Device wakeup method and system, electronic device and storage medium

Abstract

The embodiment of the invention relates to the field of voice control, and discloses a device wake-up method and system, an electronic device and a storage medium, and the method comprises the steps: obtaining decibel values corresponding to wake-up voices of a target user collected by a plurality of voice control devices in a target space; obtaining a distance value from each voice control device to the target user obtained based on the positioning data of the plurality of sensor devices to the target user in the target space; and based on the decibel values corresponding to the voice control devices and in combination with the distance values from the voice control devices to the target user, determining a to-be-awakened target voice control device in the plurality of voice control devices. According to the device awakening method disclosed by the invention, the quality and distance factors of the voice signal are comprehensively considered, so that the problem that the unique device closest to the sound source cannot be accurately awakened according to the size of the received audio is solved, a more accurate, efficient and intelligent device awakening strategy is realized, and better interaction experience is provided for a user.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of voice control technology, and in particular to a device wake-up method, system, electronic device and storage medium. Background Art

[0002] With the increasing popularity of smart homes, multiple sound source receiving devices are usually set up in a room. When the user sends a wake-up word, it is easy for multiple devices to receive it at the same time, resulting in false wake-ups and repeated responses. To solve this problem, the sound source receiving device adopts the "nearby wake-up" method, that is, wakes up the sound source receiving device closest to the user.

[0003] However, "nearby wake-up" is usually determined by the volume of audio received by the microphone. This method cannot accurately wake up the only device closest to the sound source when a person deliberately wakes up loudly or lowers the voice, resulting in multiple devices being woken up at the same time in a partitioned space. Summary of the invention

[0004] The purpose of the present invention is to at least provide a device wake-up method, system, electronic device and storage medium, which can at least solve the problem that the audio size received by the microphone cannot accurately wake up the only device closest to the sound source, and at least can achieve the effect of more accurately waking up the only device closest to the sound source.

[0005] To solve the above technical problems, at least one embodiment of the present application provides a device wake-up method, including:

[0006] Obtaining decibel values ​​corresponding to the wake-up voices of the target user collected by multiple voice control devices in the target space;

[0007] Acquire a distance value from each of the voice control devices to the target user obtained based on positioning data of the target user by multiple sensor devices in the target space;

[0008] Based on the decibel value corresponding to each of the voice control devices and in combination with the distance value from each of the voice control devices to the target user, a target voice control device to be awakened among the multiple voice control devices is determined.

[0009] At least one embodiment of the present application further provides a device wake-up system, including:

[0010] A plurality of sensor devices are used to locate a target user in a target space;

[0011] A plurality of voice control devices, used to collect the audio signal of the wake-up voice of the target user;

[0012] The execution host is used to obtain decibel values ​​corresponding to audio signals collected by the multiple voice control devices; obtain distance values ​​between each voice control device and the target user based on the positioning data of the target user by the multiple sensor devices; and determine a target voice control device to be awakened among the multiple voice control devices based on the decibel values ​​corresponding to each voice control device and the distance values ​​between each voice control device and the target user.

[0013] At least one embodiment of the present application further provides a device waking up a device, including:

[0014] A decibel value acquisition module is used to obtain the decibel value corresponding to the wake-up voice of the target user collected by multiple voice control devices in the target space;

[0015] A distance value acquisition module, used to acquire the distance value from each of the voice control devices to the target user obtained based on the positioning data of the target user by multiple sensor devices in the target space;

[0016] The wake-up target determination module is used to determine the target voice control device to be woken up among the multiple voice control devices based on the decibel value corresponding to each of the voice control devices and the distance value from each of the voice control devices to the target user.

[0017] At least one embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned device wake-up method.

[0018] At least one embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein the computer program implements the above-mentioned device wake-up method when executed by a processor.

[0019] The device wake-up method, system, electronic device and storage medium provided by the embodiments of the present application can identify which voice control device receives the clearest and strongest voice signal by obtaining the decibel value of the target user's wake-up voice. Combined with the distance value from the device to the target user, it can further filter out those devices that receive voice signals but are far away from the user and may cause recognition errors due to environmental noise or signal attenuation. By comprehensively considering the quality of the voice signal and the distance factor, a more accurate, efficient and intelligent device wake-up strategy is achieved, providing users with a better interactive experience.

[0020] In some optional embodiments, determining a target voice control device to be awakened among the plurality of voice control devices based on the decibel value corresponding to each voice control device and in combination with a distance value from each voice control device to the target user includes:

[0021] Determining whether the decibel value corresponding to each of the voice control devices and the distance value from each of the voice control devices to the target user are in inverse proportion;

[0022] When it is an inverse proportional relationship, the voice control device with the largest decibel value and / or the voice control device with the smallest distance value to the target user is determined as the target voice control device.

[0023] In this embodiment, generally, as the distance increases, the attenuation of the sound signal causes the received decibel value to decrease. Therefore, when the decibel value and the distance value are inversely proportional, it indicates that the physical law of sound propagation is met. By confirming this inverse proportional relationship, some illogical data caused by abnormal factors (such as equipment failure, environmental noise, etc.) can be excluded, the accuracy of wake-up is improved, and the rationality of the wake-up decision is enhanced.

[0024] In some optional embodiments, after determining whether there is an inverse proportional relationship between the decibel value corresponding to each voice control device and the distance value from each voice control device to the target user, the method further includes:

[0025] When it is not an inverse proportional relationship, determining whether there is any home appliance in the target space that has been manually operated within the current preset time period;

[0026] When it is determined that a home appliance has been manually operated, obtaining distance information from the voice control device to the home appliance that has been manually operated;

[0027] The target voice control device is determined according to the distance information from each of the voice control devices to the manually operated home appliance.

[0028] In this embodiment, when the relationship between the decibel value and the distance value is abnormal, by introducing the manual operation information of the home appliance, additional decision-making basis can be provided, making the wake-up decision more flexible and accurate, and helping to avoid false wake-up or missed wake-up problems caused by interference factors such as equipment failure and environmental noise.

[0029] In some optional embodiments, determining the target voice control device according to the distance information from each of the voice control devices to the manually operated home appliance includes:

[0030] Determining whether the manually operated home appliance is the voice-controlled appliance;

[0031] When the manually operated home appliance is the voice control device, determine whether the voice content of the wake-up voice is associated with the working status of the manually operated home appliance; when associated, determine that the manually operated home appliance is the target voice control device; when not associated, determine that the voice control device that is the second closest to the manually operated home appliance is the target voice control device.

[0032] In this embodiment, by comprehensively considering the user's operating behavior, voice content, and distance information between devices, the system can more intelligently judge the user's intentions and needs, and thus make a more appropriate response, which helps to improve the system's intelligence level and adaptability, enabling it to better serve users.

[0033] In some optional embodiments, after determining whether the manually operated home appliance is the voice control appliance, the method further includes:

[0034] When the manually operated home appliance is not the voice control device, the voice control device that is closest to the manually operated home appliance is determined as the target voice control device.

[0035] In this embodiment, the user may indicate his current location or needs by operating a non-voice control device. Selecting the voice control device closest to the operated device for wake-up can maintain the continuity of user interaction.

[0036] In some optional embodiments, after determining whether the decibel value corresponding to each voice control device is in inverse proportion to the distance value from each voice control device to the target user, the method further comprises:

[0037] When the relationship is not inversely proportional, determining whether the temperature detection value of at least one temperature sensor preset in the target space reaches a preset temperature value corresponding to when a human body is within a preset distance;

[0038] When the temperature detection value reaches the preset temperature value, for all first temperature sensors corresponding to the temperature detection values ​​that reach the preset temperature value, the voice control device closest to the first temperature sensor with the highest temperature detection value is determined as the target voice control device.

[0039] In this embodiment, by introducing the data of the temperature sensor, the system can comprehensively consider multiple factors such as sound signal strength, distance and temperature, making the wake-up decision more diverse and comprehensive. When the user approaches a certain area, the temperature of the area usually rises. By detecting the data of the temperature sensor, the system can intelligently determine the user's location and select the voice control device closest to the user for wake-up.

[0040] In some optional embodiments, the positioning data is obtained by one of the following methods:

[0041] When the number of the sensor devices is two, the positioning data is obtained based on the law of cosines according to the distance between the two sensor devices and the distance value between the sensor devices and the target user; and

[0042] When the number of the sensor devices is three or more, based on a mathematical model of trilateration, the model is solved according to the coordinate values ​​of any three of the sensor devices and the distance value measured by each of the sensor devices to the target user to obtain the positioning data.

[0043] In this embodiment, a suitable positioning algorithm can be flexibly selected according to different numbers of sensor devices, so that stable positioning results can be obtained under different environmental conditions and configurations. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] One or more embodiments are exemplarily described by the pictures in the corresponding drawings, and these exemplary descriptions do not constitute limitations on the embodiments.

[0045] Figure 1 This is the process of a device wake-up method provided by an embodiment of the present application Figure 1 ;

[0046] Figure 2 is a structural diagram of a device wake-up system provided by another embodiment of the present application;

[0047] Figure 3 It is a structural diagram of a device wake-up apparatus provided in another embodiment of the present application. DETAILED DESCRIPTION

[0048] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the present application, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can also be implemented. The division of the following embodiments is for the convenience of description, and the specific implementation of the present application should not be construed as any limitation, and the various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0049] With the rapid development of smart home technology, more and more families are beginning to enjoy the convenience and comfort brought by intelligence. In smart home systems, sound source receiving devices play a vital role. They can capture the user's voice commands and trigger the corresponding smart home functions. However, when multiple sound source receiving devices or voice control devices are set up in a room, problems also arise: when the user issues a wake-up word, these devices may receive the command at the same time, resulting in frequent false wake-ups and repeated responses.

[0050] To solve this problem, the smart home system introduced the "nearby wake-up" strategy. The core idea of ​​this strategy is to wake up the sound source receiving device closest to the user to ensure the accurate execution of the command and avoid unnecessary interference. In actual operation, the system usually determines the distance between the user and the sound source receiving device based on the audio volume received by the microphone. However, the limitations of this method are also very obvious.

[0051] When a user deliberately wakes up a device loudly, the device may be woken up even if they are not closest to it due to the strong audio signal it receives. Similarly, if a user speaks in a low voice, the device may not be woken up due to the weak audio signal it receives even if they are very close to it. Both of these situations may cause the "nearby wake-up" strategy to fail, leading to the embarrassing situation of multiple devices being woken up at the same time.

[0052] In addition, the smart home environment in a partitioned space also brings additional challenges to the "nearby wake-up" strategy. In a partitioned space, the sound propagation between different areas may be hindered by obstacles such as walls and furniture, resulting in attenuation and deformation of the sound signal. This further increases the difficulty for the system to accurately determine the distance between the user and the sound source receiving device.

[0053] In order to solve the above-mentioned technical problem that the audio volume received by the microphone cannot accurately wake up the only device closest to the sound source, the present invention proposes a device wake-up method. The implementation details of the device wake-up method of this embodiment are specifically described below. The following content is only the implementation details provided for easy understanding and is not necessary for implementing this solution.

[0054] Embodiment 1:

[0055] The device wake-up method of this embodiment can be applied to electronic devices with communication, computing and data storage capabilities. The specific process can be as follows: Figure 1 As shown, including:

[0056] Step 110, obtaining decibel values ​​corresponding to the wake-up voices of the target user collected by multiple voice control devices in the target space;

[0057] In this embodiment, the target space can be an indoor environment, such as a home environment or an office environment. A plurality of voice control devices are arranged in the target space, and each voice control device can control each smart device in an area, or each voice control device is responsible for receiving and processing voice information in an area. When a user wants to control a smart device by voice, a wake-up voice is first issued to wake up any voice control device in the target space. When the voice control device is awakened, the wake-up voice is parsed to determine the smart device to be controlled, and the corresponding control instruction is sent to the smart device, thereby completing the corresponding control process.

[0058] Since there are multiple voice control devices in the target space, it is necessary to ensure that the wake-up voice collected by each device can be accurately synchronized and summarized. An execution host is set up in the target space. The function of the execution host is similar to that of a central control unit to coordinate data transmission and synchronization between various devices. When the wake-up voices collected by all devices are summarized in the execution host, the execution host processes the audio signals of the wake-up voices collected by each voice control device and analyzes them to obtain the decibel value of the wake-up voices collected by each voice control device.

[0059] For example, three voice control devices are placed in a living room: device A, device B, and device C. When the target user issues the wake-up word "Hello, Xiaoge", the three devices will capture the sound signal and send the collected sound to the execution host. After that, the execution host calculates the decibel value corresponding to each sound signal. For example, the decibel value collected by device A is 75dB, device B is 70dB, and device C is 65dB. These decibel values ​​will be synchronized to the execution host for subsequent processing and judgment.

[0060] Step 120, obtaining distance values ​​from each of the voice control devices to the target user based on positioning data of the target user by multiple sensor devices in the target space;

[0061] In this embodiment, multiple sensor devices are deployed in the target space to obtain the positioning data of the target user. The sensor device can be an infrared sensor, an ultrasonic sensor, or other device capable of detecting the user's position. The deployment location and number of the sensor devices will depend on the size and shape of the target space and the actual needs of the user, and are not specifically limited here.

[0062] The positioning data of the target user by the sensor device may include the user's real-time location, movement trajectory, or relative position to other objects. Different types of sensor devices have different ways of obtaining positioning data. For example, an infrared sensor determines its location by detecting infrared signals reflected from the user's body, while an ultrasonic sensor determines its location by detecting ultrasonic signals reflected from the user's body.

[0063] In actual applications, each sensor device sends positioning data to the execution host periodically. For example, the positioning data may be sent every 3 minutes or every 10 minutes. When the execution host receives the audio signal of the wake-up voice, it can synchronously integrate the positioning data of each sensor device and calculate the position of the target user in the target space based on the positioning data.

[0064] In some real-time examples, the positioning data is obtained by one of the following methods:

[0065] When the number of the sensor devices is two, the positioning data is obtained based on the law of cosines according to the distance between the two sensor devices and the distance value between the sensor devices and the target user; and

[0066] When the number of the sensor devices is three or more, based on a mathematical model of trilateration, the model is solved according to the coordinate values ​​of any three of the sensor devices and the distance value measured by each of the sensor devices to the target user to obtain the positioning data.

[0067] In this embodiment, a suitable positioning algorithm can be flexibly selected according to different numbers of sensor devices, so that stable positioning results can be obtained under different environmental conditions and configurations.

[0068] In one embodiment, there are two sensor devices A and B in the target space. The distance value of the target user measured by sensor A is dA, and the distance value of the target user measured by sensor B is dB. The distance between the two sensors is D. The angle between the straight-line distances from the two sensors to the target user can be calculated by the cosine theorem:

[0069]

[0070] Afterwards, the location of the target user can be determined by combining the distance D and the angle information.

[0071] In one embodiment, there are three or more sensors in the target space, and trilateration can be used to more accurately determine the position. For example, there are three sensor devices A (x1, y1), B (x2, y2), and C (x3, y3) with known positions, and the distances from the three points to the target point P (x, y) (where the target user is located) are d1, d2, and d3 respectively. The coordinates (x, y) of the target point P are solved according to the following mathematical model:

[0072]

[0073] After calculating the location of the target user, it is necessary to calculate the distance between each voice control device and the target user. This process can be achieved through methods such as geometric calculation or triangulation. For example, if the current location of the target user and the coordinates of each voice control device are known, the Euclidean distance formula can be used to calculate the distance between the target user and each voice control device.

[0074] Step 130: Determine a target voice control device to be awakened from the plurality of voice control devices based on the decibel value corresponding to each of the voice control devices and in combination with a distance value from each of the voice control devices to the target user.

[0075] In this embodiment, the "nearby wake-up" strategy is formulated based on two factors: decibel value and distance value, to ensure that the device finally selected is the device closest to the user and receives the highest sound intensity.

[0076] To achieve this goal, in some optional embodiments, a weighted average method is used to calculate the score of each voice control device being awakened. Specifically, a weight can be assigned to the decibel value of each voice control device, and the weight can be the inverse of the distance value from the voice control device to the target user (or a negative exponential function, etc.), to indicate that the closer the distance is, the higher the priority should be in the wake-up decision. Then, the decibel value of each device is multiplied by the corresponding weight, and the sum is obtained to obtain the total score of each device. Finally, the device with the highest total score is selected as the target voice control device to be awakened. After determining the target voice control device to be awakened, a wake-up instruction is sent to it.

[0077] In some embodiments, some boundary conditions may be considered when developing a wake-up strategy. For example, if the decibel value of a voice-controlled device is very high but it is far away from the user (perhaps due to environmental noise or other interference factors), a threshold may be set to limit its score; similarly, if the distance between a voice-controlled device and the target user is very small but the decibel value is very low (perhaps due to a problem with the device itself or the user's voice is too soft), it may also need special treatment.

[0078] For example, let's continue with the example of three voice-controlled devices in the living room. The decibel value and distance value to the target user of each voice-controlled device have been calculated, and it is necessary to determine which device should be awakened based on these data.

[0079] The decibel value of device A is 75dB and the distance value is 2 meters;

[0080] The decibel value of device B is 70dB and the distance value is 3 meters;

[0081] Device C has a decibel value of 65dB and a distance value of 4 meters.

[0082] Using the inverse of the distance value as a weight to calculate the score for each device, we get the following results:

[0083] The score of device A is: 75dB*(1 / 2 meter)=37.5;

[0084] The score of device B is: 70dB*(1 / 3 meter)≈23.33;

[0085] The score of device C is: 65dB*(1 / 4 meter)=16.25.

[0086] Since device A has the highest score, device A is selected as the target voice control device to be awakened, and a wake-up instruction is sent to it.

[0087] In summary, in this embodiment, by obtaining the decibel value of the target user's wake-up voice, it is possible to identify which voice control device receives the clearest and strongest voice signal. Combined with the distance value from the device to the target user, it is possible to further filter out those devices that receive voice signals but are far away from the user and may cause recognition errors due to environmental noise or signal attenuation. By comprehensively considering the quality of the voice signal and the distance factor, a more accurate, efficient and intelligent device wake-up strategy is implemented, providing users with a better interactive experience.

[0088] In some embodiments, the target voice control device to be awakened among the multiple voice control devices is determined based on the decibel values ​​corresponding to each of the voice control devices and the distance values ​​from each of the voice control devices to the target user, including: judging whether the decibel values ​​corresponding to each of the voice control devices and the distance values ​​from each of the voice control devices to the target user are in an inverse proportional relationship; when they are in an inverse proportional relationship, determining the voice control device with the largest decibel value and / or the voice control device with the smallest distance value to the target user as the target voice control device.

[0089] In this embodiment, generally, as the distance increases, the attenuation of the sound signal causes the received decibel value to decrease. Therefore, when the decibel value and the distance value are inversely proportional, it indicates that the physical law of sound propagation is met. By confirming this inverse proportional relationship, some illogical data caused by abnormal factors (such as equipment failure, environmental noise, etc.) can be excluded, the accuracy of wake-up is improved, and the rationality of the wake-up decision is enhanced.

[0090] For example, there are three voice-controlled devices:

[0091] Voice control device A: distance value is 3 meters, decibel value is 60dB;

[0092] Voice control device B: distance value is 5 meters, decibel value is 70dB;

[0093] Voice control device C: distance value is 7 meters, decibel value is 40dB;

[0094] Voice control device B has the highest decibel value, but it is not the device closest to the target user. Therefore, the decibel values ​​corresponding to the three voice control devices are not inversely proportional to the distance values ​​from each voice control device to the target user. Based on this data, it is difficult to accurately determine which voice control device is closest to the target user.

[0095] For another example, there are three voice-controlled devices:

[0096] Voice control device A: distance value is 3 meters, decibel value is 80dB;

[0097] Voice control device B: distance value is 5 meters, decibel value is 70dB;

[0098] Voice control device C: distance value is 7 meters, decibel value is 40dB;

[0099] It can be seen that in this case, the decibel values ​​corresponding to the three voice control devices are inversely proportional to the distance values ​​from each voice control device to the target user. Therefore, it can be determined without a doubt that voice control device A is the target voice control device to be awakened.

[0100] In some optional embodiments, after determining whether there is an inverse proportional relationship between the decibel value corresponding to each of the voice control devices and the distance value from each of the voice control devices to the target user, the method further includes: when there is no inverse proportional relationship, determining whether there is any household appliance in the target space that has been manually operated within the current preset time period; when it is determined that a household appliance has been manually operated, obtaining the distance information from the voice control device to the household appliance that has been manually operated; and determining the target voice control device based on the distance information from each of the voice control devices to the household appliance that has been manually operated.

[0101] In this embodiment, when the relationship between the decibel value and the distance value is abnormal, by introducing the manual operation information of the home appliance, additional decision-making basis can be provided, making the wake-up decision more flexible and accurate, and helping to avoid false wake-up or missed wake-up problems caused by interference factors such as equipment failure and environmental noise.

[0102] Specifically, by querying whether any home appliances have been manually operated within the current preset time period (such as the past 5 minutes, 10 minutes, etc.). This can be achieved by detecting the state changes of home appliances (such as light switches, TV channel switching, air conditioning temperature adjustment, curtain adjustment, etc.). If it is detected that any home appliances have been manually operated, the type and location information of these devices are recorded. The execution host obtains the type and location information of these devices, and determines the location of the home appliance as the current location of the target user based on the information of the home appliance most recently operated by the target user, which is used as evidence to further determine the location of the target user.

[0103] For example, voice control device A: distance value is 3 meters, decibel value is 60dB; voice control device B: distance value is 5 meters, decibel value is 70dB; at this time, it is impossible to determine which voice control device is closest to the target user, so the most likely location of the target user is determined based on the manual operation records of the home appliances. For example, after the target user issues a wake-up voice, it is detected that the projector in the living room is operated, so it is considered that the location of the target user at this time is the location of the projector. Then, the execution host calculates the distance value from the projector to each voice control device based on the location of the projector, and further determines the target voice control device based on the distance value.

[0104] In some optional embodiments, determining the target voice control device based on the distance information from each of the voice control devices to the manually operated home appliance includes: determining whether the manually operated home appliance is the voice control device; when the manually operated home appliance is the voice control device, determining whether the voice content of the wake-up voice is associated with the working status of the manually operated home appliance; when associated, determining that the manually operated home appliance is the target voice control device; when not associated, determining that the voice control device that is the second closest to the manually operated home appliance is the target voice control device.

[0105] In this embodiment, by comprehensively considering the user's operation behavior, voice content, and distance information between devices, the system can more intelligently judge the user's intentions and needs, thereby making a more appropriate response, which helps to improve the system's intelligence level and adaptive ability, so that it can better serve users. The specific execution process is as follows:

[0106] 1) When it is detected that a device is manually operated, the system first determines whether the device is a voice-controlled device. If the device being operated is a voice-controlled device (for example, the user manually triggers a button of a voice-controlled device), the system proceeds to step 2).

[0107] 2) Associate voice content with device status: The execution host obtains the current working status of the manually operated voice control device. At the same time, the voice content of the wake-up voice issued by the target user is analyzed to determine whether it is associated with the working status of the voice control device that has been operated. For example, if the target user first manually adjusts the volume button of voice control device A, and then issues a voice command of "Xiaoge, play music", these two actions are associated, which means that the voice control device that the target user expects to wake up is voice control device A.

[0108] If the voice content is not associated with the working state of the operated voice control device, for example, the target user manually adjusts the working mode of voice control device A to power saving mode, and then issues a voice command of "Xiaoge, play music", these two actions are not associated, and it is necessary to find another voice control device as the wake-up target. In this embodiment, the voice control device that is the second closest to the operated voice control device is found and determined as the target voice control device.

[0109] In some possible embodiments, after determining whether the manually operated home appliance is the voice control device, it also includes: when the manually operated home appliance is not the voice control device, determining that the voice control device that is closest to the manually operated home appliance is the target voice control device.

[0110] In this embodiment, the user may indicate his current location or needs by operating a non-voice control device. Selecting the voice control device closest to the operated device for wake-up can maintain the continuity of user interaction.

[0111] For example, in one scenario, the target user adjusts the brightness of the projector in the living room. Voice control devices D and E are located in different corners of the living room. When the user issues a voice command, the execution host detects the following:

[0112] The decibel value received by voice control device D is 70dB, and the distance to the target user is 4 meters;

[0113] The decibel value received by voice control device E is 75dB, and the distance to the target user is 5 meters;

[0114] The distance between the projector (which can replace the target user in this case) and the voice control device D is 2 meters, and the distance between the projector and the voice control device E is 3 meters;

[0115] At this time, due to the comprehensive consideration of the distances between the projector and each voice control device, it is found that the distance between voice control device D and the target user is closer. Therefore, the probability that voice control device D is closer to the target user is greater than that of voice control device E, and voice control device D is determined to be the target to be awakened.

[0116] In some optional embodiments, after determining whether the decibel value corresponding to each of the voice control devices is inversely proportional to the distance value from each of the voice control devices to the target user, the method further includes: when it is not an inversely proportional relationship, determining whether the temperature detection value of at least one temperature sensor preset in the target space reaches a preset temperature value corresponding to a human body approaching a preset distance; when the temperature detection value reaches the preset temperature value, for all first temperature sensors corresponding to the temperature detection values ​​that reach the preset temperature value, determining the voice control device closest to the first temperature sensor with the highest temperature detection value as the target voice control device.

[0117] In this embodiment, by introducing the data of the temperature sensor, the system can comprehensively consider multiple factors such as sound signal strength, distance and temperature, making the wake-up decision more diverse and comprehensive. When the user approaches a certain area, the temperature of the area usually rises. By detecting the data of the temperature sensor, the system can intelligently determine the user's location and select the voice control device closest to the user for wake-up.

[0118] The logic of introducing the temperature sensor as an auxiliary judgment is similar to the logic of introducing the device operation data in the above embodiment, and will not be repeated here to avoid repetition.

[0119] In some optional embodiments, each analysis data (positioning data from sensor devices, decibel values ​​from voice control devices, manual operation data from home appliances, and temperature monitoring values ​​from temperature sensors) acquired by the execution host is set with a corresponding priority, and each analysis data is comprehensively processed based on the priority to more accurately determine the wake-up target closest to the sound source. For example, the priority of the positioning data from the sensor device is 1, the priority of the decibel value from each voice control device is 2, the priority of the manual operation data from the home appliance is 3, and the priority of the temperature monitoring value from the temperature sensor is 4. First, determine whether the target voice control device to be awakened can be screened out based on the data of priority 1 and 2. If not, further support the judgment based on the manual operation data with a priority of 3. If the manual operation data cannot be obtained or the data cannot be used, the temperature monitoring value of the temperature sensor is used to further support the judgment. The setting of priorities depends on actual needs and is not limited here.

[0120] Embodiment 2:

[0121] Based on the above embodiments, Figure 2 As shown, this embodiment provides a device wake-up system, including:

[0122] A plurality of sensor devices 210 are used to locate a target user in a target space;

[0123] A plurality of voice control devices 220 are used to collect the audio signal of the wake-up voice of the target user;

[0124] The execution host 230 is used to obtain decibel values ​​corresponding to audio signals collected by the multiple voice control devices; obtain distance values ​​between each of the voice control devices and the target user based on the positioning data of the target user by the multiple sensor devices; and determine a target voice control device to be awakened among the multiple voice control devices based on the decibel values ​​corresponding to each of the voice control devices and the distance values ​​between each of the voice control devices and the target user.

[0125] In some optional embodiments, the device wake-up system further includes:

[0126] A plurality of temperature sensors are used to locate the target user based on the acquired temperature value of the target user;

[0127] The execution host is also used to calculate the distance value between the target user and each voice control device based on the decibel value corresponding to each voice control device, combined with the distance value between each voice control device and the target user, combined with the positioning result of the temperature sensor, and determine the target voice control device to be awakened among the multiple voice control devices.

[0128] In some optional embodiments, the execution host can also execute the device wake-up method described in any of the above embodiments.

[0129] Embodiment three:

[0130] Another embodiment of the present application relates to a device waking up a device. The implementation details of the device waking up a device of this embodiment are described in detail below. The following content is only provided for the convenience of understanding the implementation details and is not necessary for implementing this solution. The schematic diagram of the device waking up a device of this embodiment can be as follows: Figure 3 As shown, it includes a decibel value acquisition module 310, a distance value acquisition module 320 and a wake-up target determination module 330.

[0131] The decibel value acquisition module 310 is used to acquire the decibel value corresponding to the wake-up speech of the target user collected by multiple voice control devices in the target space;

[0132] A distance value acquisition module 320 is used to acquire the distance value from each of the voice control devices to the target user obtained based on the positioning data of the target user by multiple sensor devices in the target space;

[0133] The wake-up target determination module 330 is used to determine the target voice control device to be woken up among the multiple voice control devices based on the decibel value corresponding to each of the voice control devices and the distance value from each of the voice control devices to the target user.

[0134] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0135] Embodiment 4:

[0136] Another embodiment of the present application relates to an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the following device wake-up method:

[0137] Obtaining decibel values ​​corresponding to the wake-up voices of the target user collected by multiple voice control devices in the target space;

[0138] Acquire a distance value from each of the voice control devices to the target user obtained based on positioning data of the target user by multiple sensor devices in the target space;

[0139] Based on the decibel value corresponding to each of the voice control devices and in combination with the distance value from each of the voice control devices to the target user, a target voice control device to be awakened among the multiple voice control devices is determined.

[0140] In some optional embodiments, the processor can also execute the following method:

[0141] Determining whether the decibel value corresponding to each of the voice control devices and the distance value from each of the voice control devices to the target user are in inverse proportion;

[0142] When it is an inverse proportional relationship, the voice control device with the largest decibel value and / or the voice control device with the smallest distance value to the target user is determined as the target voice control device.

[0143] In some optional embodiments, the processor can also execute the following method:

[0144] When it is not an inverse proportional relationship, determining whether there is any home appliance in the target space that has been manually operated within the current preset time period;

[0145] When it is determined that a home appliance has been manually operated, obtaining distance information from the voice control device to the home appliance that has been manually operated;

[0146] The target voice control device is determined according to the distance information from each of the voice control devices to the manually operated home appliance.

[0147] In some optional embodiments, the processor can also execute the following method:

[0148] Determining whether the manually operated home appliance is the voice-controlled appliance;

[0149] When the manually operated home appliance is the voice control device, determine whether the voice content of the wake-up voice is associated with the working status of the manually operated home appliance; when associated, determine that the manually operated home appliance is the target voice control device; when not associated, determine that the voice control device that is the second closest to the manually operated home appliance is the target voice control device.

[0150] In some optional embodiments, the processor can also execute the following method:

[0151] When the manually operated home appliance is not the voice control device, the voice control device that is closest to the manually operated home appliance is determined as the target voice control device.

[0152] In some optional embodiments, the processor can also execute the following method:

[0153] When the relationship is not inversely proportional, determining whether the temperature detection value of at least one temperature sensor preset in the target space reaches a preset temperature value corresponding to when a human body is within a preset distance;

[0154] When the temperature detection value reaches the preset temperature value, for all first temperature sensors corresponding to the temperature detection values ​​that reach the preset temperature value, the voice control device closest to the first temperature sensor with the highest temperature detection value is determined as the target voice control device.

[0155] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0156] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0157] Embodiment five:

[0158] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0159] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as: ROM), random access memory (Random Access Memory, referred to as: RAM), disk or optical disk and other media that can store program codes.

[0160] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. A device wake-up method, characterized in that: include: Obtaining decibel values ​​corresponding to the wake-up voices of the target user collected by multiple voice control devices in the target space; Acquire a distance value from each of the voice control devices to the target user obtained based on positioning data of the target user by multiple sensor devices in the target space; Based on the decibel value corresponding to each of the voice control devices and in combination with the distance value from each of the voice control devices to the target user, a target voice control device to be awakened among the multiple voice control devices is determined.

2. The device wake-up method according to claim 1, characterized in that: The step of determining a target voice control device to be awakened among the plurality of voice control devices based on the decibel value corresponding to each voice control device and in combination with a distance value from each voice control device to the target user comprises: Determining whether the decibel value corresponding to each of the voice control devices and the distance value from each of the voice control devices to the target user are in inverse proportion; When it is an inverse proportional relationship, the voice control device with the largest decibel value and / or the voice control device with the smallest distance value to the target user is determined as the target voice control device.

3. The device wake-up method according to claim 2, characterized in that: After determining whether there is an inverse proportional relationship between the decibel value corresponding to each voice control device and the distance value from each voice control device to the target user, the method further includes: When it is not an inverse proportional relationship, determining whether there is any home appliance in the target space that has been manually operated within the current preset time period; When it is determined that a home appliance has been manually operated, obtaining distance information from the voice control device to the home appliance that has been manually operated; The target voice control device is determined according to the distance information from each of the voice control devices to the manually operated home appliance.

4. The device wake-up method according to claim 3, characterized in that: The step of determining the target voice control device according to the distance information from each of the voice control devices to the manually operated home appliance includes: Determining whether the manually operated home appliance is the voice-controlled appliance; When the manually operated home appliance is the voice control device, determine whether the voice content of the wake-up voice is associated with the working status of the manually operated home appliance; when associated, determine that the manually operated home appliance is the target voice control device; when not associated, determine that the voice control device that is the second closest to the manually operated home appliance is the target voice control device.

5. The device wake-up method according to claim 4, characterized in that: After determining whether the manually operated home appliance is the voice control appliance, the method further includes: When the manually operated home appliance is not the voice control device, the voice control device that is closest to the manually operated home appliance is determined as the target voice control device.

6. The device wake-up method according to claim 2, characterized in that: After determining whether the decibel value corresponding to each voice control device is in an inverse proportional relationship with the distance value from each voice control device to the target user, the method further comprises: When the relationship is not inversely proportional, determining whether the temperature detection value of at least one temperature sensor preset in the target space reaches a preset temperature value corresponding to when a human body is within a preset distance; When the temperature detection value reaches the preset temperature value, for all first temperature sensors corresponding to the temperature detection values ​​that reach the preset temperature value, the voice control device closest to the first temperature sensor with the highest temperature detection value is determined as the target voice control device.

7. The device wake-up method according to any one of claims 1 to 6, characterized in that: The positioning data is obtained by one of the following methods: When the number of the sensor devices is two, the positioning data is obtained based on the law of cosines according to the distance between the two sensor devices and the distance value between the sensor devices and the target user; and When the number of the sensor devices is three or more, based on a mathematical model of trilateration, the model is solved according to the coordinate values ​​of any three of the sensor devices and the distance value measured by each of the sensor devices to the target user to obtain the positioning data.

8. A device wake-up system, characterized in that: include: A plurality of sensor devices are used to locate a target user in a target space; A plurality of voice control devices, used to collect the audio signal of the wake-up voice of the target user; The execution host is used to obtain decibel values ​​corresponding to audio signals collected by the multiple voice control devices; obtain distance values ​​between each voice control device and the target user based on the positioning data of the target user by the multiple sensor devices; and determine a target voice control device to be awakened among the multiple voice control devices based on the decibel values ​​corresponding to each voice control device and the distance values ​​between each voice control device and the target user.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the device wake-up method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the device wake-up method according to any one of claims 1 to 7 is implemented.

Images