy, and viewing angle deviation of the electronic device included in the image.

When it detects that the user needs to wake up other electronic devices, the smart glasses can capture images. Wherein, the smart glasses may include the image acquisition module 1102 and the image recognition module 1103 of the foregoing embodiments. The smart glasses can collect images through the image collection module 1102 . The image is the image within the user's field of vision. The smart glasses can use the image recognition module 1103 to determine the type, recognition accuracy and viewing angle deviation of the electronic device included in the image. For a specific implementation method, reference may be made to the foregoing embodiments. I won't go into details here.

S203. The smart glasses can send the type of the electronic device, the recognition accuracy, and the deviation of the viewing angle to the mobile phone.

S204. The mobile phone may perform prioritization on the electronic devices included in the image. The priority of the electronic device may be determined according to one or more of the following: type of electronic device, recognition accuracy, and viewing angle deviation.

The mobile phone may include the device priority determining module 1104 of the foregoing embodiments. The mobile phone may prioritize the electronic devices contained in the image through the device priority determining module 1104, and obtain a priority ranking result. The result of this prioritization can be the priority list of the foregoing embodiment.

S205. The mobile phone obtains the local device list, and determines the electronic device with the highest priority among the prioritized results and existing in the local device list as the target wake-up device.

The mobile phone may include the device wake-up module 1105 of the foregoing embodiments. When receiving the above priority sorting result, the mobile phone can determine the target wake-up device through the device wake-up module 1105, and execute the following step S206.

S206. The mobile phone sends a wake-up instruction to the target wake-up device.

In some embodiments, the cell phone is the target wake-up device. Then, when it is determined that the target wake-up device is itself, the mobile phone can enter the wake-up state.

In some embodiments, the target wake-up device is an electronic device other than a mobile phone, and the mobile phone may directly send a wake-up instruction to the target wake-up device. Optionally, both the mobile phone and the target wake-up device are connected to the router. The mobile phone can send a wake-up command to the router. The router can send a wake-up instruction to the target wake-up device.

S207. After receiving the wake-up, the target wake-up device enters the wake-up state, recognizes the voice command and executes an operation corresponding to the voice command.

Not limited to the above-mentioned mobile phones, the smart glasses can also send the results of prioritization of electronic devices to other electronic devices (such as routers) connected to themselves, and the electronic device determines the target wake-up device and sends a wake-up instruction to the target wake-up device.

In some embodiments, after the smart glasses determine the type, recognition accuracy, and viewing angle deviation of the electronic devices contained in the image, they can also prioritize the electronic devices contained in the image, determine the target to wake up the device, and wake up the device to the target. The device sends a wake-up command. That is to say, the above step S204, the above step S205 and the above step S206 can all be completed by smart glasses.

In some embodiments, after the smart glasses collect the images, they can send the collected images to the mobile phone. Cell phones can identify electronic devices contained in images. That is, the identification of the electronic devices contained in the image in the above step S202 may be performed by the mobile phone. This can reduce the requirements on the computing power and storage capacity of the smart glasses, and save the power consumption of the smart glasses.

As can be seen from the method shown in FIG. 12 , the user can use the smart glasses to wake up the electronic device he wants to wake up. The method can effectively reduce the situation of false wake-up, and bring a better user experience for the user to use the voice interaction function of the electronic device.

In some embodiments, not limited to the above-mentioned smart glasses, the user can also use other types of image acquisition devices to assist in realizing device wake-up. Exemplarily, the image acquisition device may be a surveillance camera or the like.

The above image acquisition device can detect the first user input, and when the first user input is detected, acquire the first image. By detecting the above-mentioned first user input, the image acquisition device can determine whether the user needs to wake up the device. When it is determined that the user needs to wake up the device, the image acquisition device may perform image acquisition to obtain the above-mentioned first image. It can be understood that, in the case that the user needs to wake up the device, it is more likely that the above-mentioned first image contains the electronic device that the user wants to wake up.

The above-mentioned image acquisition apparatus may select a target electronic device included in the first image from a plurality of electronic devices. Wherein, the image acquisition device may first identify the electronic equipment included in the first image, and obtain information about the electronic equipment included in the first image. The above information of the electronic device may include but not limited to type, recognition accuracy and viewing angle deviation. The image acquisition device may sort the electronic devices included in the first image according to the above electronic device information to obtain the priority of the electronic devices included in the first image. Further, the image acquisition device may determine whether the electronic device included in the first image exists in the device wake-up system.

The electronic devices in the above-mentioned device wake-up system may exist in the local device list. The local device list may be stored in one or more electronic devices in the device wake-up system. Optionally, the local device list may also be stored in a cloud server. All electronic devices in the local device list can obtain the local device list and update the local device list. An electronic device can be added to or deleted from the local device list by electronic devices already present in the local device list. Exemplarily, an electronic device establishes a communication connection with another electronic device in the local device list, and completes the trusted identity authentication indicated by the other electronic device. The other electronic device may update the local device list, adding the one electronic device to the local device list. That is, this electronic device can be added to the above-mentioned device to wake up the system. After the above local device list is updated, all electronic devices in the local device list can obtain the updated local device list. For the communication connection mode of the electronic device in the above-mentioned device wake-up system, reference may be made to the introduction of the communication system shown in FIG. 3 and FIG. 4 . I won't go into details here.

Then, the image acquisition device may acquire the local device list, and determine whether the electronic device included in the first image exists in the local device list. The image acquisition apparatus may determine the electronic device with the highest priority included in the local device list in the first image as the target electronic device, and instruct the target electronic device to enter a wake-up state.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still understand the foregoing The technical solutions described in each embodiment are modified, or some of the technical features are replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the various embodiments of the application.

Claims

A device wake-up system, characterized in that the device wake-up system includes an image acquisition device and a plurality of electronic devices, wherein,

The image acquisition device is configured to detect a first user input, and when the first user input is detected, acquire a first image;

The image acquisition device is further configured to select a target electronic device contained in the first image from the plurality of electronic devices, and send a wake-up instruction to the target electronic device; the wake-up instruction is used to trigger the The target electronic device enters a wake-up state;

The target electronic device is configured to enter the wake-up state in response to the received wake-up instruction.
The device wake-up system according to claim 1, wherein the first user input is voice input including a wake-up word; or, the first user input acts on the first position of the image acquisition device user actions.
The device wake-up system according to claim 1 or 2, wherein the image acquisition device is smart glasses;

The multiple electronic devices are also used to monitor wake-up words;

The multiple electronic devices are further configured to detect whether the image capture device exists in the device wake-up system when the wake-up word is heard, and whether the image capture device is in a wearing state;

The plurality of electronic devices are further configured to wait for receiving the wake-up instruction when it is determined that the image capture device exists in the device wake-up system and the image capture device is in the wearing state, and respond to the received The wakeup instruction enters the wakeup state.
The device wake-up system according to any one of claims 1-3, wherein the image acquisition device is specifically used for:

Determine at least one of the type of electronic equipment contained in the first image, recognition accuracy, and viewing angle deviation; the recognition accuracy is used to indicate the accuracy of the recognition result of the type of electronic equipment contained in the first image , the viewing angle deviation is used to indicate the distance between the position of the electronic device in the first image and the center of the first image;

Determining the electronic device with the highest priority among the plurality of electronic devices included in the first image as the target electronic device; the priority is based on the type, the recognition accuracy and the viewing angle Determined by one or more of the deviations; the priority order of the type of the electronic device in the wake-up order determined according to the type is positively correlated with the priority of the electronic device, and the priority of the electronic device The recognition accuracy rate is positively correlated with the priority of the electronic device, and the viewing angle deviation of the electronic device is negatively correlated with the priority of the electronic device.
The device wake-up system according to claim 1, 2 or 4, wherein the image acquisition device is smart glasses.
A device wake-up system, characterized in that the device wake-up system includes an image acquisition device and a processing device, wherein,

The image acquisition device is used to detect the first user input, and when the first user input is detected, acquire the first image;

The image acquisition device is further configured to send a first instruction to the processing device, the first instruction includes the first image, and the first instruction is used to instruct the processing device to select Find out the target electronic device included in the first image;

The processing device is configured to respond to the first instruction, select a target electronic device contained in the first image from the plurality of electronic devices, and send a wake-up instruction to the target electronic device, the wake-up instruction It is used to trigger the target electronic device to enter the wake-up state.
The device wake-up system according to claim 6, wherein the first user input is voice input including a wake-up word; or, the first user input acts on the first position of the image acquisition device user actions.
The device wake-up system according to claim 6 or 7, wherein the device wake-up system further comprises the plurality of electronic devices, wherein,

The multiple electronic devices are configured to enter the wake-up state in response to the wake-up instruction.
The device wake-up system according to claim 8, wherein the image acquisition device is smart glasses, and the plurality of electronic devices are also used for:

Listen for the wake word;

Detecting whether the image capture device exists in the device wake-up system when the wake-up word is heard, and whether the image capture device is in a wearing state;

Waiting to receive the wake-up instruction when the image capture device exists in the device wake-up system and the image capture device is in a wearing state.
The device wake-up system according to any one of claims 6-9, wherein the processing device is specifically used for:

Determine at least one of the type of electronic equipment contained in the first image, recognition accuracy, and viewing angle deviation; the recognition accuracy is used to indicate the accuracy of the recognition result of the type of electronic equipment contained in the first image , the viewing angle deviation is used to indicate the distance between the position of the electronic device in the first image and the center of the first image;

Determining the electronic device with the highest priority among the plurality of electronic devices included in the first image as the target electronic device; the priority is based on the type, the recognition accuracy and the viewing angle Determined by one or more of the deviations; the priority order of the type of the electronic device in the wake-up order determined according to the type is positively correlated with the priority of the electronic device, and the priority of the electronic device The recognition accuracy rate is positively correlated with the priority of the electronic device, and the viewing angle deviation of the electronic device is negatively correlated with the priority of the electronic device.
The device wake-up system according to any one of claims 6-8 or 10, wherein the image acquisition device is smart glasses.
A device wake-up method, characterized in that the method comprises:

get the first image;

selecting a target electronic device included in the first image from a plurality of electronic devices;

Send a wake-up instruction to the target electronic device; the wake-up instruction is used to trigger the target electronic device to enter a wake-up state.
The method according to claim 12, characterized in that the method is executed by an image acquisition device;

The acquisition of the first image specifically includes:

When a first user input is detected, the first image is captured.
The method according to claim 13, wherein the detecting the first user input specifically comprises:

A wake word is detected; or,

A user operation acting on a first position of the image capture device is detected.
The method according to claim 12, wherein the method is performed by a processing device;

The acquisition of the first image specifically includes:

receiving a first instruction from an image acquisition device, where the first instruction includes the first image captured by the image acquisition device, and the first instruction is used to instruct the processing device to select from the plurality of electronic devices Display the target electronic device included in the first image.
The method according to any one of claims 13-15, wherein the image acquisition device is smart glasses.
The method according to any one of claims 12-16, wherein the selecting the target electronic device contained in the first image from a plurality of electronic devices specifically includes:

Determine at least one of the type of electronic equipment contained in the first image, recognition accuracy, and viewing angle deviation; the recognition accuracy is used to indicate the accuracy of the recognition result of the type of electronic equipment contained in the first image , the viewing angle deviation is used to indicate the distance between the position of the electronic device in the first image and the center of the first image;

Determining the electronic device with the highest priority among the plurality of electronic devices included in the first image as the target electronic device; the priority is based on the type, the recognition accuracy and the viewing angle determined by one or more of the deviations; the priority order of the type of the electronic device in the wake-up order determined by type is positively correlated with the priority of the electronic device, and the priority of the electronic device The recognition accuracy rate is positively correlated with the priority of the electronic device, and the viewing angle deviation of the electronic device is negatively correlated with the priority of the electronic device.
A method for waking up a device, characterized in that the method includes:

When the first user input is detected, the image acquisition device acquires the first image;

The image acquisition device sends a first instruction to a processing device, the first instruction includes the first image, and the first instruction is used to instruct the processing device to select the first image from a plurality of electronic devices A target electronic device is included, and the target electronic device is an object to which the processing device sends a wake-up instruction, and the wake-up instruction is used to trigger the target electronic device to enter a wake-up state.
The method according to claim 18, wherein the image acquisition device is smart glasses.
The method according to claim 18 or 19, wherein the detecting the first user input specifically comprises:

A wake word is detected; or,

A user operation acting on a first position of the image capture device is detected.
A device wake-up method, characterized in that the method comprises:

The first electronic device monitors the wake-up word;

In response to the wake-up word, the first electronic device detects whether there are smart glasses in the device wake-up system, and whether the smart glasses are in a wearing state;

If the smart glasses exist in the device wake-up system, and the smart glasses are in the wearing state, the first electronic device waits to receive a wake-up instruction, and the wake-up instruction is used to trigger the first electronic device to enter the wake-up state;

The first electronic device enters the wake-up state upon receiving the wake-up instruction.
An electronic device, characterized in that the electronic device includes a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call the computer program, so that the electronic device executes claim 12 - the method of any one of 17 or 18-20 or 21.
A computer-readable storage medium, comprising instructions, characterized in that, when the instructions are run on an electronic device, the electronic device executes the method described in any one of claims 12-17 or 18-20 or 21 .