Method and device for waking up nearby equipment in a smart home system and related equipment

Abstract

The application relates to Internet of Things technology and provides a device nearby wake-up method and device in a whole-house intelligent system and related equipment. The method comprises the following steps: determining a target voice signal-to-noise ratio of a wake-up voice corresponding to each device in the whole-house intelligent system; determining a target device according to the target voice signal-to-noise ratio; and sending a wake-up instruction to the target device to perform wake-up processing on the target device. The application can improve the accuracy of device nearby wake-up.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to a method, device, and related equipment for waking up devices in a smart home system. Background Technology

[0002] Currently, the method of selecting the nearest smart device from multiple smart devices after the voice output terminal or user outputs a wake-up voice command is quite common. The existing decision on the proximity of smart devices for wake-up mainly relies on the signal strength received by the device to be woken up, selecting the device with the strongest signal strength for wake-up processing.

[0003] In the process of developing this application, the applicant discovered the following problems with the existing technology: there are differences in the decoration location and decoration materials between different devices to be woken up, which causes the signal strength received by the device to be woken up to not correctly reflect the distance between the voice output terminal and the device to be woken up. As a result, the device that is woken up is not the expected device, and the accuracy of device wake-up is poor. Summary of the Invention

[0004] In view of the above, it is necessary to propose a method, device and related equipment for waking up devices in a smart home system, which can improve the accuracy of waking up devices in a nearby location.

[0005] The first aspect of this application provides a method for waking up devices in a smart home system based on proximity, the method comprising:

[0006] Determine the target speech signal-to-noise ratio for the wake-up voice of each device;

[0007] Determine the target device based on the target speech signal-to-noise ratio;

[0008] Send a wake-up command to the target device to wake it up.

[0009] Furthermore, in the device wake-up method for the whole-house smart system provided in the embodiments of this application, the step of determining the target speech signal-to-noise ratio for the wake-up voice corresponding to each device specifically includes:

[0010] Determine the initial speech signal-to-noise ratio for the wake-up voice corresponding to each device;

[0011] Determine the signal-to-noise ratio weight for each device;

[0012] The initial speech signal-to-noise ratio is adjusted according to the signal-to-noise ratio weight to obtain the target speech signal-to-noise ratio for each device.

[0013] Furthermore, in the device wake-up method for the whole-house smart system provided in the embodiments of this application, the step of determining the signal-to-noise ratio weight corresponding to each device specifically includes:

[0014] Determine the initial speech signal-to-noise ratio for the wake-up voice corresponding to each device;

[0015] The initial wake-up priority for each device is determined based on the initial voice signal-to-noise ratio.

[0016] When the initial wake-up priority does not meet the preset priority requirement, determine the initial voice signal-to-noise ratio of the device that does not meet the preset priority requirement;

[0017] Increase the signal-to-noise ratio weight of the initial speech signal-to-noise ratio until the device meets the preset priority requirements.

[0018] Furthermore, in the device wake-up method for the whole-house smart system provided in the embodiments of this application, the step of adding a predetermined initial voice signal-to-noise ratio weight until the device meets the preset priority requirement specifically includes:

[0019] Determine the first initial wake-up voice signal-to-noise ratio of the device with the highest initial wake-up priority;

[0020] Determine the second initial wake-up voice signal-to-noise ratio of the device corresponding to the preset priority requirements;

[0021] The signal-to-noise ratio difference between the second initial wake-up speech signal-to-noise ratio and the first initial wake-up speech signal-to-noise ratio is calculated as the signal-to-noise ratio weight.

[0022] Furthermore, in the device wake-up method for the whole-house smart system provided in the embodiments of this application, the step of adjusting the initial speech signal-to-noise ratio according to the signal-to-noise ratio weight to obtain the target speech signal-to-noise ratio for each device specifically includes:

[0023] Calculate the sum of the signal-to-noise ratio (SNR) of the weighted SNR and the initial speech SNR;

[0024] The signal-to-noise ratio (SNR) and its value are used as the target speech SNR for each device.

[0025] Furthermore, in the device wake-up method for the whole-house smart system provided in the embodiments of this application, the step of determining the target device based on the target voice signal-to-noise ratio specifically includes:

[0026] The target speech signal-to-noise ratios are sorted in descending order to obtain the sorting results;

[0027] The sorting results will be used as the priority order for each device to be woken up.

[0028] The wake-up priority of each device is determined according to the wake-up priority order.

[0029] The device with the highest priority to be woken up is identified as the target device.

[0030] Furthermore, in the device wake-up method for the whole-house smart system provided in the embodiments of this application, the step of determining the initial speech signal-to-noise ratio of the wake-up voice for each device specifically includes:

[0031] Determine the voice area audio and silence area audio corresponding to the wake-up voice for each device;

[0032] Spectral analysis was performed on the audio from the speech region and the audio from the silence region respectively to obtain the power spectrum of the speech region and the power spectrum of the silence region;

[0033] The power value corresponding to the power spectrum of the speech region is determined to be the speech signal power, and the power value corresponding to the power spectrum of the silence region is determined to be the noise signal power.

[0034] The ratio of speech signal power to noise signal power is calculated as the initial speech signal-to-noise ratio.

[0035] A second aspect of this application also provides a device for nearby wake-up in a whole-house smart system, the device comprising:

[0036] The signal-to-noise ratio (SNR) determination module is used to determine the target SNR of the wake-up voice for each device in the whole-house smart system.

[0037] The device determination module is used to determine the target device based on the target speech signal-to-noise ratio.

[0038] The wake-up processing module is used to send a wake-up command to the target device to perform wake-up processing on the target device.

[0039] A third aspect of this application also provides a computer device, which includes a processor. The processor is used to execute a computer program stored in a memory to implement the above-described method for waking up devices in a nearby smart home system.

[0040] The fourth aspect of this application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, a method for waking up nearby devices in the above-mentioned whole-house smart system is provided.

[0041] The device wake-up method, apparatus, computer device, and computer-readable storage medium in the whole-house smart system provided in this application embodiment determine the target speech signal-to-noise ratio corresponding to each device to be woken up, determine the target device based on the target speech signal-to-noise ratio, and perform wake-up processing on the target device. This can avoid the problem of inaccurate proximity caused by differences between devices and improve the accuracy of device wake-up. Attached Figure Description

[0042] Figure 1 This is a flowchart of a method for waking up devices in a smart home system provided in an embodiment of this application.

[0043] Figure 2 This is a flowchart illustrating the determination of the target speech signal-to-noise ratio according to an embodiment of this application.

[0044] Figure 3 This is a flowchart illustrating the determination of a target device according to an embodiment of this application.

[0045] Figure 4 This is a structural diagram of a device wake-up device in a whole-house smart system provided in an embodiment of this application.

[0046] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application.

[0047] The following detailed description, in conjunction with the accompanying drawings, will further illustrate this application. Detailed Implementation

[0048] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0049] Numerous specific details are set forth in the following description in order to provide a full understanding of this application. The described embodiments are only some, not all, of the embodiments of this application.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0051] Please see Figure 1 , Figure 1 This is a flowchart illustrating a device wake-up method in a whole-house smart system according to an embodiment of this application. The device wake-up method in the whole-house smart system provided in this embodiment is applied to a main device, which is communicatively connected to each device in the whole-house smart system. The main device can be a computer device, and correspondingly, the device wake-up device in the whole-house smart system can operate in various main devices such as computer devices. Figure 1 As shown, the method for waking up devices in a smart home system from nearby locations may include the following steps. The order of these steps in the flowchart can be changed depending on different needs, and some steps may be omitted:

[0052] S11, determine the target speech signal-to-noise ratio for the wake-up speech of each device.

[0053] In at least one embodiment of this application, the wake-up voice can be the voice output by the main device. For example, the main device includes several touch components, and the form of the touch components is not limited. The user can output a wake-up voice by clicking the touch component, and the wake-up voice can be pre-stored in a preset database. When the main device detects that a touch component has been triggered, it outputs the wake-up voice to each device in the whole-house smart system. The main device can output the wake-up voice at a certain wake-up location and simultaneously transmit the wake-up voice to each device in the whole-house smart system. The wake-up location can be set according to actual needs. The wake-up voice refers to the voice used to turn on the device to be woken up. For example, the wake-up voice can be "Please turn on device A" or "Please open," etc., and is not limited here. In other embodiments, the wake-up voice can also be the voice output by the user. The user can output the wake-up voice at a certain wake-up location, where the wake-up voice can be a fixed wake-up word, and the wake-up voice is simultaneously transmitted to each device in the whole-house smart system to turn on the device to be woken up, and is not limited here.

[0054] A whole-house smart system includes multiple devices, each carrying an audio acquisition component. In one embodiment, the audio acquisition component can be a microphone component, which captures the wake-up voice. Each device in the whole-house smart system can capture the same wake-up voice output at a specific wake-up location. The multiple devices in the device set can be of the same type or different types, without limitation. When the multiple devices are of the same type, for example, all devices are air conditioners. When the wake-up voice "Please turn on the air conditioner" is received, the nearest air conditioner is selected to execute the turn-on command. When the multiple devices are of different types, for example, the devices can be a television, a smart speaker, an air conditioner, a smart central control switch, etc. When the wake-up voice "Please turn on" is received, the nearest device is selected to execute the turn-on command.

[0055] In one embodiment, after receiving a wake-up voice, each device calculates the initial wake-up voice signal-to-noise ratio (SNR) and transmits it to the master device. In other embodiments, after receiving a wake-up voice, each device transmits the audio information required to calculate the initial wake-up voice SNR to the master device, which then calculates the initial wake-up voice SNR for each device's corresponding wake-up voice; this is not limited in this respect. The initial wake-up voice SNR can refer to the ratio of voice signal power to noise signal power, or it can refer to the audio direct-to-noise ratio (ANR), where the ANR refers to the energy ratio of direct audio to reverberant audio in the wake-up voice. The initial wake-up voice SNR can also be the SNR obtained based on the angle of the audio signal; this is not limited in this respect. In one embodiment, taking the initial wake-up voice SNR as the ratio of voice signal power to noise signal power as an example, optionally, the steps for calculating the initial wake-up voice SNR specifically include:

[0056] Determine the audio in the speech area and the audio in the silence area corresponding to the wake-up voice.

[0057] Spectral analysis was performed on the audio from the speech region and the silence region respectively to obtain the power spectrum of the speech region and the power spectrum of the silence region.

[0058] The power value corresponding to the power spectrum of the speech region is determined to be the power of the speech signal, and the power value corresponding to the power spectrum of the silence region is determined to be the power of the noise signal.

[0059] The ratio of speech signal power to noise signal power is calculated as the initial wake-up speech signal-to-noise ratio.

[0060] The wake-up voice sequence includes both voice zone audio and silence zone audio. The voice zone audio contains the wake-up voice and reflects the energy level received by the device. The silence zone audio does not contain the wake-up voice and reflects the ambient noise around the device. After obtaining the voice zone and silence zone audio, spectral analysis is performed on both to obtain the voice zone power spectrum and the silence zone power spectrum. The power value corresponding to the voice zone power spectrum is taken as the voice signal power, and the power value corresponding to the silence zone power spectrum is taken as the noise signal power. Finally, the ratio of the voice signal power to the noise signal power is calculated as the initial wake-up voice signal-to-noise ratio.

[0061] In at least one embodiment of this application, the master device establishes a heartbeat connection with each device in the whole-house smart system. Each device sends a heartbeat packet to the master device at a preset time interval. When the master device receives a heartbeat packet from each device within the preset time interval, it determines that the device is operating normally; when the master device does not receive a heartbeat packet from a device within the preset time interval, it determines that the device is operating abnormally. When a device is operating normally, if the master device does not receive the initial wake-up voice signal-to-noise ratio (SNR) or audio information sent by that device, it continues to wait for a preset time period until it receives the initial wake-up voice SNR or audio information sent by that device. When a device is operating abnormally, if the master device does not receive the initial wake-up voice SNR or audio information sent by that device, it does not need to continue waiting for the device to send the initial wake-up voice SNR or audio information. The preset time interval and preset time period are pre-set and are not limited here. By establishing a heartbeat connection between the master device and the devices, this embodiment of the application ensures that the master device receives the initial wake-up voice SNR or audio information sent by the normally operating device, avoiding the master device waiting for a long time for the abnormally operating device to send the initial wake-up voice SNR or audio information, thus improving the efficiency of nearby wake-up.

[0062] Because there may be differences between different devices, such as differences in decoration location or decoration materials, the initial wake-up voice signal-to-noise ratio calculated by the device cannot accurately reflect the distance between the device and the wake-up location (in one embodiment, the wake-up location is the location of the main device or user). Therefore, it is necessary to set a signal-to-noise ratio weight to adjust the initial wake-up voice signal-to-noise ratio to obtain the target wake-up voice signal-to-noise ratio, thereby eliminating the differences between different devices and improving the accuracy of device wake-up in the whole-house smart system.

[0063] Combination Figure 2 This application describes the process for determining the target speech signal-to-noise ratio (SNR) provided in its embodiments. Optionally, the steps for determining the target SNR of the wake-up speech for each device specifically include:

[0064] S110, determine the initial speech signal-to-noise ratio for the wake-up voice corresponding to each device.

[0065] S111, determine the signal-to-noise ratio weight for each device.

[0066] S112, adjust the initial speech signal-to-noise ratio according to the signal-to-noise ratio weight to obtain the target speech signal-to-noise ratio for each device.

[0067] Each device has a corresponding signal-to-noise ratio (SNR) weight. These weights can be the same or different for each device; there is no restriction on this. The target wake-up speech SNR reflects the distance between each device and the wake-up location. The target wake-up speech SNR for each device may be the same or different. When two devices have the same target wake-up speech SNR, it indicates that the two devices are at the same distance from the wake-up location. When any two devices have different target wake-up speech SNRs, it indicates that the two devices are at different distances from the wake-up location.

[0068] In one embodiment, the step of determining the signal-to-noise ratio weight corresponding to each device specifically includes:

[0069] S1110, determine the initial speech signal-to-noise ratio for the wake-up voice corresponding to each device.

[0070] The wake-up voice can be output at a preset wake-up location. This preset location can be a pre-defined area in the smart home system where the device's wake-up effect is poor. This poor wake-up effect can be determined through multiple trials, and the wake-up voice will be output at the preset location. There can be one or more preset wake-up locations. Because the wake-up effect is poor at the preset location, the initial wake-up priority of the device may not meet the preset priority requirements. Therefore, the signal-to-noise ratio of the initial wake-up voice needs to be adjusted to improve the wake-up effect at the preset location.

[0071] S1111, determine the initial wake-up priority for each device based on the initial voice signal-to-noise ratio.

[0072] S1112, when the initial wake-up priority does not meet the preset priority requirement, determine the initial voice signal-to-noise ratio of the device that does not meet the preset priority requirement.

[0073] S1113, Increase the signal-to-noise ratio weight of the determined initial speech signal-to-noise ratio until the device meets the preset priority requirements.

[0074] The preset priority requirement is a pre-set priority that meets the user's needs. For example, when the device set includes three devices, device A, device B, and device C, the initial wake-up priorities are A, B, and C, with device A having the highest priority and device C having the lowest. When the preset priority requirement is that device A has the highest priority, the initial wake-up priority meets the preset priority requirement, and no adjustment to the initial wake-up voice signal-to-noise ratio (SNR) is needed. When the preset priority requirement is that device B has the highest priority, the initial wake-up priority does not meet the preset priority requirement. Therefore, the SNR of device B, which does not meet the preset priority requirement, is determined, and its SNR weight is increased until the device meets the preset priority requirement.

[0075] In one embodiment, the step of determining the initial wake-up priority for each device based on the initial speech signal-to-noise ratio specifically includes:

[0076] S11110, arrange the initial wake-up voice signal-to-noise ratios in descending order to obtain the initial sorting results.

[0077] S11111, use the initial sorting result as the initial wake-up priority order of the device.

[0078] S11112, determine the initial wake-up priority of each device according to the initial wake-up priority order.

[0079] In one embodiment, the step of increasing the signal-to-noise ratio weight of a determined initial speech signal-to-noise ratio until the device meets a preset priority requirement specifically includes:

[0080] S11130, determine the first initial wake-up voice signal-to-noise ratio of the device with the highest priority corresponding to the initial wake-up priority.

[0081] S11131, Determine the second initial wake-up voice signal-to-noise ratio of the device corresponding to the preset priority requirement.

[0082] S11132, calculate the signal-to-noise ratio difference between the second initial wake-up speech signal-to-noise ratio and the first initial wake-up speech signal-to-noise ratio as the signal-to-noise ratio weight.

[0083] As illustrated above, the smart home system includes devices A, B, and C. Device A has the highest initial wake-up priority, while the preset priority requirement is that device B has the highest priority. The initial wake-up voice signal-to-noise ratio (SNR) for device A is 'a', and for device B it is 'b'. The SNR difference 'ab' between device A and device B is calculated. This SNR difference 'ab' is added to the preset value and then added to the initial wake-up voice SNR 'b' for device B, ensuring that device B has the highest initial wake-up voice SNR and thus meets the preset priority requirement. The preset value is a pre-set value and is not restricted here.

[0084] In one embodiment, the signal-to-noise ratio (SNR) weights are summed with the initial wake-up speech SNR to obtain the target wake-up speech SNR. Optionally, the step of adjusting the initial speech SNR according to the SNR weights to obtain the target speech SNR for each device specifically includes:

[0085] S1120, calculate the sum of the signal-to-noise ratio (SNR) of the weighted SNR and the initial speech SNR.

[0086] S1121 uses the sum of signal-to-noise ratios as the target speech signal-to-noise ratio for each device.

[0087] S12, determine the target device based on the target speech signal-to-noise ratio.

[0088] In at least one embodiment of this application, the target wake-up voice signal-to-noise ratio can reflect the distance between the device and the master device after eliminating the differences between the devices. The larger the target wake-up voice signal-to-noise ratio, the closer the corresponding device is to the master device, and the higher the priority is given to the corresponding device. The smaller the target wake-up voice signal-to-noise ratio, the closer the corresponding device is to the master device, and the lower the priority is given to the corresponding device.

[0089] Combination Figure 3 This application describes the process for determining the target device according to its embodiments. Optionally, the step of determining the target device based on the target speech signal-to-noise ratio specifically includes:

[0090] S120: Sort the target speech signal-to-noise ratios in descending order to obtain the sorting results.

[0091] S121, use the sorting results as the priority order for each device to be woken up.

[0092] S122, determine the wake-up priority of each device according to the wake-up priority order.

[0093] S123, determine the device with the highest wake-up priority as the target device.

[0094] The target wake-up speech signal-to-noise ratio (SNR) for each device may be the same or different. When two devices have the same target wake-up speech SNR, it indicates that the distance between these two devices and the wake-up location is the same; when the target wake-up speech SNR for any two devices is different, it indicates that the distance between these two devices and the wake-up location is different.

[0095] Taking a whole-house smart system containing devices A, B, and C as an example, when devices A and B have the same target wake-up voice signal-to-noise ratio (SNR), the SNRs are sorted in descending order, resulting in a sorted order of A, B, C. The corresponding wake-up priority order is also A, B, C. Since devices A and B have the same target wake-up voice SNR, their priorities are the same (1), while device C has a priority of 2. When there are two devices with the highest wake-up priority (i.e., devices A and B in this embodiment), in one embodiment, one of them can be randomly selected as the target device; for example, device A can be randomly selected. In other embodiments, a fixed device can be selected as the target device according to requirements. For example, a fixed rule can be preset so that when device A has the same target wake-up voice SNR as any other device, device A is always selected as the target device.

[0096] Taking a smart home system containing devices A, B, and C as an example, when the target wake-up voice signal-to-noise ratios (SNRs) are different for each of devices A, B, and C, the target wake-up voice SNRs are sorted in descending order, resulting in the sorting order: A, B, C. The corresponding wake-up priority order is also A, B, C. In this case, device A has the highest priority (1), device B has the highest priority (2), and device C has the highest priority (3). Device A is then selected as the target device.

[0097] S13, send a wake-up command to the target device to wake up the target device.

[0098] In at least one embodiment of this application, after determining the device with the highest wake-up priority as the target device, a wake-up command is sent to the target device. The wake-up command is a pre-set command for waking up the device. When the target device receives the wake-up command, it performs the wake-up processing operation.

[0099] The device proximity wake-up method in the whole-house smart system provided in this application embodiment determines the signal-to-noise ratio (SNR) weight corresponding to each device, adjusts the initial wake-up voice SNR according to the SNR weight to obtain the target wake-up voice SNR, and determines the wake-up priority corresponding to each device according to the target wake-up voice SNR. Then, the device with the highest wake-up priority is selected as the target wake-up device. This can avoid the problem of inaccurate proximity caused by the difference between wake-up devices and improve the accuracy of proximity wake-up.

[0100] Please see Figure 4 , Figure 4 This is a structural diagram of a device wake-up device in a whole-house smart system according to an embodiment of this application. In some embodiments, the device wake-up device 20 in the whole-house smart system may include multiple functional modules composed of computer program segments. The computer programs of each program segment in the device wake-up device 20 in the whole-house smart system may be stored in the memory of a computer device and executed by at least one processor to perform (see details). Figure 1 (Description) The function of waking up from the nearest location.

[0101] In this embodiment, the device proximity wake-up device 20 in the whole-house smart system can be divided into multiple functional modules according to its function. Taking the device proximity wake-up device 20 applied to the main device in the whole-house smart system as an example, the functional modules may include: a signal-to-noise ratio determination module 201, a device determination module 202, and a wake-up processing module 203. The module referred to in this application is a series of computer program segments that can be executed by at least one processor and can perform a fixed function, and which are stored in memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0102] The signal-to-noise ratio determination module 201 can be used to determine the target voice signal-to-noise ratio for the wake-up voice corresponding to each device in the whole-house smart system.

[0103] The device determination module 202 can be used to determine the target device based on the target speech signal-to-noise ratio.

[0104] The wake-up processing module 203 can be used to send a wake-up command to the target device to perform wake-up processing on the target device.

[0105] See Figure 5 The diagram shown is a structural schematic of a computer device provided in an embodiment of this application. In a preferred embodiment of this application, the computer device 3 includes a memory 31, at least one processor 32, at least one communication bus 33, and a transceiver 34.

[0106] Those skilled in the art should understand that Figure 5The structure of the computer device shown does not constitute a limitation of the embodiments of this application. It can be a bus structure or a star structure. The computer device 3 may also include more or fewer other hardware or software than shown, or different component arrangements.

[0107] In some embodiments, the computer device 3 is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices. The computer device 3 may also include client devices, which include, but are not limited to, any electronic product that can interact with a client via a keyboard, mouse, remote control, touchpad, or voice control device, such as a personal computer, tablet computer, smartphone, or digital camera.

[0108] It should be noted that computer device 3 is only an example. Other existing or future electronic products that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0109] In some embodiments, the memory 31 stores a computer program that, when executed by at least one processor 32, implements all or part of the steps in a proximity wake-up method. The memory 31 includes read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0110] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of the computer device 3, etc.

[0111] In some embodiments, at least one processor 32 is the control unit of the computer device 3, connecting various components of the computer device 3 via various interfaces and lines. It executes programs or modules stored in the memory 31 and calls data stored in the memory 31 to perform various functions and process data. For example, when at least one processor 32 executes a computer program stored in the memory, it implements all or part of the steps of the proximity wake-up method in this embodiment; or it implements all or part of the functions of the proximity wake-up device. At least one processor 32 may be composed of integrated circuits, such as a single-packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips.

[0112] In some embodiments, at least one communication bus 33 is configured to enable communication between the memory 31 and at least one processor 32, etc.

[0113] Although not shown, the computer device 3 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to at least one processor 32 via a power management device, thereby enabling functions such as charging, discharging, and power consumption management. The power supply may also include one or more DC or AC power sources, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The computer device 3 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0114] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, a computer device, or a network device, etc.) or a processor to execute portions of the methods of the various embodiments of this application.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0116] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0118] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that it can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other elements or, and the singular does not exclude the plural. Multiple elements or devices recited in the specification may also be implemented by a single element or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A method for waking up devices in a whole-house smart system, characterized in that, The method includes: A target speech signal-to-noise ratio (SNR) is determined for each device's wake-up voice. This target SNR reflects the distance between each device and the wake-up location. The target SNR is obtained by adjusting the initial SNR of the wake-up voice for each device based on SNR weights. Determining the SNR weights includes: determining the initial SNR of the wake-up voice for each device; determining the initial wake-up priority for each device based on the initial SNR; determining the initial SNR of the device that does not meet the preset priority requirement when the initial wake-up priority does not meet the preset priority requirement; and increasing the SNR weight of the determined initial SNR until the device meets the preset priority requirement. The target device is determined based on the target speech signal-to-noise ratio. The higher the target speech signal-to-noise ratio, the higher the wake-up priority of the corresponding device. The target device has the highest wake-up priority. A wake-up command is sent to the target device to wake it up.

2. The method for waking up devices in a smart home system according to claim 1, characterized in that, The step of determining the target speech signal-to-noise ratio for the wake-up speech of each device specifically includes: Determine the initial speech signal-to-noise ratio for each device corresponding to the wake-up voice; Determine the signal-to-noise ratio weight corresponding to each device; The initial speech signal-to-noise ratio is adjusted according to the signal-to-noise ratio weight to obtain the target speech signal-to-noise ratio for each device.

3. The method for waking up devices in a whole-house smart system according to claim 2, characterized in that, The step of increasing the signal-to-noise ratio weight of the determined initial speech signal-to-noise ratio until the device meets the preset priority requirement specifically includes: Determine the first initial wake-up voice signal-to-noise ratio of the device with the highest priority corresponding to the initial wake-up priority; Determine the second initial wake-up voice signal-to-noise ratio of the device corresponding to the preset priority requirement; The signal-to-noise ratio difference between the second initial wake-up speech signal-to-noise ratio and the first initial wake-up speech signal-to-noise ratio is calculated as the signal-to-noise ratio weight.

4. The method for waking up devices in a whole-house smart system according to claim 2, characterized in that, The step of adjusting the initial speech signal-to-noise ratio according to the signal-to-noise ratio weight to obtain the target speech signal-to-noise ratio for each device specifically includes: Calculate the sum of the signal-to-noise ratio (SNR) of the SNR weights and the initial speech SNR; The signal-to-noise ratio and value are used as the target speech signal-to-noise ratio for each device.

5. The method for waking up devices in a smart home system according to claim 1, characterized in that, The step of determining the target device based on the target speech signal-to-noise ratio specifically includes: The target speech signal-to-noise ratios are sorted in descending order to obtain the sorting results; The sorting results shall be used as the priority order for waking up each device. The wake-up priority of each device is determined according to the wake-up priority order; The device with the highest priority to be woken up is identified as the target device.

6. The method for waking up devices in a whole-house smart system according to claim 1, characterized in that, The step of determining the initial speech signal-to-noise ratio for each device corresponding to the wake-up speech specifically includes: Determine the voice area audio and the silence area audio corresponding to the wake-up voice for each device; Spectral analysis was performed on the audio from the speech region and the audio from the silence region respectively to obtain the power spectrum of the speech region and the power spectrum of the silence region; The power value corresponding to the power spectrum of the speech region is determined to be the speech signal power, and the power value corresponding to the power spectrum of the silence region is determined to be the noise signal power. The ratio of the speech signal power to the noise signal power is calculated as the initial speech signal-to-noise ratio.

7. A device for nearby wake-up in a whole-house smart system, characterized in that, The device includes: The signal-to-noise ratio (SNR) determination module is used to determine the target SNR of the wake-up voice for each device in the whole-house smart system. The target SNR reflects the distance between each device and the wake-up location. The target SNR is obtained by adjusting the initial SNR of the wake-up voice for each device according to the SNR weight. The determination of the SNR weight includes: determining the initial SNR of the wake-up voice for each device; determining the initial wake-up priority for each device based on the initial SNR; when the initial wake-up priority does not meet the preset priority requirement, determining the initial SNR of the device that does not meet the preset priority requirement; and increasing the SNR weight of the determined initial SNR until the device meets the preset priority requirement. The device determination module is used to determine the target device based on the target speech signal-to-noise ratio. The higher the target speech signal-to-noise ratio, the higher the wake-up priority of the corresponding device. The target device has the highest wake-up priority. The wake-up processing module is used to send a wake-up command to the target device to perform wake-up processing on the target device.

8. A computer device, characterized in that, The computer device includes a processor that executes a computer program stored in a memory to implement the device wake-up method in a whole-house smart system as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is executed by the processor, it implements the device wake-up method in the whole-house smart system as described in any one of claims 1 to 6.

Images